KR20240083927A - Method, server and user terminal for providing an image of a speaker based on an utterance message - Google Patents

Abstract

A method of providing a speaker image based on a speech message of the present invention includes the steps of storing a keyword dictionary including a plurality of keywords, obtaining an input of a speech message, and at least a portion of the speech message is a specific keyword among the plurality of keywords. determining whether the speech message corresponds to the specific keyword, identifying a speaker image corresponding to the specific keyword, and at least one of information on the specific keyword and information on the speaker image. It includes matching the speech message and providing it to the server.

Description

Method, terminal and server for providing an image of a speaker based on an utterance message {Method, server and user terminal for providing an image of a speaker based on an utterance message}

The present invention relates to a messenger service, and more specifically, to a technology for providing a speaker image matching a spoken message.

With the development of wireless communication, various social media services are widely provided. Using these social media services, users can communicate with others and actively express their thoughts. Additionally, users can more actively convey their thoughts, feelings, status, news, etc. to the other person in the form of spoken messages through the instant messaging service. The spoken messages exchanged at this time may include text, images, videos, emoticons, etc. In addition, there are attempts to convey thoughts or emotions in a more detailed and intuitive way through various information.

Some messenger services provide a function where, when a user uploads his or her profile photo to the server, the profile photo is displayed as the speaker's image in the spoken message. Since this speaker image is displayed along with the speech message on the other terminal, it can be useful as a means of conveying the speaker's thoughts or emotions.

Therefore, some messenger services are attempting various functions related to the speaker image displayed along with the speech message. For example, there is a function in which a user uploads multiple profile photos and, depending on who the conversation partner is, one of the multiple profile photos is selected and used as the speaker image.

Recently, there is an increasing demand for a function that can change the speaker image more dynamically according to the conversation situation.

Republic of Korea Patent Publication No. 10-1882293

The purpose of the present invention is to improve user convenience by providing a messenger service with the user's intention or state inferred through the spoken message through an image.

A method of providing a speaker image based on a speech message of the present invention includes the steps of storing a keyword dictionary including a plurality of keywords, obtaining an input of a speech message, and at least a portion of the speech message is a specific keyword among the plurality of keywords. determining whether the speech message corresponds to the specific keyword, identifying a speaker image corresponding to the specific keyword, and at least one of information on the specific keyword and information on the speaker image. It includes matching the speech message and providing it to the server.

In one embodiment of the present invention, the step of displaying the speaker image to correspond to the spoken message in the chat room may be further included.

In one embodiment of the present invention, an image of the speaker based on the speech message can be provided.

In one embodiment of the present invention, the displaying step may include obtaining an interaction with the speaker image displayed and, in response to the interaction, displaying a user's profile page including the speaker image. .

In one embodiment of the present invention, the method further includes storing a speaker image set including at least one speaker image matching at least some of the plurality of keywords, and in the step of identifying the speaker image, the user The terminal can identify the speaker image corresponding to the specific keyword among the speaker image set.

In one embodiment of the present invention, the method further includes obtaining information about the concept of the speaker image, and at least one speaker image included in the speaker image set may be related to the concept.

In one embodiment of the present invention, the step of providing to the server is performed before the step of identifying the speaker image, and in the step of providing to the server, the at least one keyword is the specific keyword, and the speaker image is the specific keyword. It may be received from the server in response to providing a keyword to the server.

In one embodiment of the present invention, the method further includes obtaining information about the concept of the speaker image, and providing information about the concept to the server, wherein the speaker image includes the concept and It can be related.

In one embodiment of the present invention, the spoken message includes multimedia information - the multimedia information is at least one of emoticons, image information, photo information, and video information - and the step of determining whether the speech message corresponds to the specific keyword includes: It may include identifying matching text corresponding to multimedia information and determining whether the matching text corresponds to a specific keyword among the plurality of keywords.

In one embodiment of the present invention, determining whether at least some of the spoken messages correspond to recommended keywords among the plurality of keywords; and if at least some of the spoken messages correspond to the recommended keywords, they correspond to the recommended keywords. and displaying a recommended emoticon, wherein a keyword corresponding to the specific keyword among the plurality of keywords may correspond to a portion of keywords corresponding to the recommended keyword.

In one embodiment of the present invention, at least a portion of the utterance message includes a first part corresponding to a first specific keyword and a second part corresponding to a second specific keyword, and the first specific keyword is the second specific keyword. 2 If priority is given to a specific keyword according to a preset standard, a step of identifying the first specific keyword as the specific keyword may be provided, and an image of the speaker based on the speech message may be provided.

In one embodiment of the present invention, when identifying a speaker image corresponding to the specific keyword, displaying the speaker image and a confirmation interface and obtaining a confirmation interaction for the confirmation interface are used to display the speaker image and the confirmation interface. The method may further include matching at least one of information and information on the speaker image to the speech message and providing the information to the server.

The user terminal that identifies the speaker image based on the speech message of the present invention includes a memory and a processor connected to the memory and configured to execute instructions contained in the memory, wherein the processor includes a keyword dictionary containing a plurality of keywords. Storing, obtaining a speech message, determining whether at least some of the speech messages correspond to a specific keyword among the plurality of keywords, if at least some of the speech messages correspond to the specific keyword, the specific keyword Identifying a speaker image corresponding to a keyword and matching at least one of information on the specific keyword and information on the speaker image to the speech message and providing the information to the server.

A method of displaying a speaker image based on a speech message of the present invention includes receiving at least one general speech message and a basic speaker image transmitted by a speaker terminal from a server, and displaying the at least one general speech message and the basic speaker image in a chat room. Displaying - the basic speaker image is displayed to correspond to at least a portion of the at least one general speech message -, a specific speech message transmitted by the speaker terminal from the server and a specific speaker image matched to the specific speech message. Receiving information and displaying the specific speech message and the specific speaker image in the chat room - the specific speaker image is displayed to correspond to the specific speech message.

In one embodiment of the present invention, the specific speaker image may be displayed together with the basic speaker image.

In one embodiment of the present invention, the specific speaker image may include a first image displayed in the profile area corresponding to the specific speech message and a second image displayed in the text area corresponding to the specific speech message. there is.

In one embodiment of the present invention, it includes obtaining an interaction with the basic speaker image or the specific speaker image displayed in the chat room, and displaying a profile page including a specific profile image in response to the interaction. can do.

In one embodiment of the present invention, the specific profile image may be a specific speaker image matched to at least one of status information of the speaker terminal, media information of the speaker terminal, and the specific speech message.

In one embodiment of the present invention, in the step of displaying the specific speech message and the specific speaker image in the chat room, the specific speaker image is displayed when the step of receiving the specific speech message satisfies a preset time condition. It can only be displayed.

In one embodiment of the present invention, the preset time condition may be that the specific utterance message and the last message are received within one time interval.

A user terminal that displays a speaker image based on a speech message of the present invention includes a memory and a processor connected to the memory and configured to execute instructions contained in the memory, wherein the processor includes a plurality of messages transmitted by the speaker terminal from the server. receiving a general speech message and a basic speaker image, displaying the plurality of general speech messages and the basic speaker image in a chat room, wherein the basic speaker image is displayed to correspond to at least some of the plurality of general speech messages. , receiving information on a specific speech message transmitted by the speaker terminal and a specific speaker image matched to the specific speech message from the server, and displaying the specific speech message and the specific speaker image in the chat room - the specific speech message The speaker image is displayed to correspond to the specific speech message.

A method of providing a speaker image based on a speech message of the present invention includes providing a keyword dictionary including a plurality of keywords to a first user terminal, and at least one speaker image matching at least some of the plurality of keywords. Providing a speaker image set to the first user terminal, if at least some of the speech messages obtained by the first user terminal correspond to a specific keyword among the plurality of keywords, the speaker image set corresponds to the specific keyword Obtaining information on the speaker image and the speech message from the first user terminal and providing the information on the speaker image and the speech message to the second user terminal.

In one embodiment of the present invention, when the second user terminal obtains interaction with the speaker image information, the step of providing a profile page including a specific profile image to the second user terminal may be further included. there is.

In one embodiment of the present invention, the specific profile image may be a specific speaker image matched to at least one of status information of the speaker terminal, media information of the speaker terminal, and the specific speech message.

In one embodiment of the present invention, the method further includes providing information about the concept of the speaker image to the first user terminal, wherein at least one speaker image included in the speaker image set is related to the concept. You can.

A server that provides a speaker image based on a speech message of the present invention includes a memory and a processor connected to the memory and configured to execute instructions contained in the memory, wherein the processor includes a keyword dictionary containing a plurality of keywords. Providing to a first user terminal, providing a speaker image set including at least one speaker image matching at least some of the plurality of keywords to the first user terminal, utterance acquired by the first user terminal When at least part of the message corresponds to a specific keyword among the plurality of keywords, obtaining information on a speaker image corresponding to the specific keyword among the speaker image set and the speech message from the first user terminal, and the speaker image The step of providing the information and the speech message to the second user terminal is performed.

The apparatus and method of the present invention have the advantage of improving user convenience by providing the user's intention or state inferred through the spoken message through an image in the messenger service.

1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention.
Figure 2 is a flowchart of the operation of a first user terminal according to an embodiment of the present invention.
Figure 3 is a flowchart of operations between devices according to an embodiment of the present invention.
Figure 4 is another flowchart of operations between devices according to an embodiment of the present invention.
Figure 5 exemplarily illustrates a speaker image set according to an embodiment of the present invention.
Figure 6 illustrates an utterance message and a speaker image displayed on a chat room screen of a second user terminal according to an embodiment of the present invention.
Figure 7 illustrates an utterance message and a speaker image displayed on the profile page of a user terminal according to an embodiment of the present invention.
FIG. 8 illustrates screens of a first user terminal and a second user terminal when a plurality of input texts correspond to matching texts in a speech message according to an embodiment of the present invention.
Figure 9 illustrates a preview screen of a speaker image and a spoken message displayed on a first user terminal according to an embodiment of the present invention.
Figure 10 illustrates a speaker image and speech message displayed on the first user terminal according to an embodiment of the present invention.
Figure 11 is a flowchart of the operation of a server according to an embodiment of the present invention.

Hereinafter, embodiments disclosed in the present specification will be described in detail with reference to the attached drawings. However, identical or similar components will be assigned the same reference numbers regardless of reference numerals, and duplicate descriptions thereof will be omitted. Additionally, in describing the embodiments disclosed in this specification, if it is determined that detailed descriptions of related known technologies may obscure the gist of the embodiments disclosed in this specification, the detailed descriptions will be omitted.

Terms containing ordinal numbers, such as first, second, etc., may be used to describe various components, but the components are not limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.

Singular expressions include plural expressions unless the context clearly dictates otherwise.

In this application, each step described may be performed regardless of the listed order, except when it must be performed in the listed order due to a specific causal relationship.

In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Hereinafter, the present invention will be described with reference to the attached drawings.

1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention.

The network environment according to an embodiment of the present invention shown in FIG. 1 may include a server 10, a first user terminal 20, and a second user terminal 30.

The server 10 is a device that provides messenger services to user terminals. The user terminals exemplified by the first user terminal 20 and the second user terminal 30 are devices that use the messenger service provided by the server 10.

Hereinafter, both the first user terminal 20 and the second user terminal 30 can send or receive messages to each other through a messenger service. However, for convenience of explanation, while referring to FIGS. 2 to 10 below, the first user terminal 20 is a speaker terminal that transmits a speech message, and the second user terminal 30 is a speaker terminal that transmits a speech message. This will be explained by assuming that it is a recipient terminal that receives and displays the uttered speech message.

The messenger service may be a service that allows a plurality of users to send or receive messages to each other through a platform provided by the server 10. Here, a message can be understood to include all data that can be transmitted, such as text, photos, videos, voice files, and emoticons.

The network is not limited to communication methods, and may include not only communication methods utilizing communication networks that the network may include (e.g., mobile communication networks, wired Internet, wireless Internet, and broadcasting networks), but also short-distance wireless communications.

The server 10 may be implemented as a computer device or a plurality of computer devices that provide commands, codes, files, content, services, etc. The server 10 may be a server 10 capable of transmitting and receiving information by communicating with a user terminal over a network.

The server 10 may include a processor 11, a memory 12, and a communication unit 13.

The processor 11 can control the overall operation of the memory 12 and the communication unit 13 to provide a messenger service to the user terminal.

The memory 12 functions as a storage medium and can store a number of application programs running on the server 10, data for operation of the server 10, and commands. In one embodiment, an application related to a messenger service may be stored in the memory 12.

In terms of hardware, the memory 12 may be provided in the form of various storage devices such as ROM, RAM, flash drive, hard drive, etc., or may be provided in the form of web storage.

The communication unit 13 can communicate with a user terminal in a wired/wireless manner through a network.

The server 10 of the present invention provides a keyword dictionary including a plurality of keywords to the first user terminal 20, and provides a speaker image set including at least one speaker image matching at least some of the plurality of keywords. 1 If at least part of the speech message provided to the user terminal 20 and acquired by the first user terminal 20 corresponds to a specific keyword among a plurality of keywords, information on the speaker image corresponding to the specific keyword among the speaker image set And the speech message is acquired from the first user terminal 20, and information on the speaker image and the speech message are provided to the second user terminal 30.

Here, the keyword dictionary is a database used by the server 10 to determine the speaker image corresponding to the speech message acquired by the first user terminal 20.

A keyword dictionary may be a database storing a plurality of keywords and matching text corresponding to each keyword. Specifically, multiple matching texts with the same or similar meaning may correspond to one keyword. For example, matching texts such as 'thank you', 'thank you', 'thank you', and 'thank you' may be stored in correspondence to one keyword called 'thank you'. At least one keyword stored in the keyword dictionary can be distinguished and identified through a keyword identifier.

In some cases, such a keyword dictionary may not only be used to determine the image of the speaker, but may also be used to recommend emoticons. Specifically, the keyword dictionary may include recommended keywords for recommending emoticons. If at least part of the uttered message corresponds to a recommended keyword, the first user terminal 20 may display an emoticon corresponding to the recommended keyword as a recommended emoticon.

In this case, some of the keywords included in the keyword dictionary may correspond to specific keywords for determining the image of the speaker, or may correspond to recommended keywords for recommending emoticons. Changing and displaying a speaker image to a specific speaker image may be recommended more rarely than recommending emoticons. Therefore, among a plurality of keywords, a specific keyword for determining the speaker image may correspond to a part (subset) of recommended keywords for recommending emoticons. For example, if the keyword dictionary contains 5,000 recommended keywords for recommending emoticons, the specific keywords for determining the speaker image may be designated as 300 of the 5,000 recommended keywords.

Here, the spoken message may be text input by the first user through a messenger service. The spoken message may include a chat message entered by the first user in a chat room of the messenger service, and a status message of the first user displayed along with the profile image or displayed on the profile page. The utterance message may include at least one input text that is compared with matching text in the keyword dictionary.

Here, the speaker image may be an image of the speaker displayed in a specific area corresponding to the spoken message in the user terminal through the messenger service. The specific area is an area related to the spoken message and may be an area displayed in a chat room in which the speaker participates. Specifically, it may be an area displayed on the left or right side of the spoken message to display the speaker of the spoken message. This speaker image may be displayed on at least one of the speaker terminal participating in the chat room and the recipient terminal of the spoken message.

Additionally, the speaker image may be displayed in some areas of the speaker's profile page. The profile page may display the name or nickname selected by the user, profile image, status message, background image, etc. The speaker image may be the same as the profile image or may temporarily replace the profile image.

Here, the specific keyword may be a keyword corresponding to the input text of the speech message among a plurality of keywords. More specifically, if the input text included in the speech message exists among matching texts stored in the keyword dictionary, the keyword corresponding to the matching text may be referred to as a specific keyword.

The first user terminal 20 is a terminal device that obtains a speech message from the first user and provides at least one of the speech message, speaker image, or specific keyword to the server 10. The first user terminal 20 may include a communication unit 21, an input unit 22, an output unit 23, a memory 24, and a processor 25.

The communication unit 21 can communicate with the server 10 or other terminals in a wired/wireless manner.

The input unit 22 can receive various information through the user's manipulation and input actions. Such input units may include a touch screen module, keyboard, mouse, button, camera, stylus, and microphone.

The first user terminal 20 can receive user interaction through the input unit 22. Interaction means that the user manipulates the input unit 22 and inputs information reflecting the user's selection or intention into the first user terminal 20. For example, interaction may be touching a touch screen, clicking a mouse, typing on a keyboard, inputting sound from a microphone, capturing an image from a camera, or recognizing a motion using a motion sensor.

The output unit 23 can output various information. The output unit 23 may be a display device, a speaker, a vibration generator, a tactile generator, etc. In some cases, the output unit 23 may be a device (e.g., Bluetooth earphones) that is connected to the user terminal through wired or wireless communication (e.g., short-range wireless communication such as Bluetooth) to receive and output a signal. .

The memory 24 functions as a storage medium and can store a number of application programs running on the user terminal, data for operation of the first user terminal 20, and commands. Such memory may be provided in the form of various storage devices such as hardware, ROM, RAM, flash drive, hard drive, etc., or in the form of web storage. In one embodiment, an application (hereinafter referred to as “application”) related to a messenger service may be stored in the memory 24.

The processor 25 can execute an application by controlling the overall operation of the communication unit 21, input unit 22, output unit 23, and memory 24.

The first user terminal 20 of the present invention stores a keyword dictionary containing a plurality of keywords, obtains an input of a speech message, determines whether at least a part of the speech message corresponds to a specific keyword among the plurality of keywords, and When at least part of the message corresponds to a specific keyword, the speaker image corresponding to the specific keyword is identified, and at least one of information on the specific keyword and information on the speaker image is matched to the speech message and provided to the server.

The second user terminal 30 is a terminal device corresponding to the second user in the present invention, and is the same or similar to the first user terminal 20. The second user is a user who participated in the same chat room as the first user. The second user terminal 30 may include a communication unit 31, an input unit 32, an output unit 33, a memory 34, and a processor 35. Each detailed configuration included in the second user terminal 30 performs substantially the same function as each detailed configuration included in the first user terminal 20.

The second user terminal 30 may receive and display the speech message or speaker image generated by the first user terminal 20 from the server 10. At this time, the utterance message or speaker image may include a specific utterance message or a specific speaker image related to a specific keyword in the keyword dictionary. Additionally, the speech message or speaker image may include a general speech message or basic speaker image that is not related to a specific keyword in the keyword dictionary.

The second user terminal 30 of the present invention receives a plurality of general speech messages and basic speaker images transmitted by the speaker terminal from the server, displays a plurality of general speech messages and basic speaker images in the chat room, and transmits the plurality of general speech messages and basic speaker images from the server. It receives information on the transmitted specific speech message and the specific speaker image matched to the specific speech message, and displays the specific speech message and the specific speaker image in the chat room.

Here, the basic speaker image and the specific speaker image may be distinguished depending on whether the speech message corresponding to each is related to at least one of a plurality of keywords. Specifically, when the input text included in the speech message exists among matching texts stored in the keyword dictionary and displays a speaker image different from other existing cases, the speaker image may be referred to as a specific speaker image. At this time, the corresponding speech message may be referred to as a specific speech message.

Conversely, a speaker image corresponding to the existing general speech message of the speaker, rather than the specific speaker image described above, may be referred to as a basic speaker image. At this time, the corresponding speech message may be referred to as a general speech message.

Figure 2 is a flowchart of the operation of a user terminal according to an embodiment of the present invention.

Each step in FIG. 2 can be performed regardless of the listed order, except when it must be performed in the listed order due to a special causal relationship. However, hereinafter, for convenience of explanation, the description will be made assuming that each of the above-described steps is performed in the listed order.

In step S110, the first user terminal 20 obtains an input of a spoken message.

The first user may provide input text constituting the speech message to the first user terminal 20. The spoken message may be an input obtained through a messenger service. For example, the first user may provide a chat message through a chat window of the messenger service or provide a status message through the profile setting interface of the messenger service.

In step S120, the first user terminal 20 determines whether at least part of the uttered message corresponds to a specific keyword among a plurality of keywords.

The first user terminal 20 may analyze the speech message and identify at least one input text constituting the speech message. Additionally, the first user terminal 20 may identify matching texts that each correspond to a plurality of keywords stored in the keyword dictionary. Thereafter, the first user terminal 20 may determine whether at least one input text exists among matching texts in the keyword dictionary. If at least one input text exists among the matching texts, the first user terminal 20 may identify a keyword corresponding to the same matching text as the at least one input text as a specific keyword.

In some cases, the speech message may include multimedia information. Multimedia information may be at least one of emoticons, image information, photo information, and video information. Even in this case, the first user terminal 20 can determine whether at least part of the uttered message corresponds to a specific keyword among a plurality of keywords.

Specifically, the first user terminal 20 can identify matching text corresponding to multimedia information. For example, if the multimedia information is an emoticon, the matching text may be a keyword corresponding to the emoticon. Thereafter, the first user terminal 20 may determine whether the matching text corresponds to a specific keyword among a plurality of keywords.

In step S130, when at least part of the speech message corresponds to a specific keyword, the first user terminal 20 identifies the speaker image corresponding to the specific keyword.

A plurality of keywords stored in the keyword dictionary may each have a corresponding speaker image. A set of speaker images corresponding to a plurality of keywords may be referred to as a speaker image set. The speaker image set may be stored in the server 10, or the first user terminal 20 may receive it from the server 10 and store it. Step S130 illustrates a case where a speaker image set is stored in the first user terminal 20. In this case, the first user terminal 20 may identify a speaker image corresponding to a specific keyword among a set of previously stored speaker images.

In step S140, the first user terminal 20 matches at least one of information on a specific keyword and information on the speaker image to the speech message and provides the information to the server.

The first user terminal 20 may match the speaker image identified in step S130 to the speech message and transmit it to the server 10. Matching and transmitting the speaker image to the speech message may mean transmitting the speaker image so that it is displayed on the user terminal as related to the speech message. Accordingly, the user terminal that receives the speaker image and speech message from the server 10 can display the speaker image and speech message together.

If the speaker image set is not stored in the first user terminal 20, the first user terminal may perform step S140 before step S130. More specifically, when at least part of the utterance message corresponds to a specific keyword, the first user terminal 20 may transmit the specific keyword to the server. Thereafter, when the server storing the speaker image set transmits the speaker image corresponding to a specific keyword to the first user terminal 20, the first user terminal 20 can identify the received speaker image.

Figure 3 is a flowchart of operations between devices according to an embodiment of the present invention.

Figure 3 illustrates the operation between the server 10 and the user terminal when the speaker image set is stored in the first user terminal 20.

The server 10 provides a keyword dictionary to the first user terminal 20 (S301). The first user terminal 20 obtains and stores a keyword dictionary (S303).

The server 10 provides a speaker image set to the first user terminal 20 (S305). Here, the speaker image set may include speaker images corresponding to a plurality of keywords stored in the keyword dictionary.

To this end, the first user terminal 20 is provided with a list of selectable speaker image set concepts (character, text, picture style, theme, mood, etc.) from the server 10, and can select one of them. The server 10 may provide a keyword dictionary or a speaker image set to the first user terminal 20 based on the concept selected by the first user.

For example, when the first user sets a concept for the speaker image and the first user terminal 20 provides it to the server, a plurality of keywords included in the keyword dictionary provided by the server correspond to the selected concept. It may be a keyword corresponding to the speaker image in the speaker image set.

Therefore, before the first user terminal 20 obtains the keyword dictionary from the server 10, the first user terminal 20 provides information about the concept of the speaker image to the server 10. You can.

The first user terminal 20 obtains and stores the speaker image set from the server 10 (S307).

When a speech message is input from the first user (S309), the first user terminal 20 determines whether at least a part of the speech message corresponds to a specific keyword among a plurality of keywords (S311).

If a part of the speech message does not correspond to a specific keyword, the first user terminal 20 identifies the input speech message as a general speech message. A general speech message is transmitted from the first user terminal 20 to the server 10 (S304a), and the server 10 may provide a general speech message and a basic speaker image to the second user terminal 30 (S304b). ). In this case, the second user terminal 30 obtains and displays a general speech message and a basic speaker image (S306).

When a part of the speech message corresponds to a specific keyword, the first user terminal 20 identifies the speaker image corresponding to the specific keyword from the speaker image set (S313).

The first user terminal 20 provides information about the identified speaker image to the server 10 (S315). Information about the speaker image may be a speaker image file or identification information of the speaker image. At this time, information about the speaker image may be matched to the accompanying speech message and provided to the server (S315, S317).

The server 10 provides the acquired speaker image information and speech message to the second user terminal 30 as specific speaker image information and a specific speech message (S319). The second user terminal 30 obtains and displays specific speaker image information and a specific speech message from the server 10 (S321).

Figure 4 is another flowchart of operations between devices according to an embodiment of the present invention.

Figure 4 illustrates the operation between the server 10 and the user terminal when the speaker image set is stored in the server 10.

The server 10 provides a keyword dictionary to the first user terminal 20 (S401). The first user terminal 20 obtains and stores a keyword dictionary (S403).

Thereafter, when a speech message is input from the first user (S405), the first user terminal 20 determines whether at least a part of the speech message corresponds to a specific keyword among a plurality of keywords (S407).

If a part of the speech message does not correspond to a specific keyword, the first user terminal 20 identifies the input speech message as a general speech message. A general speech message is transmitted from the first user terminal 20 to the server 10 (S404a), and the server 10 may provide a general speech message and a basic speaker image to the second user terminal 30 (S404b). ). In this case, the second user terminal 30 obtains and displays a general speech message and a basic speaker image (S406).

When a part of the spoken message corresponds to a specific keyword, the first user terminal 20 provides information on the specific keyword to the server 10 (S409).

The server 10 determines whether a speaker image corresponding to a specific keyword exists (S411). Specifically, the server 10 determines whether a speaker image corresponding to a specific keyword exists from the stored speaker image set.

Here, the speaker image set may include speaker images corresponding to a plurality of keywords stored in the keyword dictionary. The keyword dictionary or speaker image set may be determined based on information about the concept preset by the first user. Therefore, before the server 10 provides the keyword dictionary to the first user terminal 20, the first user terminal 20 provides information about the concept of the speaker image to the server 10. It can be.

The server 10 may identify a speaker image corresponding to a specific keyword and provide information on the identified speaker image to the first user terminal 20 (S413). The first user terminal 20 may provide the server 10 with a speech message to be matched with the speaker image obtained from the server 10 (S415).

The server 10 matches the speaker image information and the speech message with the specific speaker image information and the specific speech message and provides the information to the second user terminal 30 (S417). The second user terminal 30 obtains specific speaker image information and a specific speech message from the server 10 and displays them (S419).

Figure 5 exemplarily illustrates a speaker image set according to an embodiment of the present invention.

The speaker image set may be one of a plurality of sets, and the plurality of sets may be classified according to the concept of the image. More specifically, the concept of the image may be determined based on at least one of the character, text, drawing style, and atmosphere that constitute the speaker image. For example, if the character constituting the speaker image is a character named “Jordi,” the first speaker image set may be composed of a set of speaker images composed of the character “Jordi.” At this time, the image concept corresponding to the first speaker image set may be referred to as the first concept for “Jordi character.”

The speaker image set includes at least one speaker image and a keyword, and may further include matching text corresponding to each speaker image.

5 shows a speaker image set area 510 in which at least one speaker image and keywords corresponding to each speaker image are displayed, and a keyword dictionary area 530 in which a plurality of keywords and matching text corresponding to each keyword are displayed. It can be divided into:

When the speech message includes "sad (555)" as the same input text as the matching text, the first user terminal 20 selects a specific keyword corresponding to "sad (555)" based on the keyword dictionary, "sad ( 535)" can be identified. Thereafter, the first user terminal 20 or the server 10 can identify the “sad Jordi character (515)” corresponding to the specific keyword “sadness (535)” as the speaker image based on the speaker image set. there is.

The server 10 transmits the identified speaker image “sad Jordi character 515” as a speaker image to the second user terminal 30, but the first user terminal includes the input text “sad 555”. The utterance message of (20) can be transmitted together.

In this case, the second user terminal 30 may display the first user's profile image as a “sad Jordi character 515” through the chat room screen of the messenger service.

FIG. 6 illustrates an utterance message and a speaker image displayed on the chat room screen of the second user terminal 30 according to an embodiment of the present invention.

Referring to FIG. 6 , the second user terminal 30 may display the speech message 610 provided by the first user terminal 20 on the chat room screen in which the first user and the second user participate.

When at least a portion 611 of the input text constituting the speech message 610 of the first user terminal 20 matches one of a plurality of keywords stored in the keyword dictionary, the second user terminal 30 is connected to the first user terminal 30. At least one of the speech message and speaker image provided by may be displayed as a specific speech message 610 or a specific speaker image 630 that is displayed differently from the general speech message 620.

The specific speech message 610 displayed on the second user terminal 30 may be different from the general speech message 620. More specifically, the input text, speech bubble, background, etc. that make up the specific speech message 610 may be displayed to distinguish it from the general speech message. For example, the speech bubble layout 611 constituting the specific speech message 610 may be displayed in various colors, or an image icon 613 associated with the matching text may be displayed together.

The specific speaker image 630 displayed on the second user terminal 30 may be different from the basic speaker image 640. More specifically, characters, text, drawings, etc. that make up the specific speaker image 630 may be displayed to be distinguished from the basic speaker image 640. For example, the characters, actions, or moods that make up a particular speaker image may include images selected from a set of speaker images based on the spoken message.

Additionally, the specific speaker image 630 may be displayed in the user's profile photo area displayed along with the speech message, replacing the default speaker image (eg, profile photo) set by the user.

A specific speaker image 630 may be displayed in response to a specific speech message 610 on the screen of the user terminal. More specifically, the specific speaker image 630 may be displayed in the speaker area corresponding to the specific speech message 610. The speaker area may be formed in line with or adjacent to the spoken message in the chat room of the messenger service. The speaker of the spoken message can be identified through the information displayed in the speaker area.

After the specific speaker image 630 is displayed in the speaker area corresponding to the specific speech message 610, when the user terminal obtains the general speech message 621, the specific speaker image 630 is displayed in the speaker area of the general speech message 621. A default speaker image 650 other than may be displayed.

In another embodiment, when the general speech message acquired by the user terminal satisfies a predetermined condition, the last displayed specific speaker image may be displayed in the speaker area of the general speech message.

The predetermined condition may be that a general speech message is input within a predetermined time period after a specific speech message corresponding to a specific speaker image is displayed, or that a general speech message is input within a set number of times. For example, for five general speech messages 621 displayed after the specific speech message 610 is displayed, the specific speaker image 630 may continue to be displayed in the speaker area corresponding to the input speech message. Additionally, for example, for a general speech message 621 displayed within 5 minutes after the specific speech message 610 is displayed, the specific speaker image 630 may continue to be displayed in the speaker area corresponding to the input speech message. .

This particular speaker image may be displayed continuously after it is first displayed or even if it reappears after the screen is moved to another screen. However, although not shown in the drawing, the specific speaker image 630 may be changed to the default speaker image 640 and displayed when a predetermined release condition is satisfied. For example, the specific speaker image 630 may be changed to the default speaker image and displayed after 5 minutes have passed since it was first displayed, or after moving from the first screen to another screen due to screen scrolling.

In addition, the above-mentioned release condition may be applied only when a specific speaker image is displayed according to a predetermined condition, even though it is a general speech message 621 and not a specific speech message 610 as described above. For example, if 5 minutes have passed since the specific speaker image 630 was first displayed, the specific speaker image 630 displayed in correspondence with the specific speech message 610 continues to be maintained, while the specific speaker image 630 displayed in correspondence with the general speech message 621 is maintained. The displayed specific speaker image may be changed to a general speaker image and displayed.

Figure 7 illustrates an utterance message and a speaker image displayed on the profile page of a user terminal according to an embodiment of the present invention. The profile page may be displayed on the first user terminal 20 or the second user terminal 30.

The profile page is a screen that displays information about the user's profile in the messenger service and may include the user's name, profile photo or status message, settings interface, etc.

The first user terminal 20 may obtain a speech message as a status message of the profile page. If the input text included in the speech message exists among matching texts stored in the keyword dictionary, the first user terminal 20 may identify a specific keyword corresponding to the matching text. The first user terminal 20 may display a speaker image corresponding to a specific keyword in the profile photo area where the profile photo is displayed.

The profile photo of the first user may be referred to as a basic speaker image, and the speaker image corresponding to a specific keyword may be referred to as a specific speaker image. A specific speaker image may be displayed in the profile photo area, replacing the default speaker image, or may be displayed in a portion of the profile photo area together with the default speaker image.

Referring to FIG. 7, the first screen 710 is a profile page with a basic speaker image displayed in the profile photo area, and the second screen 730 and third screen 750 are a profile page with a specific speaker image displayed in the profile photo area. This is the profile page.

The first screen 710 illustrates a case where the status message is not displayed in the status message display box 713 of the profile page. However, even if the status message is displayed, the input text constituting the status message is among the matching texts in the keyword dictionary. If it does not exist, the default speaker image 715 may be displayed like the first screen 710.

The second screen 730 and the third screen 750 are divided according to the type in which a specific speaker image is displayed.

The second screen 730 displays a specific speaker image 735 on the profile page, replacing the default speaker image in the profile photo area. A specific speaker image 735 may be selected based on the status message entered in the status message display box of the profile page.

For example, as shown in Figure 7, when the status message is "good day" and the word "good" corresponds to a specific keyword in the keyword dictionary, the image corresponding to the specific keyword is displayed as a specific speaker image 735. It can be selected and displayed. If the user changes the status message to "Gloomy Day", the word "Gloomy" corresponds to a specific keyword in the keyword dictionary, and the profile photo area changes to a specific speaker image (736) based on the word "Gloomy". You can.

The third screen 750 displays a specific speaker image 755 in addition to the basic speaker image in the profile photo area. A specific speaker image 755 may be selected based on the status message entered in the status message display box of the profile page. Here, the additionally displayed specific speaker image 755 may be displayed in the form of a sticker, an emoticon, or a stamp.

For example, as shown in Figure 7, when the status message is "End of the weekendㅠㅠㅠ", if the word "ㅠㅠ" corresponds to a specific keyword in the keyword dictionary, the image corresponding to the specific keyword is a specific speaker image (755 ) can be selected and displayed.

Figure 7 illustrates a screen where a specific speaker image is displayed on the profile page of the messenger service. However, the display method of the specific speaker image displayed on the second and third screens can be applied in the same way to the chat room of the messenger service. Specifically, the speaker image corresponding to the spoken message in the chat room (hereinafter referred to as 'chat message') may be displayed in the speaker area of the chat message. A specific speaker image corresponding to a specific speech message may be displayed in the speaker area, replacing the default speaker image, or may be displayed in the form of a sticker added to the basic speaker image.

FIG. 8 illustrates screens of the first user terminal 20 and the second user terminal 30 when a plurality of input texts correspond to matching texts in a spoken message according to an embodiment of the present invention.

The first screen 810 may be a chat room screen displayed on the first user terminal 20. The chat room may be a chat room in which a first user and a second user participate. When the first user inputs a speech message into the first user terminal 20, among the plurality of input texts constituting the speech message, there may be a plurality of input tests that are the same as the matching text stored in the keyword dictionary. More specifically, both the first input text and the second input text included in the speech message exist among matching texts stored in the keyword dictionary, and each matching text is a first specific keyword and a second specific keyword, which are different specific keywords. can correspond to .

In this case, the first user terminal 20 identifies a specific keyword with high priority among the first specific keyword and the second specific keyword according to preset criteria, and provides a speaker image corresponding to the identified specific keyword to the server. You can. An operation of determining a specific keyword with high priority according to a preset standard may be performed by the first user terminal 20 or the server 10.

The preset condition may be determined based on at least one of the first user's usage information for the speaker image, the first user's user information, or external information.

The first user's usage information may include the frequency of use of the speaker image by the first user, total usage amount, recent number of uses, payment information, cancellation information, usage history information, etc.

The user information of the first user may include the first user's age, residence, messenger service usage time, relationship with the conversation partner, conversation history, frequently used speaker image, location information of the first user, etc.

External information may be information generated or provided from a server or another user terminal, regardless of the first user or the first user terminal. For example, when the server 10 sets the input text related to emotional expression as having the highest priority, the server 10 can update the preset condition by providing this to the first user terminal through external information.

Referring to FIG. 8, when “Congratulations” (811) and “Boyfriend” (813) among the speech messages entered by the first user on the first screen 810 both correspond to different specific keywords, the first user The terminal 20 may identify one of the two specific keywords as a specific keyword that has priority according to preset conditions. For example, since “congratulations” corresponds to an emotional expression, it may be determined as a specific keyword that takes precedence over “boyfriend.” In this case, when the first user terminal inputs the corresponding speech message, the second screen 830 displayed on the second user terminal 30 displays a specific speaker image 835 related to “congratulations” along with the speech message. You can.

Figure 9 illustrates a preview screen of a speaker image and a spoken message displayed on a first user terminal according to an embodiment of the present invention.

When a speech message is input to the first user terminal 20, and a specific keyword corresponding to the input text of the speech message exists among a plurality of keywords in the keyword dictionary, the first user terminal 20 previews the speech message. Screen 910 can be displayed.

The preview screen 910 may include a speaker image 930 corresponding to the spoken message 950. More preferably, the preview screen 910 may display the speech message 950 together with the speaker image 930.

The first user can check the speaker image 930 displayed on the screen of the second user terminal 30 in advance through the preview screen 910 even before transmitting the speech message 950 to the server 10.

In some cases, the speech message may be displayed as a specific speech message 950 that is displayed differently from the general speech message. The specific speech message 950 may be displayed so that the input text, speech bubble, background, etc. are distinguished from the general speech message. For example, the speech bubble layout 911 constituting the specific speech message 950 may be displayed in various colors, or an image icon 913 associated with the matching text may be displayed together. The features 911 and 913 of this specific speech message 950 are also displayed on the screen of the second user terminal 30 and can be confirmed in advance.

The preview screen 910 may further include a confirmation interface 970 or an end interface 990. The first user can check the speaker image 930 through the preview screen 910 and transmit the speech message 950 to the server 10 by providing a confirmation interaction on the confirmation interface 970. The first user can check the speaker image 930 through the preview screen 910 and release the speaker image 930 matched to the speech message 950 by providing a termination interaction on the termination interface 990. there is. In this case, even when the first user terminal 20 transmits the speech message 950 to the server 10, the speaker image 930 may not be transmitted.

Figure 10 illustrates a speaker image and speech message displayed on the first user terminal according to an embodiment of the present invention.

Referring to FIG. 10, not only the first user's spoken message 1030 but also the speaker image 1010 may be displayed on the chat room screen of the first user terminal 20 that provides the spoken message.

The display of the speech message on the first user terminal 20 may be performed according to preset conditions. When the input text included in the speech message 1030 corresponds to a specific keyword in the keyword dictionary, the first user terminal 20 may display the speaker image 1010 in the speaker area corresponding to the speech message. Here, the displayed speaker image 1010 may be a specific speaker image for the speech message 1030 input by the first user.

If the input text included in the speech message 1035 does not correspond to a specific keyword in the keyword dictionary, the first user terminal 20 displays the default speaker image in the speaker area corresponding to the speech message 1035, or displays the default speaker image in the speaker area. It may not display itself.

Additionally, a specific speaker image displayed on the first user terminal 20 may be displayed for a predetermined time period from the time the speech message is input. In this case, a specific speaker image and speaker area may be temporarily displayed on the first user terminal 20 and then disappear.

Figure 11 is a flowchart of the operation of a server according to an embodiment of the present invention.

Each step in FIG. 11 can be performed regardless of the listed order, except in cases where it must be performed in the listed order due to a special causal relationship. However, hereinafter, for convenience of explanation, the description will be made assuming that each of the above-described steps is performed in the listed order.

In step S210, the server 10 provides a keyword dictionary containing a plurality of keywords to the first user terminal 20.

In step S220, the server 10 provides a speaker image set including at least one speaker image matching at least some of the plurality of keywords to the first user terminal.

The keyword dictionary provided to the first user terminal 20 may correspond to a speaker image set. For example, when the server 10 obtains information requesting a first concept for an image from the first user terminal 20, the server first identifies the first speaker image set corresponding to the first concept, A plurality of speaker images included in the identified speaker image set can be identified. Thereafter, the server 10 may provide the first user terminal 20 with a keyword dictionary containing a plurality of keywords matching each of the plurality of speaker images.

In another embodiment, the keyword dictionary provided by the server 10 to the first user terminal 20 may include a set of speaker images. In this case, the step of transmitting the speaker image set (S220) can be omitted.

In another embodiment, the server 10 may not provide the speaker image set to the first user terminal 20. In this case, as shown in FIG. 4, the server 10 may perform an operation to determine whether a specific keyword provided by the first user terminal 20 matches a speaker image included in the speaker image set.

In step S230, if at least a part of the speech message obtained by the first user terminal corresponds to a specific keyword among a plurality of keywords, the server 10 provides information on the speaker image corresponding to the specific keyword among the speaker image set and the speech message. Obtain a message from the first user terminal.

If the first user terminal 20 does not acquire the speaker image set, the server 10 obtains information about a specific keyword from the first user terminal 20 and specifies the speaker image set stored in the server 10. Information on the speaker image can be obtained by determining whether a speaker image corresponding to the keyword exists.

In step S240, the server 10 provides information on the speaker image and the speech message to the second user terminal.

The server 10 may provide information on the speaker image and a speech message to the second user terminal 30 as a specific speaker image and a specific speech message. At this time, a specific speaker image may be provided as matching a specific speech message.

The technical features disclosed in each embodiment of the present invention are not limited to the corresponding embodiment, and unless they are incompatible with each other, the technical features disclosed in each embodiment may be combined and applied to other embodiments.

Therefore, in each embodiment, each technical feature is mainly explained, but unless the technical features are incompatible with each other, they can be applied in combination with each other.

The present invention is not limited to the above-described embodiments and the accompanying drawings, and various modifications and variations will be possible from the perspective of those skilled in the art to which the present invention pertains. Therefore, the scope of the present invention should be determined not only by the claims of this specification but also by equivalents to these claims.

10: Server
20: First user terminal
30: Second user terminal

Claims (26)

In a method for a user terminal to provide a speaker image based on an utterance message,
storing a keyword dictionary including a plurality of keywords;
Obtaining input of a spoken message;
determining whether at least a portion of the utterance message corresponds to a specific keyword among the plurality of keywords;
When at least part of the speech message corresponds to the specific keyword, identifying a speaker image corresponding to the specific keyword; and
Comprising the step of matching at least one of the information on the specific keyword and the information on the speaker image to the speech message and providing it to the server.
A method of providing a speaker image based on the speech message. According to claim 1,
Further comprising the step of displaying the speaker image to correspond to the speech message in the chat room.
A method of providing a speaker image based on the speech message. According to clause 2,
Obtaining interaction with the speaker image displayed in the displaying step; and
In response to the interaction, displaying a user profile page including the speaker image.
A method of providing a speaker image based on the speech message. According to claim 1,
further comprising storing a speaker image set including at least one speaker image matching at least some of the plurality of keywords,
In the step of identifying the speaker image, the user terminal identifies the speaker image corresponding to the specific keyword among the speaker image set.
A method of providing a speaker image based on the speech message. According to clause 4,
Further comprising the step of obtaining information about the concept of the speaker image,
At least one speaker image included in the speaker image set is related to the concept.
A method of providing a speaker image based on the speech message. According to claim 1,
The step of providing to the server is performed before the step of identifying the speaker image,
In the step of providing to the server, the at least one keyword is the specific keyword,
The speaker image is received from the server in response to providing the specific keyword to the server.
A method of providing a speaker image based on the speech message. According to clause 6,
Further comprising the step of obtaining information about the concept of the speaker image,
Further comprising providing information about the concept to the server,
The speaker image is related to the concept.
A method of providing a speaker image based on the speech message. According to claim 1,
The speech message includes multimedia information, and the multimedia information is at least one of emoticons, image information, photo information, and video information.
The step of determining whether it corresponds to the specific keyword is,
Identifying matching text corresponding to the multimedia information; and
Including determining whether the matching text corresponds to a specific keyword among the plurality of keywords.
A method of providing a speaker image based on the speech message. According to claim 1,
determining whether at least a portion of the utterance message corresponds to a recommended keyword among the plurality of keywords; and
When at least part of the utterance message corresponds to the recommended keyword, displaying a recommended emoticon corresponding to the recommended keyword,
Among the plurality of keywords, the keyword corresponding to the specific keyword is part of the keyword corresponding to the recommended keyword.
A method of providing a speaker image based on the speech message. According to claim 1,
At least a portion of the utterance message includes a first part corresponding to a first specific keyword and a second part corresponding to a second specific keyword,
If the first specific keyword has priority over the second specific keyword according to a preset criterion, identifying the first specific keyword as the specific keyword;
A method of providing a speaker image based on the speech message. According to claim 1,
When identifying a speaker image corresponding to the specific keyword, displaying the speaker image and a confirmation interface; and
In response to obtaining a confirmation interaction for the confirmation interface, matching at least one of information on the specific keyword and information on the speaker image to the speech message and providing it to the server.
A method of providing a speaker image based on the speech message. A computer program combined with hardware and stored on a medium to execute the method of any one of claims 1 to 11. In the user terminal that identifies the speaker image based on the speech message,
Memory; and
A processor connected to the memory and configured to execute instructions contained in the memory,
The processor,
storing a keyword dictionary including a plurality of keywords;
Obtaining an utterance message;
determining whether at least a portion of the utterance message corresponds to a specific keyword among the plurality of keywords;
When at least part of the speech message corresponds to the specific keyword, identifying a speaker image corresponding to the specific keyword; and
Performing the step of matching at least one of the information on the specific keyword and the information on the speaker image to the speech message and providing it to the server.
A user terminal that identifies the speaker image based on the speech message. In a method for a user terminal to display a speaker image based on an utterance message,
Receiving at least one general speech message and a basic speaker image transmitted by the speaker terminal from the server;
Displaying the at least one general speech message and the basic speaker image in a chat room, wherein the basic speaker image is displayed to correspond to at least a portion of the at least one general speech message;
Receiving information on a specific speech message transmitted by the speaker terminal and a specific speaker image matched to the specific speech message from the server; and
Displaying the specific speech message and the specific speaker image in the chat room, where the specific speaker image is displayed to correspond to the specific speech message; containing
A method of displaying a speaker image based on the speech message. According to claim 14,
The specific speaker image is displayed together with the default speaker image.
A method of displaying a speaker image based on the speech message. According to claim 14,
The specific speaker image includes a first image displayed in the profile area corresponding to the specific speech message and a second image displayed in the text area corresponding to the specific speech message.
A method of displaying a speaker image based on the speech message. According to claim 14,
Obtaining interaction with the basic speaker image or the specific speaker image displayed in the chat room; and
Comprising the step of displaying a profile page including a specific profile image in response to the interaction.
A method of displaying a speaker image based on the speech message. According to claim 17,
The specific profile image above is,
A specific speaker image matched to at least one of status information of the speaker terminal, media information of the speaker terminal, and the specific speech message.
A method of displaying a speaker image based on the speech message. According to claim 14,
In the step of displaying the specific speech message and the image of the specific speaker in the chat room,
The specific speaker image is displayed only when the step of receiving the specific speech message satisfies a preset time condition.
A method of displaying a speaker image based on the speech message. According to clause 19,
The preset time condition is that the specific utterance message and the last message are received within one time interval.
A method of displaying a speaker image based on the speech message. In a user terminal that displays a speaker image based on an utterance message,
Memory; and
A processor connected to the memory and configured to execute instructions contained in the memory,
The processor,
Receiving a plurality of general speech messages and a basic speaker image transmitted by the speaker terminal from the server;
Displaying the plurality of general speech messages and the basic speaker image in a chat room, wherein the basic speaker image is displayed to correspond to at least a portion of the plurality of general speech messages;
Receiving information on a specific speech message transmitted by the speaker terminal and a specific speaker image matched to the specific speech message from the server; and
Displaying the specific speech message and the specific speaker image in the chat room - displaying the specific speaker image to correspond to the specific speech message -; to do
A user terminal that displays a speaker image based on the speech message. In a method for a server to provide a speaker image based on an utterance message,
Providing a keyword dictionary including a plurality of keywords to a first user terminal;
providing a speaker image set including at least one speaker image matching at least some of the plurality of keywords to the first user terminal;
When at least a portion of the speech message acquired by the first user terminal corresponds to a specific keyword among the plurality of keywords, information on the speaker image corresponding to the specific keyword among the speaker image set and the speech message are sent to the first user. Obtaining from a terminal; and
Providing information on the speaker image and the speech message to a second user terminal; comprising
A method of providing a speaker image based on the speech message. According to clause 22,
When the second user terminal obtains interaction with the speaker image information, further comprising providing a profile page including a specific profile image to the second user terminal.
A method of providing a speaker image based on the speech message. According to clause 23,
The specific profile image above is,
A specific speaker image matched to at least one of status information of the speaker terminal, media information of the speaker terminal, and the specific speech message. According to clause 22,
Further comprising providing information about the concept of the speaker image to the first user terminal,
At least one speaker image included in the speaker image set is related to the concept.
A method of providing a speaker image based on the speech message. In the server that provides a speaker image based on the speech message,
Memory; and
A processor connected to the memory and configured to execute instructions contained in the memory,
The processor,
Providing a keyword dictionary including a plurality of keywords to a first user terminal;
providing a speaker image set including at least one speaker image matching at least some of the plurality of keywords to the first user terminal;
When at least a portion of the speech message acquired by the first user terminal corresponds to a specific keyword among the plurality of keywords, information on the speaker image corresponding to the specific keyword among the speaker image set and the speech message are sent to the first user. Obtaining from a terminal; and
Providing information on the speaker image and the speech message to a second user terminal; performing
A server that provides speaker images based on speech messages.