KR20210046262A - Server and method for providing karaoke service using instant messaging service - Google Patents

Abstract

A chatbot server for providing a karaoke service through an instant messaging service according to one embodiment of the present invention may comprise: a chatbot activation unit receiving a chatbot activation signal including chat room information corresponding to a chat room from a messenger server and activating the chatbot participating in the chat room based on the chatbot activation signal; a message processing unit receiving a plurality of messages inputted through the chat room from the messenger server, and performing natural language processing on the plurality of messages to derive a control command for the karaoke service and a response to the control command; a response transmission unit transmitting a response to the control command to the messenger server; and a karaoke service providing unit providing a karaoke service through a sound output device corresponding to the chat room based on the control command.

Description

Server and method for providing karaoke service through instant messaging service {SERVER AND METHOD FOR PROVIDING KARAOKE SERVICE USING INSTANT MESSAGING SERVICE}

The present invention relates to a server and method for providing a karaoke service through an instant messaging service, and more particularly, to a server and method for providing a karaoke service based on a plurality of messages input through a chat room.

Conventionally, when a user reserves a song on a karaoke device, the karaoke device is controlled by pressing a button on the karaoke device or using a wired or wireless remote control.

In order to select the song name to be selected in the karaoke room, the user had to manually turn over the booklet provided in the karaoke room and find the song number corresponding to the song name they want. There was a problem that was difficult to select.

In summary, when people use karaoke, they have to remember the song they will sing, and even if they choose the song to sing, they have to find the song number every time or search through the booklet.

Meanwhile, recently, a karaoke service through a voice recognition device has been proposed. However, there is a problem in that the recognition rate of the corresponding voice command is remarkably low because the voice recognition device needs to receive a voice command (eg, song reservation) in a situation where a sound source is being output through a speaker of a karaoke device or a voice recognition device.

Japanese Published Patent Publication No. 2005-077752 (published on March 24, 2005)

The present invention seeks to solve the above-described problem by deriving a control command related to a karaoke service from a message input to a chat room, and providing a karaoke service according to the derived control command through a sound output device. However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, a chatbot server providing a karaoke service through an instant messaging service according to an embodiment of the present invention receives a chatbot activation signal including chat room information corresponding to the chat room from the messenger server. And a chatbot activation unit that activates a chatbot participating in the chat room based on the chatbot activation signal; A message processing unit for receiving a plurality of messages input through the chat room from the messenger server, and performing natural language processing on the plurality of messages to derive a control command for a karaoke service and a response to the control command; And a response transmission unit for transmitting a response to the control command to the messenger server. And the karaoke service providing unit providing the karaoke service through a sound output device corresponding to the chat room based on the control command.

A messenger server that provides a karaoke service through an instant messaging service according to another embodiment of the present invention receives an invitation request from a chatbot from at least one user participating in the chat room, invites the chatbot to the chat room, and responds to the chat room. A chatbot inviting unit that transmits a chatbot activation signal including chat room information to the chatbot server; A message transmission unit receiving a plurality of messages from the at least one user and transmitting the plurality of messages to the chatbot server; A response receiver configured to receive a response to a control command derived based on natural language processing performed on the plurality of messages from the chatbot server; And a response output unit for outputting a response to the control command to the chat room, and the karaoke service is provided through a sound output device corresponding to the chat room based on the control command.

A karaoke service providing method through an instant messaging service performed by a chatbot server according to another embodiment of the present invention receives a chatbot activation signal including chat room information corresponding to the chat room from a messenger server, and based on the chatbot activation signal Activating a chatbot participating in the chat room; Receiving a plurality of messages input through the chat room from the messenger server, and performing natural language processing on the plurality of messages to derive a control command for a karaoke service and a response to the control command; Transmitting a response to the control command to the messenger server; And providing the karaoke service through a sound output device corresponding to the chat room based on the control command.

According to any one of the above-described problem solving means of the present invention, the present invention provides a karaoke service to a sound output device based on a control command for a karaoke service derived through natural language processing for a plurality of messages input through a chat room. By doing so, it is possible to solve the problem of misrecognizing a user's voice command due to the output of a song sound source in karaoke service through an existing artificial intelligence speaker.

1 is a diagram schematically showing a system for providing a karaoke service according to an embodiment of the present invention.
2 is a block diagram of a chatbot server according to an embodiment of the present invention.
3A to 3D are diagrams for explaining a method of providing a karaoke service according to an embodiment of the present invention.
4 is a flowchart of a method for providing a karaoke service through an instant messaging service according to an embodiment of the present invention.
5 is a block diagram of a messenger server according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" with another part, this includes not only "directly connected" but also "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included rather than excluding other components unless specifically stated to the contrary.

In the present specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized by using two or more hardware, or two or more units may be realized by one piece of hardware. Meanwhile,'~ unit' is not meant to be limited to software or hardware, and'~ unit' may be configured to be in an addressable storage medium or configured to reproduce one or more processors. Thus, as an example,'~ unit' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , Subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays and variables. Components and functions provided in the'~ units' may be combined into a smaller number of elements and'~ units', or may be further separated into additional elements and'~ units'. In addition, components and'~ units' may be implemented to play one or more CPUs in a device or a security multimedia card.

The "user terminal" mentioned below may be implemented as a computer or portable terminal that can access a server or other terminal through a network.

1 is a diagram schematically showing a system for providing a karaoke service according to an embodiment of the present invention.

Referring to FIG. 1, a system for providing a karaoke service may include a chatbot server 100, a messenger server 110, and a sound output device 120. In this case, the chatbot server 100 and the messenger server 110 may be configured integrally. Since the karaoke service providing system of FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1. That is, according to various embodiments of the present invention, a system for providing a karaoke service may be configured differently from that of FIG. 1.

The messenger server 110 may provide an instant messaging service that enables a user of a user terminal and another user registered as a real friend to exchange conversations in a chat room. In addition, the messenger server 110 may provide an instant messaging service through an instant messaging application that enables exchanges with chatbots or official accounts registered as virtual friends in the instant messaging application of the user terminal.

The messenger server 110 may receive an invitation request from the karaoke chatbot from the user terminal of at least one user participating in the chat room and invite the karaoke chatbot to the corresponding chat room. For example, when the user terminal of at least one user participating in the chat room scans a digital code (eg, a QR code) attached to the sound output device 120, the messenger server 110 is a karaoke chatbot corresponding to the digital code. Can be invited to a chat room. Here, in the karaoke chatbot, different karaoke chatbots may exist for each platform operating the sound output device 120. For example, each of the karaoke chatbots can provide different types of comments, responses, and services according to the operating policy of the corresponding platform.

As another example, when the terminal of at least one user participating in the chat room selects a karaoke chatbot from among a plurality of chatbots previously registered as virtual friends in the instant messaging application, the messenger server 110 may invite the selected karaoke chatbot to the chat room. .

The messenger server 110 may transmit a chatbot activation signal including chat room information corresponding to the chat room to the chatbot server 100. Here, the chat room information may include at least one of an identifier of a chat room, an identifier of at least one user participating in the chat room, and information on the sound output device 120.

When the chatbot server 100 receives a chatbot activation signal including chat room information corresponding to the chat room from the messenger server 110, the chatbot server 100 may activate a karaoke chatbot participating in the chat room based on the received chatbot activation signal.

The messenger server 110 may receive a plurality of messages of a user input into a chat room from a user's terminal, and transmit the plurality of received messages to the chatbot server 100.

The chatbot server 100 receives a plurality of messages input through the chat room from the messenger server 110, and performs natural language processing on the plurality of messages to derive a control command for karaoke service and a response to the control command. have. For example, chaetbot server 100, messenger when the message received from the server 110 is "IU" good day "reserve me" message containing, predetermined by the natural language processing for a message keyword (e.g., ' extract the reservation ") can be derived by the control command (for example, to derive a song reserve command), the response to the control command (for example, the IU" good day "schedule) associated with that keyword.

The chatbot server 100 may transmit a response to the derived control command to the messenger server 110 and provide a karaoke service to the sound output device 120 corresponding to the chat room based on the control command. For example, chaetbot server 100 may send a sound output device, song information (e.g., the IU, "good day") to schedule to 120 corresponding to the chat room to perform the reserved songs.

The messenger server 110 may output a response to the control command received from the chatbot server 100 to a chat room.

The sound output device 120 may connect and disconnect with the chatbot server 100 based on a message input to the chat room, and provide a karaoke service through the control of the chatbot server 100.

The sound output device 120 may include all terminals that provide speech recognition services including, for example, a speech recognition speaker and a vehicle speaker, and may also include a karaoke terminal disposed in a karaoke room.

The operation of each component included in the karaoke service providing system of FIG. 1 will be described in more detail with reference to the following drawings.

2 is a block diagram of a chatbot server 100 according to an embodiment of the present invention. 2, the chatbot server 100 according to an embodiment of the present invention includes a chatbot activation unit 200, a message processing unit 210, a response transmission unit 220, a karaoke service provider 230, and a score management unit. It may include a sound source receiving unit 250, a storage unit 260, and a recommendation unit 270. Here, the message processing unit 210 may include a reservation unit 212. However, the configuration of the chatbot server 100 according to an embodiment of the present invention may be different from that of FIG. 2.

The chatbot activation unit 200 may receive a chatbot activation signal including chat room information corresponding to the chat room from the messenger server 110 and activate a chatbot participating in the chat room based on the chatbot activation signal. Here, the chat room information may include at least one of an identifier of a chat room, an identifier of at least one user participating in the chat room, and information on the sound output device 120. At this time, when the chatbot activation unit 200 receives a chatbot activation signal from the messenger server 110, the chatbot may already be participating in the chat room. Alternatively, when the chatbot is not participating in the chat room, a control message for inducing the chatbot invitation to the chat room may be provided to the chat room through the messenger server 110. That is, the user of the chat room can invite the chatbot to the chat room through a control message.

For example, when the user terminal inputs the serial number of the sound output device 120 into an instant messaging application of the user terminal or scans a digital code (eg, a QR code) of the sound output device 120, the sound output device 120 A karaoke chatbot controlling the sound output device 120 may be invited to a chat room with a karaoke chatbot controlling) opened in an instant messaging application of the user terminal, or to a previously opened chat room (personal chat room or group chat room).

For another example, the sound output device 120 is pre-registered in the user terminal (ie, the account of the user's instant messaging application), and the user terminal is a connection request message to the pre-registered sound output device 120 through a chat room. If you input (e.g.,'Start karaoke on my speaker'), a karaoke chatbot can be invited to the chat room.

Thereafter, a chatbot activation signal for activating a karaoke chatbot participating in the chat room is transmitted to the chatbot activation unit 200 through the messenger server 110 to activate the karaoke chatbot in the chat room.

After this, settings for interworking between the sound output device 120 and the karaoke chatbot may be made by the chatbot server 100. Here, the digital code or serial number of the sound output device 120 may include a code for connecting the sound output device 120 and the karaoke chatbot to control the karaoke service through the sound output device 120. . In this case, the chatbot activation unit 200 includes chat room information corresponding to the chat room with the karaoke chatbot from the messenger server 110 (e.g., identification information of the karaoke chatbot and identification information of the sound output device 120 associated with the karaoke chatbot) A chatbot activation signal including a may be received.

As another example, the user terminal registers a karaoke chatbot corresponding to the karaoke service as a virtual friend through an instant messaging application, and then interlocks the sound output device 120 (eg, an artificial intelligence speaker) placed in the user's premises with the karaoke chatbot. A connection message (including information on the sound output device 120) for the message may be transmitted to the messenger server 110. The connection message is provided to the chatbot server 100 through the messenger server 110, and the sound output device 120 and the karaoke chatbot may be linked by the chatbot server 100 according to the connection message. Here, the information of the sound output device 120 may be information extracted through a scan of a digital code attached to the sound output device 120 and automatically input into a chat room with a karaoke chatbot. It may be the serial number of the sound output device 120 directly input to the chat room. Alternatively, the information on the sound output device 120 may be information on an artificial intelligence speaker as the sound output device 120 previously registered in the user terminal.

After the sound output device 120 and the karaoke chatbot are linked based on the connection message, when the user terminal invites the karaoke chatbot to the user's own chat room (or open chat room), the chatbot activation unit 200 is the messenger server 110 ) From the chatbot corresponding to the chat room opened by the user terminal (eg, identification information of the karaoke chatbot invited to the chat room, the user's own identifier, and information on the sound output device 120 linked to the karaoke chatbot) It can receive an activation signal.

As another example, when a user terminal invites a karaoke chatbot registered as a virtual friend in an instant messaging application (a karaoke chatbot linked to the sound output device 120 mapped to the user's account) to a group chat room opened between real friends, Chatbot activation unit 200 is the chat information corresponding to the group chat room from the messenger server 110 (e.g., identification information of a karaoke chatbot invited to the group chat room, identifiers of a plurality of other users participating in the group chat room, and interlocking with the karaoke chatbot) A chatbot activation signal including information on the sound output device 120) may be received.

The message processing unit 210 may receive a plurality of messages input through a chat room with a karaoke chatbot from the messenger server 110. For example, when at least one user participating in a chat room with a karaoke chatbot inputs a message into the chat room, the message processing unit 210 sends the message together with the identifier of at least one user who entered the message into a messenger server. It can be received from (110).

Here, the plurality of messages input through the chat room with the karaoke chatbot may include a control message related to connection and release of the sound output device 120 or additional registration of another sound output device. For example, when there are a plurality of sound output devices already registered in the user terminal, a message for selecting a sound output device from among the plurality of sound output devices to be connected or disconnected by the user, and a request for connection of the selected sound output device Messages can be entered through chat rooms.

Alternatively, a plurality of messages input through a chat room with a karaoke chatbot may include various control messages related to a karaoke service. For example, a request message for a specific song reservation, a request message for a list of reserved song names, a sound output device A request message for information on a song title played through 120, a request message for a song title list played through the sound output device 120 for each user participating in the chat room, and the like may be included. For example, a request message for a particular song reservation, for example, "Let me IU good day scheduled," "Music Weekly Chart No. 1 song scheduled me, 'Let me reserve a 1990s ballad song might include. The request message of the reserved song name list may include'show the reserved song list','tell me the next reserved song name', and the like. The request message for information on the names of songs played through the sound output device 120 may include'show a list of played songs'. The request message of the song name list played through the sound output device 120 for each user participating in the chat room may include'tell me of the songs I sang', and the like.

The message processing unit 210 may derive a control command for a karaoke service and a response to the control command by performing natural language processing on a plurality of received messages. The message processing unit 210 may further derive a response to a control command and a control command related to connection and release of the sound output device 120 and additional registration of another sound output device.

For example, when a message including'Show a list of reserved songs' by at least one user is input into a chat room with a karaoke chatbot, the message processing unit 210 receives the message from the messenger server 110, A control command for outputting a list of reserved songs can be derived from the message through natural language processing on the message. In addition, the message processing unit 210 may derive a response including'outputting a list of reserved songs' in response to the derived control command. As another example, when the message processing unit 210 receives a message from the messenger server 110 that includes'terminate karaoke service' input to a chat room with a karaoke chatbot, the message processing unit 210 issues a control command for executing karaoke service termination from the message. In response to the derived control command, a response including'terminating the karaoke service' can be derived.

The response transmission unit 220 may transmit a response to the control command to the messenger server 110. The response to the control command may be output to the chat room in which the karaoke chatbot is participating by the messenger server 110.

The karaoke service provider 230 may provide a karaoke service through the sound output device 120 corresponding to the chat room based on a control command.

<First Example>

Referring to FIG. 3A, a plurality of users 31 and 33 participating in the chat room 300 are together in the same first space (eg, karaoke), and a sound output device 120-corresponding to a karaoke device in the first space. It is assumed that 1) is arranged and explained.

The digital code attached to the sound output device 120-1 disposed in the first space by the user terminal of at least one of the plurality of users 31 and 33 is scanned and input to an instant messaging application or a sound output device ( When the serial number of 120-1) is input to the instant messaging application, a karaoke chatbot controlling the sound output device 120-1 may be invited to the chat room 300. At this time, when a karaoke chatbot is invited to the chat room 300, after that, a linkage between the sound output device 120-1 and the karaoke chatbot may be set.

As another example, when a karaoke chatbot is invited to the chat room 300 and activated, and the user inputs a message for changing the sound output device through the chat room, the message processing unit 210 Respond to a control command related to the change of the sound output device by receiving a message about the change of the output device and performing natural language processing on the received message (e.g.,'Enter the QR code or device number of the sound output device Please enter'). At this time, the response may be transmitted to the messenger server 110 and output to the chat room.

Each of the plurality of users 31 and 33 inputs a control message related to a song service while chatting with a karaoke chatbot in the corresponding chat room 300, and sings through the sound output device 120-1 based on the input control message. Service can be provided.

The message processing unit 210 extract the first user (31) message (302, for example, IU, "good day" reserve me), keyword (e.g., "Schedule") through a natural language processing on the input to the chat room (300) Then, a control command (eg, a song reservation command) related to the keyword may be derived by comparing the extracted keyword with a database (not shown). Here, information on related song services for each keyword may be stored in advance in the database (not shown). For example, the message processor 210 is a user intended by the natural language processing of the message (302, for example, IU, "good day" reserve me) of the first user (31) input to the chat room (300) (e.g., " Song reservation') can be identified and a control command related thereto (eg,'song reservation command') can be derived.

When the derived control command is related to the song reservation command, the reservation unit 212 receives song information to be reserved to the sound output device 120-1 from the message 302 of the first user 31 inputted in the chat room 300. (e.g., "good day" for the "IU" and the music name corresponding to the singer) may be extracted.

The reservation unit 212 may perform a song reservation for the first user 31 based on the extracted song information. For example, the reservation unit 212 searches for a song number corresponding to the extracted song information from a sound source database (not shown), and controls the sound output device 120-1 to a song reservation message including the searched song number. The song may be reserved by the first user 31 by transmitting it to an external server or the sound output device 120-1. When the song reservation message is transmitted to an external server, the external server may transmit the song reservation message to the sound output device 120-1.

Response transmission unit 220 may transmit to the first user (31) in response (304, for example, "good day IU reservation is made") the messenger server 110, a reservation for the song. Here, the response to the song reservation may include user information and song information indicating whether the response to a message from a user. The response 304 to the song reservation may be displayed in the chat room 300 by the messenger server 110.

<Second Example>

3B, a plurality of users 31 and 33 participating in the chat room 300 with the karaoke chatbot are together in the same second space (e.g., a space other than karaoke), and the voice recognition device is in the second space. It is assumed that the corresponding sound output device 120-2 is disposed. Here, the sound output device 120-2 may be a voice recognition device mapped to an account of a user among a plurality of users 31 and 33 participating in the chat room 300.

The message processing unit 210 extracts a keyword (for example,'reservation') through natural language processing for the message 306 of the second user 33 input to the chat room 300 (for example,'reservation of Yoon Jong-shin red bean paste'), and , It is possible to derive a control command (eg, a song reservation command) related to a keyword from a database (not shown). For example, the message processing unit 210 processes the user's intention (for example,'song 'Reservation') can be identified and a control command related thereto (for example, a'song reservation command') can be derived.

When the derived control command is related to the song reservation command, the reservation unit 212 receives a song for reservation of a song for the second user 33 from the message 302 of the second user 33 inputted in the chat room 300. Information (eg,'Jongshin Yoon' corresponding to the name of the singer and'Bingsu Red Bean' corresponding to the name of the song) can be extracted.

The sound source receiving unit 250 requests a song sound source (eg, MR) corresponding to the extracted song information from an external server (eg, a server of a company providing a sound source streaming service), and sends a request to the song sound source or song sound source from the external server. You can receive a link to it.

The response transmission unit 220 may perform a song reservation of the second user 33. When the song reservation of the second user 33 is completed, the response transmission unit 220 transmits the song sound source received from the external server to the sound output device 120-2, and is then provided through the sound output device 120-2. 2 A song sound source corresponding to a song reservation by the user 33 may be played.

In addition, the response transmission unit 220 may transmit a song sound source or a link to a song sound source received from an external server to the messenger server 110. Here, the song sound source received from the external server may be a sound source of a song sung by the first user 31 or the second user 33 participating in the chat room 300. The song sound source or the link to the song sound source may be provided to the group chat room 300 of the plurality of users 31 and 32, or may be provided to the private chat room of the second user 32 who has requested a song reservation.

<Third Example>

3C, a first sound output device 120-3 corresponding to a voice recognition device is disposed in a first space 310, and a second sound corresponding to a voice recognition device is disposed in a second space 312. The output device 120-4 is arranged.

In addition, among the plurality of users 31 and 33 participating in the chat room 300, the first user 31 is in the first space 310, and the second user 33 is 2 It is assumed that it is in the space 312 and described.

After the karaoke chatbot is invited to the chat room 300 and the karaoke chatbot is activated, when the first user 31 inputs a first control message related to the song service in the chat room 300, the first user 31 A song service based on the first control message may be provided through the first sound output device 120-3 mapped to the user 31's account. In addition, when the second user 33 inputs a second control message related to the song service in the chat room 300, the second user 33 is a second sound output device mapped to the account of the second user 33 ( Through 120-4), a song service based on the second control message may be provided.

Specifically, when the message 302 of the first user 31 and the message 306 of the second user 33 input into the chat room 300 are related to song reservation, the first user ( From each of the message 302 of 31) and the message 306 of the second user 33, song information for song reservation may be extracted.

The sound source receiving unit 250 requests a song sound source corresponding to each extracted song information from an external server, and a song sound source corresponding to a song reservation for each of the first user 31 and the second user 33 received from the external server Alternatively, a link to a song source may be received.

The response transmission unit 220 provides the first sound output device 120-3 in which the song sound source corresponding to the song reservation for the first user 31 received from the external server is mapped to the account of the first user 31. The song sound source may be transmitted to the first sound output device 120-3 to be output through. Also, the song sound source corresponding to the song reservation for the second user 33 received from the external server is output through the second sound output device 120-4 mapped to the account of the second user 33. The sound source may be transmitted to the second sound output device 120-4.

In addition, the response transmission unit 220 transmits a song sound source corresponding to the song reservation for each of the first user 31 and the second user 33 received from the external server or a link to the song sound source to the messenger server 110 Can be transmitted. Here, the song sound source corresponding to the song reservation for the first user 31 or a link to the song sound source is provided to the personal chat room of the first user 31, and corresponding to the song reservation for the second user 33 The song sound source or a link to the song sound source may be provided to the personal chat room of the second user 33.

<Fourth Example>

3D, a first sound output device 120-5 corresponding to a karaoke device is disposed in a first space 310, and a second sound output device corresponding to a voice recognition device is output in the second space 312. The device 120-6 is placed.

In addition, among the plurality of users 31 and 33 participating in the chat room 300 with the karaoke chatbot, the first user 31 is in the first space 310, and the second user 33 is in the first space 310 It is assumed that it is in the second space 312 different from that of the description.

The digital code attached to the first sound output device 120-5 disposed in the first space 310 by the user terminal of the first user 31 is scanned and input to an instant messaging application or the first sound output device ( When the serial number of 120-5) is input to the instant messaging application, the first sound output device 120-5 may be set as a device controlled by the karaoke chatbot.

When the second user 33 inputs a karaoke service request message using the second sound output device 120-6 mapped to the account of the second user 33 into the chat room 300, the second sound output device (120-6) It can also be set as a device controlled by a karaoke chatbot.

Thereafter, when the first user 31 inputs a first control message related to the song service in the chat room 300, the first user 31 is the first sound output device 120-arranged in the first space 310. Through 5), a song service based on the first control message may be provided. In addition, when the second user 33 inputs a second control message related to the song service in the chat room 300, the second user 33 is a second sound output device mapped to the account of the second user 33 (A song service based on the second control message may be provided through 120-6.

Returning to FIG. 2 again, the storage unit 260 may store the selection history of at least one user participating in the chat room with the karaoke chatbot. For example, the storage unit 260 may store a selection history for each user participating in the chat room by mapping with a chat room identifier assigned to the chat room. In addition, the storage unit 260 may store the user's music selection history in the order of song reservation time.

The storage unit 260 may manage songs preferred by each user based on the music selection history for each identifier of each of the plurality of users. For example, the storage unit 260 may select and manage a song whose number of reserved songs is equal to or greater than a preset number or a song whose song score is equal to or greater than a preset score among the stored user-specific selection histories as preferred songs of each user.

The response transmission unit 220 may transmit information on a reserved song (eg, a title of a reserved song and a singer's name, etc.) to the messenger server 110 through a chat room with a karaoke chatbot. Information on music selection may be displayed in a chat room through the messenger server 110.

For example, when the message processing unit 210 receives from the messenger server 110 a message including "what is the next reserved song name" input into the chat room with the karaoke chatbot, the song name reserved in the next order from the message Deriving a control command to search for and linking information on the song name to be output in the next order of songs currently being output from the sound output device 120 with the storage unit 260 and an external server based on the derived control command You can search. That is, the message processing unit 210 searches for the song name to be output in the next order of the song currently output from the sound output device 120 from the selection history stored in the storage unit 260, and provides information on the searched song name from an external server. I can receive it. Thereafter, the response transmission unit 220 may transmit information on the searched song name to the messenger server 110 when a song title scheduled to be output is searched in the next order of songs currently being output from the sound output device 120. Information on the searched song name may be transmitted to the chat room through the messenger server 110.

The score management unit 240 may map and manage scores for each identifier of at least one user based on a song reservation by at least one user. For example, the score management unit 240 may map and manage a score calculated based on the pitch and beat of a song reserved by at least one user in the order of song reservation, with an identifier of a corresponding user.

The response transmission unit 220 may transmit a score for each identifier of at least one user to the messenger server 110. For example, the response transmission unit 220 may transmit, to the messenger server 110, a score mapped to an identifier of a user who requested the completed song each time songs are completed in the order of song reservation.

The response transmission unit 220 terminates the song for each user according to the song reservation, and a message for requesting information on the song result from at least one user through the chat room (e.g., informs the result of the song competition, informs the score of the song so far, Or, when request information for a specific number (who is first, or who is last, etc.) is input, information about the song result to the messenger server 110 (eg, score results sorted in descending order, song competition 1st place) ** or, the song match is **, etc.) can be transmitted to the messenger server 110.

For example, the response transmission unit 220 ends the song for each user according to the song reservation, and a message requesting sharing of the song result from at least one user to a specific user or a specific chat room through a chat room (e.g., ** Send the song result to the first chat room, share the song result to the first chat room, etc.), information on the target to share the song result to the messenger server 110 (e.g., the identifier of the shared object and the identifier of the shared chat room) And song result information. The song result information may be transmitted to the sharing object based on information on the object to be shared with the song result.

For example, when the message processing unit 210 receives from the messenger server 110 a message including "show playlist" input to a chat room with a karaoke chatbot, the message is played through the sound output device 120 from the message. A control command for filtering the selection list is derived, the selection list played from the storage unit 260 is filtered based on the derived control command, and information on the song names included in the filtered played selection list is transmitted from an external server. Can be provided. Thereafter, the response transmission unit 220 may transmit the information on the song name included in the played song selection list, the name of the person who reserved each song name, and the song score to the messenger server 110. The name of the person who reserved each song name, along with information on the song name included in the played song selection list, and the song score may be displayed in the chat room through the messenger server 110.

As another example, when a message including'tell me about the songs I sang' is input by the first user to a chat room with the karaoke chatbot, the message processing unit 210 determines the first user's identifier from the selection history stored in the storage unit 260. At least one song selection mapped to (a song name that the first user sang in the past) may be extracted, and information on at least one selection mapped to the extracted first user's identifier may be provided from an external server. Thereafter, the response transmission unit 220 may transmit information on at least one song selection mapped to the first user's identifier and a score for each song song to the messenger server 110. The information on at least one song selection mapped to the first user's identifier and the song score for each song selection may be transmitted to a chat room with a karaoke chatbot or to an individual chat room of the first user.

When a song recommendation is requested from at least one user participating in the chat room with the karaoke chatbot, the recommendation unit 270 may recommend at least one song based on the selection history. For example, when a message for recommending a song from the first user is input into the chat room, the recommendation unit 270 may select a song preferred by the first user among the selection history stored in the storage unit 260 (e.g., the identifier of the first user). Based on the searched songs, a song in which the reservation number is recorded more than a preset number, or a song whose song score is more than a preset score among songs sung by the first user) may be extracted and recommended to the first user. Alternatively, the recommendation unit 270 may further recommend a song similar to the extracted song to the first user when a song preferred by the first user is extracted from the selection history. The response transmission unit 220 may transmit a song sound source corresponding to a recommended song for the first user received from an external server or a link to a song sound source to the messenger server 110.

For example, when a plurality of users participating in a chat room are located in different spaces and each user wants to receive karaoke service through different sound output devices arranged in different spaces, the response transmission unit 220 A notification message indicating the start and end of a song through different sound output devices arranged in different spaces may be transmitted to the messenger server 110 according to the order of the song reservation in which the song is reserved through the message input of.

The chatbot activation unit 200 may receive a chatbot deactivation signal from the messenger server 110 and deactivate the chatbot in the chat room based on the chatbot deactivation signal. For example, when at least one user participating in the chat room with the karaoke chatbot leaves the karaoke chat bot from the chat room or all users participating in the chat room leave the chat room, the chatbot activation unit 200 is the messenger server 110 ), the chatbot deactivation signal can be received, and the chatbot in the chat room can be deactivated. Alternatively, when a message related to the termination of the karaoke service is input to the chat room, the chatbot activation unit 200 may receive a chatbot deactivation signal from the messenger server 110 and deactivate the chatbot in the chat room. In this case, when receiving the chatbot deactivation signal, the karaoke chatbot of the chat room may be exited from the chat room.

4 is a flowchart of a method for providing a karaoke service through an instant messaging service according to an embodiment of the present invention. 4, in step S401, the chatbot server 100 receives a chatbot activation signal including chat room information corresponding to the chat room from the messenger server 110, and activates the chatbot participating in the chat room based on the chatbot activation signal. can do. Here, the chat room information may include at least one of an identifier of a chat room, an identifier of at least one user participating in the chat room, and information on the sound output device 130.

In step S403, the chatbot server 100 receives a plurality of messages input through the chat room from the messenger server 110, performs natural language processing on the plurality of messages, and responds to a control command and control command related to the karaoke service. Can be derived.

In step S405, the chatbot server 100 may transmit a response to the derived control command to the messenger server 110.

In step S407, the chatbot server 100 may provide a karaoke service to the sound output device 120 corresponding to the chat room based on the derived control command.

Although not shown in FIG. 4, in step S403, the chatbot server 100 extracts song information based on a message input from at least one user participating in the chat room, and reserves a song for at least one user based on the song information. You can do it. Although not shown in FIG. 4, in step S407, the chatbot server 100 receives a song sound source or a link to a song sound source corresponding to a song reservation for at least one user from an external server, and the received song sound source or song sound source The link to the message may be transmitted to the messenger server 110. Although not shown in FIG. 4, after step S407, the chatbot server 100 may receive a chatbot deactivation signal from the messenger server 110 and deactivate the chatbot based on the chatbot deactivation signal.

5 is a block diagram of a messenger server 110 according to an embodiment of the present invention. 5, the messenger server 110 according to an embodiment of the present invention may include a chatbot invitation unit 500, a message transmission unit 510, a response receiving unit 520, and a response output unit 530. have. However, the configuration of the messenger server 110 according to an embodiment of the present invention may be different from that of FIG. 5.

The chatbot invitation unit 500 receives an invitation request from the karaoke chatbot from at least one user participating in the chat room, invites the karaoke chatbot to the chat room, and sends a chatbot activation signal including chat room information corresponding to the chat room to the chatbot server 100 Can be sent to. For example, when the terminal of at least one user participating in the chat room scans a digital code attached to the sound output device 120 disposed in the karaoke room, or inputs the serial number of the sound output device 120 into the chat room, The chatbot invitation unit 500 may invite a karaoke chatbot that controls the sound output device 120 to a chat room. The chatbot invitation unit 500 sends a chatbot activation signal including chat room information corresponding to the chat room (e.g., the identifier of the chat room, information on the sound output device 120 input to the chat room, and the identifier of the user participating in the chat room). It can be transmitted to the server 100.

Alternatively, when the terminal of at least one user participating in the chat room selects a karaoke chatbot from among a plurality of chatbots previously registered as virtual friends in the instant messaging application, the chatbot invitation unit 500 may invite the karaoke chatbot to the chat room. The chatbot invitation unit 500 includes information about the chat room corresponding to the chat room (e.g., the identifier of the chat room, information on the sound output device 120 mapped to the account of at least one user participating in the chat room, and the identifier of the user participating in the chat room) A chatbot activation signal including) may be transmitted to the chatbot server 100.

The message transmission unit 510 may receive a plurality of messages from at least one user through a chat room with a karaoke chatbot and transmit the plurality of messages to the chatbot server 100. For example, when at least one user participating in a chat room with a karaoke chatbot inputs a message into the chat room, the message transmission unit 510 sends the message together with the identifier of at least one user who entered the message. It can be transmitted to the server 100. Here, the plurality of messages input through the chat room with the karaoke chatbot may include various control messages related to the karaoke service. For example, in a plurality of messages, a request message for a specific song reservation, a request message for a list of reserved song names, a request message for information on the song name played through the sound output device 120, and a sound output for each user participating in a chat room A request message for a song title list played through the device 120 may be included.

The response receiver 520 may receive a response to a control command derived based on natural language processing performed on a plurality of messages from the chatbot server 100. For example, if a message containing "IU good day reservation me 'to the chat room with the karaoke chaetbot entered into the chat room with the karaoke chaetbot, the response receiving section 520 from chaetbot server 100' IU good day of booking It is possible to receive a response to the control command including'it has been done' from the chatbot server 100. For example, when a message including'Show a list of reserved songs' by at least one user is input into a chat room with a karaoke chatbot, the response receiver 520 includes'outputs a list of reserved songs'. A response to a control command including information on a reserved song list together with a message may be received from the chatbot server 100. For example, when a message including'terminate karaoke service' is input to a chat room with a karaoke chatbot, the response receiver 520'terminates the karaoke service' in response to a control command for which the karaoke service termination command was executed. A response including'do' may be received from the chatbot server 100.

When the control command derived from at least one message processed in natural language is a control command related to song reservation, the response receiving unit 520 is a song sound source or song sound source corresponding to the song reservation for at least one user from the chatbot server 100 You can receive a link to.

The response output unit 530 may output a song sound source or a link to a song sound source to a personal chat room or a group chat room of each of the at least one user.

For example, the response receiver 520 outputs a control command derived from at least one message processed in natural language (eg, a message including “what is the next reserved song name”) through the current sound output device 120 In the case of a command related to a search for a song title reserved in the next order of a sound source being played, information on a song title scheduled to be output in the next order may be received from the chatbot server 100 as a response to the corresponding control command.

For example, the response receiving unit 520 may provide a control command derived from at least one message processed in natural language (e.g., tell me the result of a song match, tell me the score of the song so far, etc.) related to the song result (eg, score, ranking, etc.) In the case of a command, information about the song result from the chatbot server 100 as a response to the corresponding control command (eg, score result sorted in descending order, song match 1 is **. Or, song match last is **. .Etc).

For example, the response receiving unit 520 may provide a control command derived from at least one message processed in natural language (e.g., send the song result to **, share the song result to the first chat room, etc.) related to the sharing of the song result. In the case of a command, information about an object to be shared (eg, an identifier of a sharing object and an identifier of a shared chat room) and song result information may be received from the chatbot server 100 as a response to the corresponding control command. In this case, the song result information may be transmitted to the sharing object based on information on the object to be shared with the song result.

The response output unit 530 may output a response to the control command received from the chatbot server 100 to a chat room. In this case, a karaoke service may be provided to the sound output device 120 corresponding to the chat room based on the control command. For example, when the control command is a command related to song reservation, information on the reserved song may be transmitted to the sound output device 120 and a sound source of the reserved song may be output through the sound output device 120.

When receiving a request to leave the chatbot from at least one user, the chatbot invitation unit 500 may transmit a chatbot deactivation signal to deactivate the chatbot to the chatbot server 100. Thereafter, when the chatbot server 100 receives the chatbot deactivation signal, it may exit the chatbot from the chat room.

For another example, when a message related to termination of a karaoke service is input to a chat room, the chatbot inviting unit 500 may transmit a chatbot deactivation signal to the chatbot server 100. Alternatively, when all users participating in the chat room have left the chat room, the chatbot inviting unit 500 may transmit a chatbot deactivation signal to the chatbot server 100 and exit the chatbot from the chat room.

An embodiment of the present invention may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. Computer-readable media can be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Further, the computer-readable medium may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

Although the methods and systems of the present invention have been described in connection with specific embodiments, some or all of their components or operations may be implemented using a computer system having a general-purpose hardware architecture.

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that other specific forms can be easily modified without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative and non-limiting in all respects. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

100: chatbot server 110: messenger server
120: sound output device

Claims (17)

In a chatbot server that provides a karaoke service through an instant messaging service,
A chatbot activation unit receiving a chatbot activation signal including chat room information corresponding to the chat room from the messenger server, and activating a chatbot participating in the chat room based on the chatbot activation signal;
A message processing unit for receiving a plurality of messages input through the chat room from the messenger server and performing natural language processing on the plurality of messages to derive a control command for a karaoke service and a response to the control command; And
A response transmission unit for transmitting a response to the control command to the messenger server;
The karaoke service provider for providing the karaoke service through a sound output device corresponding to the chat room based on the control command
That includes, a chatbot server.
The method of claim 1,
The chat room information includes at least one of an identifier of the chat room, an identifier of at least one user participating in the chat room, and information on the sound output device.
The method of claim 1,
The message processing unit is a reservation unit that extracts song information based on a message input from at least one user participating in the chat room, and performs a song reservation for the at least one user based on the song information
That includes, a chatbot server.
The method of claim 3,
The response transmission unit transmits a response to the song reservation to the messenger server,
The response to the song reservation includes information of the at least one user and the song information.
The method of claim 3,
Score management unit for mapping and managing scores for each identifier of the at least one user based on the song reservation
That further comprises a chatbot server.
The method of claim 5,
The response transmission unit transmits the score for each identifier of the at least one user to the messenger server.
The method of claim 3,
A sound source receiver for receiving a song sound source corresponding to a song reservation for the at least one user from an external server or a link to the song sound source
Including more,
The response transmission unit transmits the song sound source or a link to the song sound source to the messenger server,
The song sound source or the link to the song sound source is provided to a personal chat room of each of the at least one user.
The method of claim 1,
A storage unit for storing the music selection history of at least one user participating in the chat room; And
When a song recommendation is requested from at least one user participating in the chat room, a recommendation unit recommending at least one song based on the selection history
That further comprises a chatbot server.
The method of claim 1,
The chatbot activation unit receives a chatbot deactivation signal from the messenger server and deactivates the chatbot based on the chatbot deactivation signal.
The method of claim 9,
When receiving the chatbot activation signal, the chatbot is participating in the chat room, and when receiving the chatbot deactivation signal, the chatbot is exited from the chat room.
In a messenger server providing a karaoke service through an instant messaging service,
A chatbot invitation unit for receiving an invitation request from a chatbot from at least one user participating in the chat room, inviting the chatbot to the chat room, and transmitting a chatbot activation signal including chat room information corresponding to the chat room to the chatbot server;
A message transmission unit receiving a plurality of messages from the at least one user and transmitting the plurality of messages to the chatbot server;
A response receiver configured to receive a response to a control command derived based on natural language processing performed on the plurality of messages from the chatbot server; And
Response output unit for outputting a response to the control command to the chat room
Including,
The messenger server, wherein the karaoke service is provided through a sound output device corresponding to the chat room based on the control command.
The method of claim 11,
The response receiver receives a song sound source corresponding to a song reservation for the at least one user or a link to the song sound source from the chatbot server,
The response output unit outputs the song sound source or a link to the song sound source to a personal chat room of each of the at least one user.
The method of claim 11,
The chatbot invitation unit receives a request to leave the chatbot from the at least one user, leaves the chatbot from the chat room, and transmits a chatbot deactivation signal to the chatbot server.
In the method for providing a karaoke service through an instant messaging service performed by a chatbot server,
Receiving a chatbot activation signal including chat room information corresponding to the chat room from a messenger server, and activating a chatbot participating in the chat room based on the chatbot activation signal;
Receiving a plurality of messages input through the chat room from the messenger server, and performing natural language processing on the plurality of messages to derive a control command for a karaoke service and a response to the control command;
Transmitting a response to the control command to the messenger server; And
Providing the karaoke service through a sound output device corresponding to the chat room based on the control command
That includes, a karaoke service providing method.
The method of claim 14,
The step of deriving a response to the control command,
Extracting song information based on a message input from at least one user participating in the chat room, and performing a song reservation for the at least one user based on the song information
That includes, a karaoke service providing method.
The method of claim 15,
Receiving a song sound source corresponding to a song reservation for the at least one user or a link to the song sound source from an external server; And
The response transmission unit transmitting the song sound source or a link to the song sound source to the messenger server
The method of providing a karaoke service further comprising a.
The method of claim 14,
Receiving a chatbot deactivation signal from the messenger server and deactivating the chatbot based on the chatbot deactivation signal
The method of providing a karaoke service further comprising a.

Images