JP7365195B2 - karaoke system - Google Patents

Description

The present invention relates to a karaoke system.

BACKGROUND ART When a karaoke device is used by a plurality of users, a technique is known that recommends songs for karaoke singing to the users.

For example, Patent Document 1 discloses a technique for presenting recommended songs to be sung that a plurality of users can enjoy in common, using a music playlist for each user.

Japanese Patent Application Publication No. 2015-210343

Here, in Patent Document 1, the music registered in a music playlist of a certain user is a favorite music that the certain user has downloaded to a mobile information terminal. Therefore, some users do not want other users to sing karaoke songs on their own song playlists. In other words, some users may want to sing a certain song themselves at karaoke, or they may prefer to have it sung by a professional artist and may not be satisfied with karaoke singing by an amateur user. .

However, when the technology of Patent Document 1 is used, the user (singer) who performs karaoke singing, the user (audience) who appreciates karaoke singing does not want to perform karaoke singing (i.e., the music playlist of the audience). registered songs) may be recommended.

An object of the present invention is to provide a karaoke system that can recommend songs that a singer would like to sing at karaoke and songs that an audience would like to enjoy karaoke singing.

One invention for achieving the above object includes a first storage unit that associates song identification information of a song karaoke-sung by a user with user identification information of the user and stores it as a singing history. ,
A second storage unit that associates the song identification information of the song that the user has watched karaoke singing with the user identification information of the user and stores it as a viewing history; A login processing unit that performs logging in as a user, and when a certain user among the multiple logged-in users inputs an instruction to recommend a song, the user identification information of the certain user is used as the user identification information of the singer. an acquisition unit that acquires information, a singing history that is linked to the acquired user identification information of the singer among the singing histories stored in the first storage unit, and the second storage unit. Based on the listening history that is linked to the user identification information of the audience member who is a user other than the singer, out of the listening history stored in the song, songs that are common to the singing history and the listening history are selected. The karaoke system includes an extraction section that extracts the music, and a notification section that notifies the singer of the extracted music.
Other features of the present invention will become clear from the description and drawings described below.

According to the present invention, it is possible to recommend a song that a singer would like to sing at karaoke and a song that the audience would like to enjoy karaoke singing.

FIG. 1 is a diagram schematically showing a karaoke system according to a first embodiment. FIG. 1 is a diagram showing a server device according to a first embodiment. It is a figure showing the singing history memorized by the 1st storage part concerning a 1st embodiment. FIG. 7 is a diagram showing viewing history stored in a second storage unit according to the first embodiment. FIG. 1 is a diagram showing a karaoke apparatus according to a first embodiment. It is a figure showing a karaoke main body concerning a 1st embodiment. It is a flowchart which shows the processing of the karaoke system concerning a 1st embodiment. FIG. 3 is a diagram showing a server device according to a second embodiment. It is a flowchart which shows the processing of the karaoke system concerning a 2nd embodiment. FIG. 3 is a diagram showing a karaoke apparatus according to a first modification. It is a figure showing the karaoke main body concerning modification 1. It is a figure which shows the karaoke main body based on the modification 2.

<First embodiment>
A karaoke system according to a first embodiment will be described with reference to FIGS. 1 to 7.

==Karaoke system==
As shown in FIG. 1, the karaoke system 1 according to this embodiment includes a server device S and a karaoke device K. The server device S and the karaoke device K are communicably connected via a network N. The network N is, for example, a transmission path such as a public telephone line network or an Internet line.

==Server device==
The server device S is a computer that manages and processes various information. FIG. 2 is a diagram showing the configuration of the server device S. The server device S includes a storage means 10, a communication means 20, and a control means 30. Each component is connected to bus B via an interface (not shown).

[Storage means]
The storage means 10 is a large capacity storage device that stores various data. In this embodiment, part of the storage area of the storage means 10 functions as a first storage section 10a and a second storage section 10b.

(first storage section)
The first storage unit 10a associates the song identification information of the song karaoke-sung by the user with the user identification information of the user and stores it as a singing history.

The song identification information is unique information set for each song, such as a song ID. The user identification information is unique information set for each user, such as a user ID, for example.

When a user who has logged in to karaoke device K (described later) performs karaoke singing, karaoke device K associates the song ID of the song to be karaoke sung with the user ID of the user, that is, the singer, and registers it in the reservation queue. do. The karaoke device K transmits the user ID of the user and the song ID of the song sung at karaoke to the server device S. The first storage unit 10a stores the received music ID in association with the user ID as a singing history. In addition, when a certain user's singing history is already stored, the first storage unit 10a identifies the certain user's singing history based on the received user ID, and stores the newly received song ID. By linking, the singing history is updated. Note that the singing history also includes date information (year, month, day, and time) of karaoke singing.

FIG. 3 is an example of the singing history stored in the first storage unit 10a. In FIG. 3, the song ID of song X1 is "ID**S001", the song ID of song X3 is "ID**S003", the song ID of song X5 is "ID**S005", and the song ID of song X5 is "ID**S005", as the singing history of user U1. The song ID "ID**S007" of song X7, the song ID "ID**S009" of song X9, the song ID "ID**S011" of song X11, and the song ID "ID**S013" of song X13 are used. It is linked to the user ID "ID****U1" of user U1. That is, according to the example of FIG. 3, the user U1 has performed karaoke singing of songs X1, X3, X5, X7, X9, X11, and X13 at least once in the past. In addition, in FIG. 3, information on the date of karaoke singing and the number of times karaoke singing has been performed are omitted.

(Second storage unit)
The second storage unit 10b associates the music identification information of the music for which the user has enjoyed karaoke singing with the user identification information of the user and stores this as a viewing history.

When a user who has logged in to the karaoke device K (described later) watches karaoke singing by a singer, the karaoke device K sends the user ID of the user, that is, the audience, and the song ID of the song watched to the server device S. . The user ID of the audience is the user ID of the logged-in user minus the user ID of the singer. The second storage unit 10b stores the received music ID in association with the user ID as a viewing history. In addition, if the listening history of a certain user is already stored, the second storage unit 10b identifies the listening history of the certain user based on the received user ID, and stores the newly received song ID. By linking, the viewing history is updated. Note that the viewing history also includes viewing date information (year, month, day, and time).

FIG. 4 is an example of the viewing history stored in the second storage unit 10b. In FIG. 4, the listening history of user U2 includes the song ID "ID**S002" for song X2, the song ID "ID**S004" for song X4, the song ID "ID**S006" for song X6, and the song ID "ID**S006" for song X6. The song ID "ID**S007" of song X7, the song ID "ID**S010" of song X10, the song ID "ID**S012" of song X12, and the song ID "ID**S013" of song X13 are used. It is linked to the user ID "ID***U2" of user U2. That is, according to the example of FIG. 4, the user U2 has listened to karaoke singing of songs X2, X4, X6, X7, X10, X12, and X13 at least once in the past. In addition, as user U3's listening history, the song ID of song X4 is "ID**S004," the song ID of song X5 is "ID**S005," the song ID of song X7 is "ID**S007," and the song is of song X8. ID “ID**S008”, song ID “ID**S011” of song X11, and song ID “ID**S013” of song It is tied. That is, according to the example of FIG. 4, user U3 has listened to karaoke singing of songs X4, X5, X7, X8, X11, and X13 at least once in the past. Note that in FIG. 4, information on the date of viewing and the number of viewings are omitted.

[Communication means]
The communication means 20 provides an interface for communicating with the karaoke apparatus K.

[Control means]
The control means 30 performs various controls in the server device S. The control means 30 includes a CPU and a memory (both not shown). The CPU implements various functions by executing programs stored in memory. For example, the control means 30 transmits the singer's singing history and the audience's listening history in response to a request from the karaoke apparatus K (described later).

==Karaoke machine==
The karaoke device K is a device for karaoke performances of songs and for users to sing karaoke. As shown in FIG. 5, the karaoke apparatus K includes a karaoke main body 40, a speaker 50, a display device 60, a microphone 70, and a remote control device 80.

The karaoke main body 40 performs various controls related to karaoke performance and karaoke singing, such as controlling the performance of selected songs, controlling the display of lyrics and background images, and processing audio signals input through the microphone 70. The speaker 50 is configured to emit sound based on a sound emitted signal from the karaoke main body 40. The display device 60 is configured to display videos and images on a screen based on signals from the karaoke main body 40. The microphone 70 is configured to convert the singer's singing voice into an analog audio signal and input it to the karaoke main body 40. The remote control device 80 is a device for performing various operations on the karaoke main body 40.

As shown in FIG. 6, the karaoke main body 40 includes a storage means 40a, a communication means 40b, an input means 40c, and a control means 40d. Each component is connected to bus B via an interface (not shown).

[Storage means, communication means, input means]
The storage means 40a is a large-capacity storage device that stores various data such as music data for performing karaoke. Each song has music identification information set therein. The communication means 40b provides an interface for communicating with the server device S. The input means 40c is configured for the user to input various instructions. The input means 40c is a button or the like provided on the karaoke main body 40. Alternatively, the remote control device 80 may function as the input means 40c.

[Control means]
The control means 40d performs various controls in the karaoke apparatus K. The control means 40d includes a CPU and a memory (both not shown). The CPU implements various functions by executing programs stored in memory.

In this embodiment, the control unit 40d functions as the login processing unit 100, the acquisition unit 200, the extraction unit 300, and the notification unit 400 by the CPU executing a program stored in the memory.

(Login processing section)
The login processing unit 100 performs user login in response to input of user identification information.

For example, assume that three people, user U1, user U2, and user U3, use karaoke machine K. In this case, each of the users U1 to U3 inputs their own user ID via the remote control device 80. The login processing unit 100 completes the login of each user to the karaoke apparatus K by storing the user ID of each user in the storage means 40a.

(Acquisition Department)
When a certain user among the plurality of logged-in users inputs an instruction to recommend a song, the acquisition unit 200 acquires the user identification information of the certain user as the user identification information of the singer. The singer is a user who performs karaoke singing.

For example, assume that after users U1 to U3 log in, user U1 requests a song recommendation. In this case, the user U1 selects the "Recommend" icon displayed on the display screen of the remote control device 80.

In response to the selection of the "recommend" icon, the remote control device 80 causes the display screen to display an icon corresponding to each user currently logged in. The user U1 selects his own icon from among the plurality of icons. Note that the icon corresponding to such a user is, for example, a user ID, a nickname, an illustration of a face, etc. of the user. A nickname and a face illustration can be set at the same time when the user ID is first registered in the karaoke system 1.

The acquisition unit 200 reads the user ID of the user U1 from the storage means 40a according to the selection of the user U1, and acquires it as the user ID of the singer.

(extraction part)
The extraction unit 300 extracts the singing history associated with the acquired user identification information of the singer from among the singing histories stored in the first storage unit 10a and the singing history stored in the second storage unit 10b. Based on the listening history linked to the user identification information of the audience, songs that are common to the singing history and the listening history are extracted from among the listening histories.

The audience is users other than the singer. In the above example, when user U1 becomes a singer, user U2 and user U3 correspond to the audience.

In this case, the extraction unit 300 transmits the user ID of the user U1 to the server device S as the user ID of the singer. The control means 30 of the server device S reads the singing history of the user U1 from the first storage unit 10a and transmits it to the karaoke device K. In the following explanation, it is assumed that the singing history of the user U1 shown in FIG. 3 has been read out.

On the other hand, the extraction unit 300 transmits the user IDs of the user U2 and the user U3 to the server device S as the user IDs of the audience. The control means 30 of the server device S reads the viewing history of the user U2 and the user U3 from the second storage unit 10b and transmits it to the karaoke device K. In the following explanation, it is assumed that the viewing histories of the user U2 and the user U3 shown in FIG. 4 have been read.

The extraction unit 300 compares the received singing history of the user U1 and the listening history of the users U2 and U3, and extracts the song X7 and the song X13 as songs common to all the histories.

Note that when there are multiple songs common to all the histories, the extraction unit 300 only needs to extract at least one song.

Further, the extraction unit 300 extracts music identification information of the music that satisfies the first predetermined condition from among the music identification information of the music included in the singing history, and second music identification information of the music that is included in the listening history. Songs may be extracted based on song identification information of songs that satisfy predetermined conditions.

The first predetermined condition and the second predetermined condition are conditions for narrowing down a plurality of songs included in the history. The predetermined conditions are set based on the most recent period of singing or appreciating karaoke or the number of times.

Here, for example, the first predetermined condition is "the number of times I sang karaoke in the last three months is 10 or more times", and the second predetermined condition is "the number of times I sang karaoke in the last three months is five or more times". Suppose there is.

Furthermore, in the singing history of user U1 in the above example, the songs sung at karaoke in the last three months include song X1, song X3, song X5, song X7, song X9, song X11, and song X13, The number of times each song was sung at karaoke was "Song X1: 10 times", "Song X3: 8 times", "Song X5: 15 times", "Song X7: 13 times", "Song X9: 3 times", " Suppose that the songs are "Music X11: 11 times" and "Song X13: 10 times."

Furthermore, in the listening history of user U2 in the above example, the songs listened to in the last three months include song X2, song X4, song X6, song X7, song X10, song X12, and song X13, The number of times each song was viewed is "Song X2: 11 times," "Song X4: 10 times," "Song X6: 2 times," "Song X7: 15 times," "Song X10: 5 times," "Song X12: 10 times" and "Music X13: 16 times." In addition, in the listening history of user U3 in the above example, the songs listened to in the last three months include song X4, song X5, song X7, song X8, song X11, and song X13, and for each song The number of times I watched "Song X4: 1 time", "Song X5: 10 times", "Song X7: 14 times", "Song X8: 15 times", "Song X11: 3 times", "Song X13: 4" Suppose that it is "times".

In this case, the extraction unit 300 extracts the song IDs of the song X1, song X5, song X7, song X11, and song X13 that satisfy the first predetermined condition from the received singing history of the user U1, and the song IDs of the song X1, the song X5, the song X7, the song X11, and the song Among the histories, the song IDs of song X2, song X4, song X7, song X10, song X12, and song X13 satisfy the second predetermined condition, and among the user U3's viewing history, the second predetermined condition is satisfied. The music IDs of music X5, music X7, and music X8 are compared, and music X7 that is commonly included in all the histories is extracted.

(Notification Department)
The notification unit 400 notifies the singer of the extracted song.

Notification to the singer can be done in various ways. For example, the notification unit 400 can display the name of the extracted song, the name of the singer, etc. on the display screen of the display device 60 or the remote control device 80. The notification unit 400 may also cause the speaker 50 to emit the name of the extracted song. Alternatively, the notification unit 400 may transmit the name of the extracted song, etc. to the singer's mobile terminal that has been paired with the karaoke device K in advance. The singer can check the name of the received song on the mobile terminal by starting a dedicated application installed in advance on the mobile terminal.

==About processing in the karaoke system==
Next, a specific example of processing in the karaoke system 1 according to this embodiment will be described with reference to FIG. FIG. 7 is a flowchart showing an example of processing in the karaoke system 1. In this example, it is assumed that karaoke machine K is used by a plurality of users. Further, it is assumed that the first storage section 10a stores each user's singing history, and the second storage section 10b stores each user's listening history.

The login processing unit 100 performs login of each user according to the input of the user ID from each user (login of multiple users. Step 10).

Here, it is assumed that a certain user among the plurality of users who have logged in inputs an instruction to recommend a song via the remote control device 80 (recommendation instruction input. Step 11).

The acquisition unit 200 acquires the user ID of the certain user as the singer's user ID (acquires the singer's user ID. Step 12).

The extraction unit 300 transmits the singer's user ID to the server device S (sends the singer's user ID. Step 13). The control means 30 of the server device S reads the singer's singing history from the first storage unit 10a and transmits it to the karaoke device K (sends the singer's singing history. Step 14).

Further, the extraction unit 300 transmits the user ID of a logged-in user other than the singer (that is, the audience) to the server device S (sends the user ID of the audience. Step 15). The control means 30 of the server device S reads the audience's viewing history from the second storage unit 10b and transmits it to the karaoke device K (sends the audience's viewing history. Step 16).

Note that steps 15 and 16 may be performed first, and then steps 13 and 14 may be performed. Alternatively, the transmission of the user ID in steps 13 and 15 and the transmission of the history in steps 14 and 16 may be performed simultaneously.

The extraction unit 300 extracts songs that are common to the singing history and the listening history based on the singing history sent in step 14 and the listening history sent in step 16 (extracting common songs. Step 17).

The notification unit 400 notifies the singer of the music extracted in step 17 (notifies the extracted music. Step 18).

As is clear from the above, the karaoke system 1 according to the present embodiment associates the song identification information of the song karaoke-sung by the user with the user identification information of the user and stores it as a singing history. 1 storage unit 10a, a second storage unit 10b that associates the music identification information of the music that the user has watched karaoke singing with the user identification information of the user and stores it as a viewing history; A login processing unit 100 performs user login in response to input information, and when a certain user among the plurality of logged-in users inputs an instruction to recommend a song, the user of the certain user An acquisition unit 200 that acquires identification information as the singer's user identification information, and a song that is linked to the acquired singer's user identification information among the singing histories stored in the first storage unit 10a. Based on the history and the viewing history that is linked to the user identification information of the audience who are users other than the singer, among the viewing history stored in the second storage unit 10b, the singing history and the viewing history are stored in the second storage unit 10b. It has an extraction section 300 that extracts songs common to the listening history, and a notification section 400 that notifies the singer of the extracted songs.

According to the karaoke system 1, songs that are common to the singer's singing history and the audience's listening history can be recommended to the singer. The songs included in the singer's singing history are songs that the singer has sung at karaoke in the past. Therefore, it is a song that the singer can sing karaoke to, and there is a high possibility that it is a song that the singer would like to sing karaoke again. On the other hand, the songs included in the audience's viewing history are songs that the audience has watched karaoke singing in the past. For example, when a plurality of users use a karaoke device, it is not uncommon for one user to request a song that he or she would like to hear karaoke sung by another user. Therefore, it is unlikely that the audience will not want to sing karaoke songs. That is, according to the karaoke system 1 according to the present embodiment, it is possible to recommend a song that a singer would like to sing at karaoke and a song that the audience would like to enjoy karaoke singing.

In addition, the extraction unit 300 according to the present embodiment extracts the song identification information of the songs that satisfy the first predetermined condition from among the song identification information of the songs included in the singing history, and the song identification information of the songs included in the listening history. Among them, songs can be extracted based on the song identification information of songs that satisfy the second predetermined condition.

A song that the singer has recently sung at karaoke or a song that has been sung at karaoke many times is more likely to be a song that the singer is good at or likes. Therefore, there is a higher possibility that the song is a song that the singer would like to perform karaoke singing again. Furthermore, songs that the audience has listened to recently or songs that have been listened to many times are more likely to be songs that the audience listens to often. Therefore, it is less likely that the song is a song that the audience does not want to sing karaoke. That is, according to the karaoke system 1 according to the present embodiment, it is possible to more reliably recommend a song that the singer wants to perform karaoke singing and a song that the audience wants to enjoy karaoke singing.

<Second embodiment>
Next, a karaoke system according to a second embodiment will be described with reference to FIGS. 8 and 9. In this embodiment, an example will be described in which songs are recommended in consideration of user attribute information. Description of the same configuration as in the first embodiment will be omitted.

==Server device==
[Storage means]
In this embodiment, a part of the storage area of the storage means 10 functions as a first storage section 10a, a second storage section 10b, and a third storage section 10c (see FIG. 8).

(Third storage)
The third storage unit 10c stores attribute information including at least gender in association with user identification information.

For example, assume that the user U1 and the user U2 in the first embodiment are male, and the user U3 is female. In this case, the third storage unit 10c stores the attribute information "male" in association with the user ID "ID****U1" of the user U1, and stores the user ID "ID**U1" of the user U2. **U2'' is associated with the attribute information ``Male'', and the user ID ``ID***U3'' of the user U3 is associated with the attribute information ``Female''.

Note that the attribute information may include the user's date of birth, address, place of birth, and the like.

==Karaoke machine==
(extraction part)
In this embodiment, the extraction unit 300 extracts attribute information linked to user identification information of the singer and user identification information of the audience from among the attribute information stored in the third storage unit 10c. Get linked attribute information. Then, the extraction unit 300 extracts a song based on the singing history of the singer and the listening history of an audience member whose gender is different from that of the singer.

For example, as described in the first embodiment, it is assumed that the user U1 is a singer, and the users U2 and U3 are audience members.

In this case, the extraction unit 300 transmits the user ID of the user U1 to the server device S as the user ID of the singer. The control means 30 of the server device S reads the singing history of the user U1 from the first storage unit 10a and transmits it to the karaoke device K. At this time, the control means 30 reads the attribute information of the user U1 from the third storage section 10c and transmits it to the karaoke apparatus K together with the singing history. In the following explanation, it is assumed that the singing history of the user U1 and the attribute information "male" of the user U1 shown in FIG. 3 have been read out.

On the other hand, the extraction unit 300 transmits the user IDs of the user U2 and the user U3 to the server device S as the user IDs of the audience. The control means 30 of the server device S reads the viewing history of the user U2 and the user U3 from the second storage unit 10b and transmits it to the karaoke device K. At this time, the control means 30 reads the attribute information of the user U2 and the user U3 from the third storage unit 10c, and transmits it to the karaoke apparatus K together with the viewing history. In the following explanation, the viewing history of user U2 and the viewing history of user U3 shown in FIG. 4, and the attribute information "male" of user U2 and the attribute information "female" of user U3 are read out. shall be

The extraction unit 300 identifies the viewing history of an audience member whose attribute information is different from that of the singer, based on the received attribute information. In this example, the attribute information of the user U1 and the user U2 is "male", and the attribute information of the user U3 is "female". In other words, the audience member having attribute information different from the attribute information of the user U1 who is the singer is the user U3. Therefore, the extraction unit 300 extracts songs X5, X7, X11, and X13 that are common to the histories, based on the singing history of the user U1 and the listening history of the user U3.

==About processing in the karaoke system==
Next, a specific example of processing in the karaoke system 1 according to this embodiment will be described with reference to FIG. FIG. 9 is a flowchart showing an example of processing in the karaoke system 1. In this example, it is assumed that karaoke machine K is used by a plurality of users. In addition, the first storage unit 10a stores each user's singing history, the second storage unit 10b stores each user's listening history, and the third storage unit 10c stores each user's attribute information. Suppose you remember it.

The processing from step 20 to step 23 is similar to step 10 to step 13 of the first embodiment.

The control means 30 of the server device S reads the singer's singing history from the first storage unit 10a and transmits it to the karaoke device K. The control means 30 also reads the singer's attribute information from the third storage unit 10c and transmits it to the karaoke apparatus K (sends the singer's singing history and attribute information. Step 24).

On the other hand, the extraction unit 300 transmits the user ID of a logged-in user other than the singer (that is, the audience) to the server device S (sends the user ID of the audience. Step 25). The control means 30 of the server device S reads the audience's viewing history from the second storage unit 10b and transmits it to the karaoke device K. The control means 30 also reads the audience's attribute information from the third storage unit 10c and transmits it to the karaoke apparatus K (sends the audience's viewing history and attribute information. Step 26). In addition, in step 24 and step 26, the singing history and the attribute information may be transmitted at different timings.

The extraction unit 300 identifies the viewing history of the audience whose gender is different from that of the singer (identifies the viewing history of a different gender. Step 27), based on the attribute information transmitted in steps 24 and 26.

The extraction unit 300 extracts common songs based on the singing history sent in step 24 and the listening history identified in step 27 from among the listening history sent in step 26. Extraction. Step 28).

The notification unit 400 notifies the singer of the music extracted in step 28 (notifies the extracted music. Step 29).

Note that the extraction unit 300 transmits the user IDs of the singer and the audience to acquire the attribute information of the singer and the audience. Based on the acquired attribute information, the extraction unit 300 specifies the user ID of the audience member whose gender is different from the singer's, and then transmits the user ID of the singer and the audience member whose gender is different from the singer's. The singing history and the viewing history of an audience member whose gender is different from that of the singer may be acquired.

As is clear from the above, the karaoke system 1 according to the present embodiment includes the third storage unit 10c that stores attribute information including at least gender in association with user identification information. Further, the extraction unit 300 extracts attribute information that is linked to user identification information of the singer and user identification information of the audience, among the attribute information stored in the third storage unit 10c. The music piece is extracted based on the singing history of the singer and the viewing history of an audience member whose gender is different from that of the singer.

Generally, even if a male user often listens to songs by a particular female artist, it is difficult for him to sing songs by a female artist at karaoke due to his vocal range. Similarly, even if a female user often listens to songs by a particular male artist, it is difficult for her to sing songs by a male artist at karaoke due to her vocal range. Therefore, there is a high possibility that people would want a singer of the opposite sex to sing such songs at karaoke. Therefore, by using the karaoke system 1 according to the present embodiment, it is possible to recommend a song that an audience member of the opposite sex would like to sing karaoke among songs that a singer would like to sing at karaoke.

<Modification 1>
It is possible to store and update the viewing history according to the audience's concentration level on karaoke singing.

==Karaoke machine==
As shown in FIG. 10, the karaoke apparatus K according to this modification includes a karaoke main body 40, a speaker 50, a display device 60, a microphone 70, a remote control device 80, and a photographing means 90.

The photographing means 90 is, for example, a camera equipped with a wide-angle lens, and photographs the audience watching the karaoke singing to obtain an image.

[Control means]
In this modification, the control unit 40d functions as the login processing unit 100, the acquisition unit 200, the extraction unit 300, the notification unit 400, and the analysis unit 500 by the CPU executing the program stored in the memory (Fig. (see 11).

(Analysis Department)
The analysis unit 500 analyzes a video of an audience listening to karaoke singing of a certain song, which is photographed by the photographing means 90, and determines the degree of concentration of the audience toward the karaoke singing.

Photographing by the photographing means 90 is performed, for example, at the timing when a karaoke performance of a certain song starts.

The image taken by the photographing means 90 includes the singer and the audience. The analysis unit 500 identifies the audience from the video and associates it with user identification information. It is assumed that the user's facial image is previously photographed by the photographing means 90 at the time of the login operation, and the facial image data is registered in association with the user identification information. Alternatively, the face image data may be registered when the karaoke system 1 is used for the first time. The analysis unit 500 extracts the user's face image from the video using a known method, and compares it with the face image data corresponding to the user identification information of the logged-in user. One or more audience members are identified from the list and associated with user identification information.

The audience's concentration level for karaoke singing is a degree that shows how intently the audience is listening to karaoke singing. The audience's concentration on karaoke singing can be determined by using, for example, changes in the audience's facial expressions, body movements, or emotions. For example, the degree of concentration can be determined using the methods described in Patent Document 1 and Japanese Patent Application Publication No. 2016-100033. The degree of concentration can be expressed as a numerical value such as "1" to "10" ("1" being the lowest degree of concentration; "10" being the highest degree of concentration), or as a level such as low, middle, or high.

The analysis unit 500 transmits the concentration level obtained for a certain user to the server device S together with the user ID of the certain user and the song ID of the song whose karaoke singing was appreciated. Only when the concentration level satisfies a predetermined condition (for example, when the concentration level is "6" or higher), the control means 30 of the server device S associates the song ID with the user ID and stores it in a second memory as a viewing history. The information is stored in the unit 10b.

Alternatively, the second storage unit 10b may store the degree of concentration determined by the analysis unit 500 as a viewing history in association with the user ID and the song ID. In this case, when extracting songs to recommend, the extraction unit 300 selects only song IDs that satisfy a predetermined condition (for example, concentration level is "6" or higher) from among the song IDs included in the audience's listening history, and the singing history. Compare the song ID included in the song ID.

When the degree of concentration for karaoke singing of a certain song is high, there is a low possibility that the certain song is a song that the audience does not want to sing karaoke. That is, it can be determined whether the audience wants to watch karaoke singing or not, depending on the concentration level. By extracting songs to recommend using the listening history according to the concentration level, it is possible to more reliably recommend songs that the singer wants to sing at karaoke and songs that the audience wants to watch karaoke singing.

<Modification 2>
It is also possible to edit the viewing history once stored.

==Karaoke machine==
[Control means]
In this modification, the CPU executes the program stored in the memory, so that the control means 40d functions as the login processing section 100, the acquisition section 200, the extraction section 300, the notification section 400, and the editing section 600 (Fig. 12).

(Editorial department)
The editing unit 600 deletes music identification information of music included in the user's listening history in response to an instruction input from the user.

For example, assume that the viewing history shown in FIG. 4 is stored in the second storage unit 10b. Here, if the user U2 wishes to edit the viewing history, he selects the "viewing history editing mode" from the remote control device 80 and inputs his user ID. The editing unit 600 transmits the input user ID to the server device S. The control means 30 of the server device S reads the viewing history of the user U2 from the second storage unit 10b based on the received user ID, and transmits it to the karaoke device K that sent the user ID.

The remote control device 80 displays the song name on the display screen based on the received listening history. User U2 selects music piece X2 that he wishes to delete from the listening history on the display screen and issues a deletion instruction. When a deletion instruction is input, the editing unit 600 deletes the song ID of the song X2 from the listening history.

When the user U2 has finished editing, the user U2 selects the end icon. The editing unit 600 associates the edited viewing history (the viewing history with the song ID of the song X2 deleted) with the user ID of the user U2 and transmits it to the server device S. The control means 30 of the server device S updates the viewing history of the user U2 stored in the second storage unit 10b based on the user ID.

For example, even though the song is not your favorite, you may end up listening to it because your boss at work sings it, and the song may end up being stored in your listening history. According to the configuration of this modification, by making the listening history editable, even if the listening history includes a song that the user does not originally want to listen to, that song can be deleted. Therefore, when recommending music using the audience's listening history as in the above embodiment, the extraction unit 300 can reliably extract only the music that the audience would like to enjoy karaoke singing.

<Others>
In the above embodiment, an example has been described in which the server device S includes the first storage section 10a, the second storage section 10b, and the third storage section 10c. On the other hand, the karaoke apparatus K may be configured to have these storage sections. In this case, the karaoke apparatus K itself functions as a karaoke system.

Further, in the above embodiment, the extraction unit 300 transmits the user ID of the singer to the server device S to acquire the singing history, and transmits the user ID of the audience to the server device S to acquire the listening history. . On the other hand, at the time of logging into the karaoke apparatus K, it is also possible to obtain the user's singing history and listening history in advance.

Specifically, when users U1 to U3 log in to karaoke device K, login processing unit 100 requests server device S for the singing history and listening history of users U1 to U3. The control means 30 of the server device S reads the singing history of the users U1 to U3 from the first storage unit 10a and transmits it to the karaoke device K. Further, the control means 30 of the server device S reads out the viewing histories of the users U1 to U3 from the second storage unit 10b and transmits them to the karaoke device K. The storage means 40a temporarily stores the received singing history and listening history.

It is assumed that the acquisition unit 200 then acquires the user ID of the user U1 as the user ID of the singer.

In this case, the extraction unit 300 acquires the singing history of the user U1 stored in the storage means 40a based on the user ID of the user U1. On the other hand, the extraction unit 300 obtains the viewing history of the user U2 and the user U3 stored in the storage unit 40a based on the user ID of the user U2 and the user U3.

The above embodiments are presented as examples and do not limit the scope of the invention. The above configurations can be implemented in appropriate combinations, and various omissions, substitutions, and changes can be made without departing from the gist of the invention. The above-described embodiments and their modifications are included within the scope and gist of the invention as well as within the scope of the invention described in the claims and its equivalents.

1 Karaoke system 10a First storage unit 10b Second storage unit 10c Third storage unit 100 Login processing unit 200 Acquisition unit 300 Extraction unit 400 Notification unit 500 Analysis unit 600 Editorial unit K Karaoke device S Server device

Claims (4)

a first storage unit that associates music identification information of a music song performed by the user with the user identification information of the user and stores it as a singing history;
a second storage unit that associates the song identification information of the song that the user has watched karaoke singing with the user identification information of the user and stores it as a viewing history;
a login processing unit that logs in a user in response to input of user identification information;
an acquisition unit that acquires user identification information of the certain user as user identification information of a singer when a certain user among the plurality of logged-in users inputs an instruction to recommend a song;
Among the singing histories stored in the first storage unit, the singing history linked to the acquired user identification information of the singer and the appreciation history stored in the second storage unit. an extraction unit that extracts songs that are common to the singing history and the listening history, based on the listening history linked to the user identification information of the audience who are users other than the singer;
a notification unit that notifies the singer of the extracted song;
has
The extracting unit extracts music identification information of a music piece that satisfies a first predetermined condition from among the music identification information of music pieces included in the singing history, and second music identification information of a music piece included in the listening history. A karaoke system that extracts music based on music identification information of music that satisfies predetermined conditions . a third storage unit that stores attribute information including at least gender in association with user identification information;
The extraction section is
Among the attribute information stored in the third storage unit, attribute information linked to the user identification information of the singer and attribute information linked to the user identification information of the audience. Acquired,
2. The karaoke system according to claim 1, wherein the music is extracted based on the singing history of the singer and the listening history of an audience member whose gender is different from that of the singer. It has an analysis unit that analyzes a video of an audience watching karaoke singing of a certain piece of music captured by a camera, and determines the degree of concentration of the audience towards karaoke singing;
The second storage unit is characterized in that the second storage unit stores music identification information of the certain music in association with user identification information of the audience in accordance with the concentration level determined for the certain music as the appreciation history. The karaoke system according to claim 1 or 2 . 4. The apparatus according to claim 1 , further comprising an editing section that deletes song identification information of songs included in the listening history of the user in response to an instruction input from the user. karaoke system.

Images