JP7532202B2 - Karaoke equipment - Google Patents

Description

The present invention relates to a karaoke device.

Conventionally, there are many known technologies that recommend songs to users of karaoke machines to play karaoke, known as recommendation technologies. By recommending songs using recommendation technologies, it is possible to reduce the effort required for users to search for songs. For example, one recommendation technology recommends popular songs based on a national ranking of the number of songs sung over a recent specified period. This type of recommendation technology is suitable for users who enjoy the challenge of singing new songs at karaoke. For this reason, some karaoke machines are equipped with recommendation technologies.

For example, the karaoke system described in Patent Document 1 recommends to a user at an appropriate timing a predetermined number of songs or songs that are ranked high in frequency of performance from among songs sung by the user. In other words, the recommendation technology described in Patent Document 1 recommends songs based on the user's singing history. This type of recommendation technology is suitable for users who often sing songs that they are good at (so-called signature songs) or classic songs.

The method of selecting recommended songs described in Patent Document 2 creates a ranking list for each user organized in order of frequency of singing, compares songs at or above a certain rank in the user's ranking list and other people's ranking lists, and targets other people's ranking lists that have a certain number of songs in common, extracts any songs that are common to the ranking lists that have a certain percentage or more, creates a recommended song list, and presents it appropriately. In other words, the recommendation technology described in Patent Document 2 recommends songs based on the singing history of other users with similar tastes. This type of recommendation technology is suitable for users who are willing to try singing a new song that suits them when they find one.

The communication karaoke system described in Patent Document 3 includes a host device and a karaoke performance terminal. The host device has a performance order summary information file in which a list of songs that were played after each song is associated with the song, and the frequency of playing each song on each list is uniformly tallied. The karaoke performance terminal refers to the performance order summary information file each time the accompaniment music of each song is played, extracts a predetermined number of songs in descending order of frequency of playing based on the song group list corresponding to the song, and displays these songs on the display device together with the song titles and selection numbers to recommend them as candidates to be played next.

JP 2006-276547 A JP 2006-337405 A Japanese Patent Application Publication No. 11-052965

As described above, there are various types of recommendation technologies, and since different users are suitable for different recommendation technologies, the karaoke device may be equipped with a recommendation technology that is not suitable for the user. Therefore, a karaoke device may be equipped with multiple recommendation technologies, and the user may be allowed to select which recommendation technology is used to recommend songs. However, since recommendation technologies are originally intended to reduce the user's song search operations, it is not wise to increase the user's selection operations. In addition, although it is possible to present the same number of songs recommended by multiple recommendation technologies, a certain number of songs are always recommended even if the recommendation technology is not suitable for the user, which inevitably results in a lot of waste. In particular, when multiple users enjoy karaoke in a group, even if the suitable recommendation technology differs between users, the same number of songs will be recommended simultaneously by each recommendation technology. In this way, conventional karaoke devices are unable to efficiently recommend songs using recommendation technologies suitable for group users.

The object of the present invention is to provide a karaoke device that can efficiently recommend songs using recommendation technology suited to a group of users.

To solve the above problem, the karaoke device of the present invention includes an acquisition unit that acquires first information estimated to be the preferences of a plurality of users and second information estimated to be the preferences of users other than the plurality of users in order to recommend songs to be performed as karaoke to the plurality of users; a first recommendation unit that recommends a predetermined first number of the first songs to the plurality of users based on the first information; a second recommendation unit that recommends a predetermined second number of the second songs to the plurality of users based on the second information; and a determination unit that acquires the first number of times that a song has been performed in response to a recommendation to a user, the first number of times that a song has been performed in response to a recommendation to a user, and the second number of times that a song has been performed in response to a recommendation to a user, and determines the ratio between the first number of songs and the second number of songs based on the first number of times that a song has been performed and the second number of times that a song has been performed.

According to the present invention, music can be efficiently recommended using recommendation technology suited to a group of users.

1 is a block diagram showing a karaoke system including a karaoke device according to a first embodiment of the present invention; 5 is a flowchart showing a song recommendation operation of the karaoke apparatus according to the first embodiment of the present invention. FIG. 11 is a block diagram showing a karaoke system including a karaoke device according to a second embodiment of the present invention. 10 is a flowchart showing a song recommendation operation of the karaoke apparatus according to the second embodiment of the present invention.

[First embodiment]
A karaoke device 1 according to a first embodiment of the present invention will now be described.

[Karaoke system]
Fig. 1 is a block diagram showing the configuration of a karaoke system 100 including a karaoke machine 1 according to the first embodiment. As shown in Fig. 1, the karaoke system 100 includes a karaoke machine 1, a server device 2, a display device 3 such as a monitor, a speaker 4, a microphone 5, and a remote control device 6. Although Fig. 1 shows one karaoke machine 1, the karaoke system 100 may include multiple karaoke machines 1 for one server device 2.

For example, the karaoke device 1, display device 3, speaker 4, microphone 5 and remote control device 6 are installed in an installation location such as a karaoke room, and the server device 2 is installed outside the installation location. The karaoke device 1 is connected to the server device 2 so as to be able to communicate with each other via a predetermined network (not shown). The karaoke device 1 is connected to the display device 3, speaker 4, microphone 5 and remote control device 6 by wire or wirelessly.

The display device 3 displays lyrics captions along with a background image in time with the karaoke performance based on a video signal etc. from the karaoke device 1. The speaker 4 emits the user's singing voice along with the music performance sound based on a sound emission signal from the karaoke device 1. The microphone 5 converts the user's singing voice into an audio signal and inputs it to the karaoke device 1.

[Server device]
The server device 2 stores user identification information (user ID) of each of the multiple users of the karaoke device 1 to identify each user. The server device 2 receives song identification information (song ID) of songs sung karaoke by each user together with the user ID from the karaoke device 1. The server device 2 associates the song IDs of songs performed karaoke during a predetermined period (e.g., the past one year) with the number of times the songs have been performed and the user ID, and stores them as singing history information of the user (first information estimated to be the user's preferences). In other words, the server device 2 stores the song IDs of songs sung karaoke and the number of times they have been performed as singing history information for each user.

The server device 2 also obtains and stores nationwide singing frequency information (second information presumed to be the preferences of a person other than the user) by acquiring singing history information of each user from all karaoke devices 1 in the karaoke system 100 and running statistics on the information. The nationwide singing frequency information is information that associates song IDs of songs that have been performed as karaoke on any karaoke device 1 throughout the karaoke system 100 during a predetermined period (e.g., the past year) with the number of times the songs have been performed.

[Remote control device]
The remote control device 6 is mainly composed of a touch panel. The remote control device 6 displays various screens and various operation buttons on the touch panel, and also accepts login operations and song selection (reservation) operations via the touch panel. The remote control device 6 and the karaoke device 1 are paired via wireless communication, so that various information is transmitted and received between the remote control device 6 and the karaoke device 1.

The remote control device 6 transmits the user ID and other information input in response to the user's login operation to the karaoke device 1. The remote control device 6 accepts song selection (reservation) by searching for songs or selecting recommended songs, and transmits the song ID of the song selected (reserved) in response to the user's song selection (reservation) operation to the karaoke device 1 as reserved song information. Note that when multiple users are logged in, the remote control device 6 may accept the selection of the user who will sing karaoke during the song selection operation, and transmit the user ID corresponding to the selected user together with the reserved song information to the karaoke device 1.

[Karaoke equipment]
The karaoke device 1 has a function of providing recommended songs to a plurality of users by a plurality of recommendation means, in addition to a function of performing karaoke of selected (reserved) songs. For example, the karaoke device 1 of the first embodiment provides a first recommendation means based on singing history information of a plurality of users, and a second recommendation means based on nationwide singing frequency information.

The karaoke device 1 comprises a control unit 10, a storage unit 11, and a communication unit 12. The control unit 10 is configured with a CPU (Central Processing Unit) and the like, and controls the karaoke device 1. The storage unit 11 is configured with storage media such as a ROM (Read Only Memory), a RAM (Random Access Memory), and a HDD (Hard Disc Drive). The communication unit 12 is an interface that communicates via a specified network (not shown), and is connected to the server device 2 so as to be able to communicate with it.

The storage unit 11 stores programs and data for controlling each part and function of the karaoke device 1. For example, the storage unit 11 stores basic information such as the song ID, song title, singer name, and genre for each song that the karaoke device 1 can play. The storage unit 11 also stores various data related to karaoke performance, such as song data, for each song ID.

The control unit 10 controls each unit and each function of the karaoke device 1 by executing calculations based on the programs and data stored in the memory unit 11. For example, the control unit 10 of this embodiment operates as a login processing unit 15, an acquisition unit 16, a first recommendation unit 17, a second recommendation unit 18, and a determination unit 19 by executing the programs stored in the memory unit 11.

The login processing unit 15 receives a user ID from the remote control device 6 in response to a login operation of the remote control device 6 by the user, and stores the user ID in the storage unit 11, thereby performing login processing for the user corresponding to the user ID. The login processing unit 15 can allow multiple users who use the karaoke device 1 at the same time to each log in, that is, it accepts simultaneous logins from multiple users. Note that the karaoke device 1 may also have a function for inputting a user ID.

In order to recommend songs to be performed karaoke to the multiple users, the acquisition unit 16 receives and acquires from the server device 2 first information estimated to be the preferences of the multiple users, for example, singing history information of the multiple users, and receives and acquires from the server device 2 second information estimated to be the preferences of users other than the multiple users, for example, nationwide singing frequency information. The singing history information of the multiple users and the nationwide singing frequency information acquired by the acquisition unit 16 may be all songs performed at karaoke during a specified period, or a specified number of songs in descending order of the number of times they have been performed, or songs that have been performed a specified number of times or more. The singing history information of the multiple users and the nationwide singing frequency information acquired by the acquisition unit 16 may be set based on the total number of songs (for example, 20 songs) recommended by the karaoke device 1 to the multiple users.

The first recommendation unit 17 provides a first recommendation means, and recommends a predetermined first number of first songs to a plurality of users based on first information, for example, singing history information of the plurality of users.

The first recommendation unit 17 also calculates the individual number of songs for each of the multiple users in the first number of songs, and extracts the first songs of the individual number of songs calculated for each user based on the singing history information for each user. For example, the first recommendation unit 17 acquires, for each of the multiple users, the first number of times a song has been performed in karaoke in the most recent predetermined number of times that the song was performed in response to the recommendation for the user. The first recommendation unit 17 calculates the individual number of songs for each user based on the ratio of the first number of times a song has been performed for each user to the total number of first times that the multiple users have performed, and the first number of songs.

The second recommendation unit 18 provides a second recommendation means, and recommends a second predetermined number of second songs to a plurality of users based on second information, for example, nationwide singing frequency information.

Furthermore, when a second song is identical to a first song, the second recommendation unit 18 excludes the second song from recommendations by the second recommendation unit 18. When a second song identical to a first song is excluded from the recommended songs, the number of songs recommended to the user may be less than the total number of recommended songs by the amount of the excluded song. Alternatively, the second recommendation unit 18 may further recommend another second song different from the second song based on the second information to fill the excluded number.

The determination unit 19 acquires the first number of times that a song has been performed in response to a recommendation for a user, corresponding to the recommendation by the first recommendation unit 17, and the second number of times that a song has been performed in response to a recommendation for a user, corresponding to the recommendation by the second recommendation unit 18, and determines the ratio between the first number of songs and the second number of songs to be recommended to the multiple users based on the first number of songs and the second number of songs acquired for each of the multiple users. The ratio between the first number of songs and the second number of songs is the ratio out of the total number of songs (e.g., 20 songs) recommended to the multiple users.

[Karaoke device performance operation]
Next, a basic performance operation of the karaoke device 1 when a user sings karaoke will be described.

First, when a user operates the remote control device 6 to input a user ID, the login processing unit 15 in the karaoke device 1 receives the user ID from the remote control device 6 and performs login processing. For example, the login processing unit 15 accepts simultaneous logins from multiple users.

When a user operates the remote control device 6 to reserve a song, the karaoke device 1 receives reserved song information including a song ID and a user ID from the remote control device 6, and registers this reserved song information in the reservation management table of the storage unit 11. The storage unit 11 also stores various data related to karaoke singing, such as song data, for each song ID. The karaoke device 1 reads the reserved song information from the reservation management table in the order of registration, and reads the song data, etc. corresponding to the song ID of this reserved song information from the storage unit 11. The song data includes accompaniment data that is the basis for the accompaniment sounds of the karaoke song, reference data that is the scoring standard for singing, and lyric data that is the basis for the lyric subtitles displayed on the display device 3.

When the karaoke device 1 starts a karaoke performance, a lyric caption and background video are displayed on the display device 3 based on the lyric data and background video data in synchronization with the playback of the accompaniment data. In addition, in the karaoke device 1, the accompaniment sound signal of the karaoke performance and the singing voice signal input from the microphone 5 are mixed at an appropriate ratio by the mixer, and this mixed signal is amplified by the amplifier and output from the speaker 4. In this way, when the singer sings along with the karaoke performance, the singing voice is output from the speaker 4 together with the accompaniment sound. The singing voice is scored based on the reference data. The karaoke device 1 stores the singing score in the memory unit 11 in association with the user ID and the song ID.

In addition, when karaoke performance is started even for a short time or when karaoke performance is started for a predetermined period of time, the karaoke device 1 transmits the song ID of the song that was performed karaoke together with the user ID to the server device 2 in order to save the song as singing history information.

In the karaoke device 1 of the first embodiment, a song recommended by any of the recommendation means may be selected (reserved) and the recommended song may be performed as a karaoke song. For example, the karaoke device 1 identifies a first recommendation means based on the singing history information of each user by using first performance information, and identifies a second recommendation means based on nationwide singing frequency information by using second performance information. When a song recommended by any of the recommendation means is performed as a karaoke song, the karaoke device 1 stores performance information identifying the recommendation means for each user ID in the storage unit 11 as performance performance information of the recommended song. The performance performance information stores performance information for the most recent predetermined number of times in the order in which the karaoke performance was performed. In addition, when a karaoke performance of a recommended song is performed, the karaoke device 1 may transmit the performance information to the server device 2 together with the song ID and the user ID in order to store the performance performance information.

[Music recommendation operation of the first embodiment]
Next, a song recommendation operation by the multiple recommendation means of the karaoke device 1 will be described with reference to Fig. 2. Fig. 2 is a flow chart showing the song recommendation operation of the karaoke device 1.

First, similar to the above, when multiple users U1 to U4 operate the remote control device 6 to input their respective user IDs "xxxU1" to "xxxU4", the login processing unit 15 in the karaoke device 1 receives the user IDs of the multiple users U1 to U4 from the remote control device 6 and performs the login process (step S1).

In order to recommend songs to be performed by karaoke to the multiple logged-in users U1-U4, the acquisition unit 16 transmits the user IDs of the multiple users U1-U4 to the server device 2, and receives and acquires first information that is estimated to be the preferences of the multiple users U1-U4 and second information that is estimated to be the preferences of users other than the multiple users from the server device 2 (step S2). The acquisition unit 16 acquires, for example, singing history information of the multiple users U1-U4 as the first information, and nationwide singing frequency information as the second information.

The acquisition unit 16 may acquire the first information and the second information from the server device 2 immediately after the login of the multiple users U1 to U4, or may acquire from the storage unit 11 the first information and the second information that the karaoke device 1 received from the server device 2 and stored in the storage unit 11. The acquisition unit 16 may also reacquire the first information and the second information from the server device 2 every time a predetermined time has elapsed after login.

In order to determine the ratio between the first number of songs and the second number of songs to be recommended to the multiple logged-in users U1 to U4 at a predetermined timing, the determination unit 19 first acquires performance history information, i.e., performance information for a predetermined number of most recent performances, stored in the storage unit 11 in association with the user IDs of each of the multiple users U1 to U4 for each user. Here, the predetermined timing is a timing suitable for recommending songs to be performed as karaoke to the users U1 to U4, and may be, for example, immediately after login, or a predetermined time has passed without any karaoke performance reservations, or a timing when a user requests a song recommendation by operating the remote control device 6, etc.

For example, if a karaoke performance is reserved by any of users U1 to U4 (step S3: NO), the karaoke device 1 may end the song recommendation operation. On the other hand, if a karaoke performance is not reserved by any of users U1 to U4 and a predetermined time has passed (step S3: YES), the determination unit 19 determines the ratio of the first number of songs to the second number of songs (step S4).

At this time, the determination unit 19 counts the number of first performance information items from the acquired performance information of the predetermined number of times of playing for each of the users U1 to U4 as the first number of times of playing corresponding to the recommendation by the first recommendation unit 17, and counts the number of second performance information items as the second number of times of playing corresponding to the recommendation by the second recommendation unit 18. Furthermore, the determination unit 19 determines the ratio between the first number of songs and the second number of songs to be recommended to the users U1 to U4 based on the first number of times of playing and the second number of times of playing for each of the users U1 to U4.

For example, suppose that the predetermined number of times the performance history information is set to 10 times, and the performance history information of user U1 is, in order from oldest to newest, "second performance information, first performance information, second performance information, second performance information, first performance information, second performance information, second performance information, first performance information, second performance information." In this case, it can be presumed that user U1 often sings karaoke to songs recommended based on nationwide singing frequency information, and occasionally sings karaoke to songs recommended based on user U1's singing history information. In other words, it can be presumed that user U1 is a user who, if anything, likes to try singing new songs at karaoke.

In this case, the determination unit 19 counts the first number of times that user U1 has performed as 3 times, and the second number of times that user U1 has performed as 7 times. Similarly, as an example relating to user U2, the determination unit 19 counts the first number of times that user U2 has performed as 8 times, and the second number of times that user U2 has performed as 2 times. As an example relating to user U3, the determination unit 19 counts the first number of times that user U3 has performed as 4 times, and the second number of times that user U3 has performed as 6 times. As an example relating to user U4, the determination unit 19 counts the first number of times that user U4 has performed as 9 times, and the second number of times that user U4 has performed as 1 time.

Then, the determination unit 19 calculates the average number of first plays of the users U1 to U4, and in the above example, calculates 6 times from (3 + 8 + 4 + 9) / 4. The determination unit 19 also calculates the average number of second plays of the users U1 to U4, and in the above example, calculates 4 times from (7 + 2 + 6 + 1) / 4. The determination unit 19 then determines the ratio between the first number of songs and the second number of songs based on the average number of first plays and the average number of second plays, and in the above example, determines the ratio between the first number of songs and the second number of songs to be 6:4. If the total number of songs recommended to the users U1 to U4 is set to 20 songs, the determination unit 19 sets the first number of songs to 12 songs and the second number of songs to 8 songs based on the ratio of 6:4. Note that the first number of songs and the second number of songs may be rounded off to the nearest whole number.

Next, the first recommendation unit 17 extracts a first number of first songs as recommended songs from the first information estimated to be the preferences of the multiple users U1 to U4 acquired by the acquisition unit 16, for example, the singing history information of the users U1 to U4. At this time, the first recommendation unit 17 calculates the number of songs to be extracted from each of the singing history information of the users U1 to U4 as a breakdown of the first number of songs, i.e., the individual number of songs for each of the multiple users U1 to U4 (step S5).

For example, the first recommendation unit 17 calculates the individual number of songs for each of the multiple users U1 to U4 based on the first number of songs recommended to the users U1 to U4 and the ratio of the first number of times played by the users U1 to U4. In the above example, the first recommendation unit 17 calculates the individual number of songs for user U1 to be 12*3/24=1.5≒2 songs based on the first number of songs (12 songs) and the ratio of the first number of times played (3:8:4:9), since the individual ratio of user U1 is 3/(3+8+4+9). Similarly, the first recommendation unit 17 calculates the individual number of songs for user U2 to be 12*8/24=4 songs, the individual number of songs for user U3 to be 12*4/24=2 songs, and the individual number of songs for user U4 to be 12*9/24=4.5≒4 songs. The individual song counts for users U1 to U4 may be rounded off to the nearest whole number, and if the total of the individual song counts exceeds the first number of songs, the number of individual songs with the largest absolute value will be used to adjust the number, which in the above example is the number of individual songs for user U4.

Then, the first recommendation unit 17 extracts the first songs of the individual number of songs of each of the users U1 to U4 from the singing history information of each of the users U1 to U4 (step S6). In the above example, the first recommendation unit 17 extracts the first songs of the top two songs (1st to 2nd) of the individual number of songs of the user U1 in order of the number of times played from the singing history information of the user U1. Similarly, the first recommendation unit 17 extracts the first songs of the top four songs (1st to 4th) of the individual number of songs of the user U2 in order of the number of times played from the singing history information of the user U2. In addition, the first recommendation unit 17 extracts the first songs of the top two songs (1st to 2nd) of the individual number of songs of the user U3 in order of the number of times played from the singing history information of the user U3. In addition, the first recommendation unit 17 extracts the top four (1st to 4th) first songs by user U4 in terms of individual song count, in order of frequency of performance, from the singing history information of user U4.

Next, the second recommendation unit 18 extracts a second number of second songs as recommended songs from the second information, which is estimated to be the taste of a person other than the user and which is acquired by the acquisition unit 16, for example, nationwide singing frequency information (step S7). In the above example, the second recommendation unit 18 extracts the top eight second songs (1st to 8th) in the second number of songs from the nationwide singing frequency information in order of the number of times they have been played.

The karaoke device 1 recommends the first song recommended by the first recommendation unit 17 and the second song recommended by the second recommendation unit 18 to the users U1 to U4 by displaying the song titles, etc., of the first song recommended by the first recommendation unit 17 and the second song recommended by the second recommendation unit 18 on the display device 3 and the remote control device 6 (step S8).

At this time, the display device 3 or remote control device 6 may display the top 12 first songs in order of most played, followed by the top 8 second songs in order of most played. Alternatively, the display device 3 or remote control device 6 may display the top 8 second songs in order of most played, followed by the top 12 first songs in order of most played. Alternatively, the display device 3 or remote control device 6 may display the first songs and second songs randomly. In addition, the type of display order of the recommended songs may be selectable by users U1 to U4 at their own discretion.

The karaoke device 1 then repeats the song recommendation operation if users U1 to U4 have not logged out (step S9: NO), but ends the song recommendation operation if users U1 to U4 have logged out (step S9: YES).

After that, for example, when user U1 selects (reserves) the first song recommended by the first recommendation unit 17 from the 20 recommended songs displayed on the display device 3 and the remote control device 6, the karaoke device 1 plays the first song as karaoke, as described in the performance operation above. The karaoke device 1 associates the first performance information that identifies the first recommendation means with the user ID as performance performance information of the recommended song of user U1 in the storage unit 11. At this time, the performance performance information of the recommended song of user U1 stored in the storage unit 11 is updated in chronological order to "first performance information, second performance information, second performance information, second performance information, first performance information, second performance information, first performance information, second performance information, first performance information, first performance information".

Therefore, when the determination unit 19 determines the ratio between the first number of songs and the second number of songs to be recommended to the users in the next song recommendation operation, the determination unit 19 counts the first number of times of performance for user U1 as 4, which is an increase of 1 from the previous time, and counts the second number of times of performance as 6, which is a decrease of 1 from the previous time. The determination unit 19 calculates the average value of the first number of times of performance for users U1 to U4 as 6.25 times from (4 + 8 + 4 + 9) / 4, and calculates the average value of the second number of times of performance for users U1 to U4 as 3.75 times from (6 + 2 + 6 + 1) / 4. Therefore, the determination unit 19 determines the ratio between the first number of songs and the second number of songs to be recommended to the users to be 6.25:3.75, and based on the ratio of 6.25:3.75 to the total number of recommended songs of 20 songs, the first number of songs remains unchanged at 12 songs and the second number of songs remains unchanged at 8 songs.

The first recommendation unit 17 also calculates the number of individual songs for user U1 to be 2, from 12*4/25, based on the first number of songs (12) and the ratio of the first number of times played (4:8:4:9). The first recommendation unit 17 extracts the top two first songs in terms of the number of times played from the singing history information of user U1. In this way, the first recommendation unit 17 recommends 12 first songs as the first number of songs, and the second recommendation unit 18 recommends 8 second songs as the second number of songs.

As described above, the karaoke device 1 of the first embodiment of the present invention includes an acquisition unit 16 that acquires first information estimated to be the preferences of a plurality of users and second information estimated to be the preferences of users other than the plurality of users in order to recommend songs to be performed as karaoke to the plurality of users, a first recommendation unit 17 that recommends a predetermined first number of first songs to the plurality of users based on the first information, a second recommendation unit 18 that recommends a predetermined second number of second songs to the plurality of users based on the second information, and a determination unit 19 that acquires the first number of times that a song has been performed in karaoke in the past in response to a recommendation to a user, the first number of times that a song has been performed in karaoke in response to a recommendation to a user, and the second number of times that a song has been performed in karaoke in response to a recommendation to a user, and determines the ratio between the first number of songs and the second number of songs based on the first number of times that a song has been performed and the second number of times that a song has been performed in karaoke in response to a recommendation to a user.

For example, the acquisition unit 16 acquires the user's singing history information as the first information, and acquires nationwide singing frequency information as the second information.

This allows the ratio of recommended songs (first songs) suitable for users who tend to sing karaoke songs that they are good at or classic songs, and recommended songs (second songs) suitable for users who tend to try singing new songs at karaoke regardless of their preferences, to be determined for multiple users based on the performance history information of multiple users, without changing the total number of recommended songs. Therefore, more songs recommended by a recommendation technology suitable for each user can be presented, and songs recommended by other recommendation technologies can also be presented without the recommended songs being biased toward one recommendation technology, making it possible to recommend songs efficiently. Therefore, the karaoke device 1 can efficiently recommend songs using a recommendation technology suitable for a group of users.

The first recommendation unit 17 also calculates the number of individual songs for each of the multiple users based on the ratio of the first number of songs and the first number of times played by the multiple users, and extracts the first songs of the calculated individual number of songs based on the singing history information of each user.

In this way, by using the first number of times of playing by the multiple users, the number of individual songs to be recommended to each user based on the first information can be determined in consideration of the usage history of the multiple users of song recommendations based on the first information (e.g., singing history information). Therefore, songs suitable for the multiple users can be recommended according to the usage history of each of the multiple users of song recommendations.
[Modification]

In addition, as a modified example of the karaoke device 1, when a second song is identical to a first song, the second recommendation unit 18 may recommend another second song that is different from the first second song based on the second information.

For example, if the songs that user U1 likes to sing include a popular song that is also frequently sung nationwide, the same song may be ranked high in both the ranking based on user U1's singing history information and the ranking based on the national singing frequency information. In this case, the first second song is identical to the first song, but the second recommendation unit 18 excludes the first second song from the recommended songs. Note that the first recommendation unit 17 recommends the first song that is identical to the first second song as it is. By excluding the second song that is identical to the first song from the recommended songs, the sum of the first number of songs recommended by the first recommendation unit 17 and the second number of songs recommended by the second recommendation unit 18 may be less than the total number of recommended songs.

Alternatively, the second recommendation unit 18 may, for example, extract other second songs different from the one second song based on the second information and add them as recommended songs to fill the excluded portion, and adjust the number of first songs and the number of second songs so that the total number of recommended songs is the total number of first songs. At this time, it is assumed that, among the 12 songs recommended by the first recommendation unit 17 based on the singing history information of the user U1, the one first song is ranked second in the ranking of the number of times played in the singing history information of the user U1. Also, it is assumed that, among the eight songs recommended by the second recommendation unit 18 based on the nationwide singing frequency information, the one second song is ranked sixth in the ranking of the number of times played in the nationwide singing frequency information. Here, it is assumed that the one first song and the one second song are the same. In this case, the first recommendation unit 17 maintains the one first song as a recommended song. In addition, the second recommendation unit 18 removes one second song from the list of recommended songs, and in place of the removed song, moves up the second song that is ranked 9th in the ranking of the number of times it has been played in the nationwide singing frequency information to become the recommended song.

As a result, in the modified example of the karaoke device 1, when the first recommendation unit 17 and the second recommendation unit 18 recommend the same song in duplicate, the song can be recommended with priority given to the preferences of multiple users. For example, even if a song is recommended based on nationwide singing frequency information, if it is the same as a song recommended based on singing history information of multiple users, it will be deemed to be a song suitable for a user who sings songs that the user is good at or classic songs. In addition, since recommendations that match the preferences of users other than the user are redone, other songs suitable for a user who is trying to sing a new song at karaoke can be recommended, and the recommendation of various types of songs by multiple recommendation means can be maintained.

Similarly, when a first song extracted from the singing history information of one user U1 among multiple users U1 to U4 is identical to another first song extracted from the singing history information of another user U2, the first recommendation unit 17 may simply exclude the other first songs and recommend first songs that are less than the first number of songs.

Alternatively, the first recommendation unit 17 may maintain one first song related to one user U1 while excluding other first songs related to another user U2, and further extract the next most frequently played first song from the singing history information of the other user U2 in place of the other first song that has been excluded, thereby maintaining the number of recommended first songs at the first number.
[Other embodiments]

In the above first embodiment, an example has been described in which the karaoke device 1 extracts and recommends first songs in descending order of frequency of playing from the singing history information of multiple users, which is the first information, by the first recommendation unit 17, but the present invention is not limited to this example. For example, in another embodiment, the first recommendation unit 17 may extract and recommend first songs in descending order of average singing score from the singing history information of multiple users, which is the first information.

In this case, when the karaoke machine 1 transmits the song ID of the song sung by the user and the user ID to the server device 2, it also transmits the singing score for this karaoke singing. When the server device 2 stores the song ID of the song received from the karaoke machine 1 as the user's singing history information (first information) in association with the number of times it has been performed and the user ID, it also stores the singing score received from the karaoke machine 1 in association with the singing history information. It is preferable that the server device 2 averages the singing scores for each song and stores the average score as singing score information. This allows the acquisition unit 16 to acquire singing history information (first information) including singing score information from the server device 2.

In the above first embodiment, an example has been described in which the karaoke device 1 extracts and recommends the second song in order of frequency of playing from the second information, which is the nationwide singing frequency information, by the second recommendation unit 18, but the present invention is not limited to this example. For example, in another embodiment, the second recommendation unit 18 of the karaoke device 1 may extract and recommend the second song in order of frequency of playing next to the song being performed karaoke, from the second information, which is the nationwide singing frequency information.

In this case, when the server device 2 receives the song IDs of the songs sung by each user and creates the singing history information of each user, the server device 2 includes the performance order of the songs sung by each user in the singing history information of each user. When the server device 2 creates nationwide singing frequency information based on the singing history information of each user nationwide, it can identify the song (next song) that has been played after each song (current song) by referring to the performance order of the songs in each singing history information. Therefore, the server device 2 detects one or more next songs for each song and calculates the frequency (number of times) that each song has been played as the next song for each next song. The server device 2 then associates each song with the song ID and performance frequency of the next song and stores them as nationwide singing frequency information (second information).

Furthermore, when the server device 2 receives an inquiry for the second information together with the song ID of a song from the karaoke device 1, in response to this inquiry, it transmits the song ID and performance frequency of the next song corresponding to the one song to the karaoke device 1 as nationwide singing frequency information (second information). As a result, when the karaoke device 1 transmits the song ID of the song being played to the server device 2, the acquisition unit 16 can acquire from the server device 2 the nationwide singing frequency information (second information) including the song ID and performance frequency of the next song corresponding to that song.

In the above first embodiment, an example has been described in which the first recommendation unit 17 calculates the number of individual songs for each of the multiple users based on the ratio of the number of first songs and the number of first performances of the multiple users as the breakdown of the first songs extracted from the singing history information of the multiple users, and extracts the first songs of the calculated individual number of songs based on the singing history information of each user, but the present invention is not limited to this example. For example, in another embodiment, the first recommendation unit 17 may extract songs that are common to the singing history information of the multiple users as the first songs. Specifically, the first recommendation unit 17 may detect common songs from the singing history information of users U1 to U4 acquired by the acquisition unit 16, and extract the top 12 songs from the common songs in order of the total number of performances by users U1 to U4.

Second Embodiment
A karaoke device 1 according to a second embodiment of the present invention will now be described. Fig. 3 is a block diagram showing the configuration of a karaoke system 100 including the karaoke device 1 according to the second embodiment. In the description of the second embodiment, the same components as those in the first embodiment are given the same reference numerals as those in the first embodiment, and the description thereof will be omitted.

In the first embodiment, an example was described in which the karaoke device 1 uses nationwide singing frequency information as the second information estimated to be the taste of a person other than the user, but the karaoke device 1 of the second embodiment uses singing history information of other users with similar tastes (hereinafter referred to as similar preference singing history information) for each of the multiple users as the second information estimated to be the taste of a person other than the multiple users to whom songs should be recommended. That is, in the karaoke device 1 of the second embodiment, the first recommendation unit 17 provides a first recommendation means based on the singing history information of the multiple users, and the second recommendation unit 18 provides a second recommendation means based on the similar preference singing history information of the multiple users.

In the first embodiment, the server device 2 stores singing history information of users nationwide, and therefore, when acquiring second information for multiple users, the server device 2 acquires similar-preference singing history information of the multiple users from singing history information of users other than the multiple users. For example, the server device 2 creates a ranking list for each user in which the singing history information of the multiple users is organized in order of singing frequency based on the singing history information of the multiple users. The server device 2 then identifies a user by the user ID received from the karaoke device 1, compares the ranking list of the user with the ranking list of the other users, and if a predetermined number or more of songs of a predetermined rank or higher match, determines that the other users have similar tastes to the one user, and acquires the singing history information of the other users as similar-preference singing history information of the one user, i.e., the second information.

As in the first embodiment, the acquisition unit 16 acquires singing history information of multiple users as the first information, and particularly in the second embodiment, acquires similar singing preference history information for each of the multiple users as the second information. Note that the acquisition unit 16 may acquire the singing history information and similar singing preference history information of the multiple users by receiving them from the server device 2.

The second recommendation unit 18 recommends a predetermined second number of second songs to a plurality of users as second information based on the similar singing preference history information of the plurality of users. In this case, when one second song is identical to the first song, it is desirable for the second recommendation unit 18 to recommend another second song different from the one second song based on the second information.

[Music recommendation operation of the second embodiment]
Next, the song recommendation operation of the karaoke device 1 of the second embodiment will be described with reference to Fig. 4. Fig. 4 is a flow chart showing the song recommendation operation of the karaoke device 1.

In the song recommendation operation of the second embodiment, the operations (steps S11 to S16) up to the login operation of multiple users U1 to U4, the acquisition unit 16 acquiring the first information and the second information (approximate singing preference information), the determination unit 19 determining the ratio between the first number of songs and the second number of songs, and the first recommendation unit 17 recommending the first number of songs are the same as the operations (steps S1 to S6) of the first embodiment. At this time, the acquisition unit 16 receives and acquires the approximate singing preference information of multiple users U1 to U4 as the second information from the server device 2, for example. As in the song recommendation operation of the first embodiment, the determination unit 19 determines the ratio between the first number of songs and the second number of songs to be 6:4, and when the total number of songs recommended to users U1 to U4 is set to 20, the first number of songs is set to 12 and the second number of songs is set to 8. In addition, the first recommendation unit 17 extracts 12 first songs as recommended songs from the first information (singing history information) that is estimated to be the preferences of multiple users U1 to U4 acquired by the acquisition unit 16.

In particular, in the second embodiment, the second recommendation unit 18 extracts a second number of second songs as recommended songs from the approximate singing preference history information of the multiple users U1 to U4 as second information estimated to be the preferences of a user other than the user acquired by the acquisition unit 16. At this time, the second recommendation unit 18 calculates the number of songs to be extracted from each of the approximate singing preference history information of the users U1 to U4 as a breakdown of the second number of songs, that is, the individual number of songs for each of the multiple users U1 to U4 (step S17).

For example, the second recommendation unit 18 calculates the individual number of songs for each of the multiple users U1 to U4 based on the second number of songs recommended to the users U1 to U4 and the ratio of the second number of times played by the users U1 to U4. As with the song recommendation operation of the first embodiment, if the second number of songs is 8 songs and the ratio of the second number of times played is 7:2:6:1, the second recommendation unit 18 calculates the individual number of songs for user U1 to be 8*7/16=3.5≒3 songs based on the ratio of the second number of songs and the second number of times played, since the individual ratio for user U1 is 7/(7+2+6+1). Similarly, the second recommendation unit 18 calculates the number of individual songs for user U2 as 8*2/16 = 1 song, the number of individual songs for user U3 as 8*6/16 = 3 songs, and the number of individual songs for user U4 as 8*1/16 = 0.5 ≒ 1 song. Note that the numbers of individual songs for users U1 to U4 may be rounded off to the nearest whole number, and if the total number of individual songs exceeds the second number of songs, it is adjusted to the number of individual songs with the largest absolute value, which in the above example is the number of individual songs for user U1.

The second recommendation unit 18 also extracts the second songs of the individual number of songs of each of the users U1 to U4 from the approximate singing preference history information of each of the users U1 to U4 (step S18). In the above example, the second recommendation unit 18 extracts the top three second songs (1st to 3rd) of the individual number of songs of the user U1 in order of the number of times played from the approximate singing preference history information of the user U1. Similarly, the second recommendation unit 18 extracts the top one second song (up to 1st) of the individual number of songs of the user U2 in order of the number of times played from the approximate singing preference history information of the user U2. The second recommendation unit 18 also extracts the top three second songs (1st to 3rd) of the individual number of songs of the user U3 in order of the number of times played from the approximate singing preference history information of the user U3. In addition, the second recommendation unit 18 extracts the second song that is the top (up to 1st place) in terms of the number of times that the song has been played from the similar singing preference history information of user U4.

Similar to the song recommendation operation of the first embodiment, the karaoke device 1 recommends the first song recommended by the first recommendation unit 17 and the second song recommended by the second recommendation unit 18 to the users U1 to U4 by displaying the song titles, etc., of the first song recommended by the first recommendation unit 17 and the second song recommended by the second recommendation unit 18 on the display device 3 and the remote control device 6 (step S19).

The karaoke device 1 then repeats the song recommendation operation if users U1 to U4 have not logged out (step S20: NO), but ends the song recommendation operation if users U1 to U4 have logged out (step S20: YES).

This allows the ratio of recommended songs (first songs) suitable for a user who tends to sing karaoke songs that he or she is good at or classic songs, and recommended songs (second songs) suitable for a user who is willing to sing a new song that suits him or her among new songs that are similar to his or her tastes, to be determined for multiple users based on the performance record information of multiple users without changing the total number of recommended songs. Specifically, by using singing history information of other users whose tastes are similar to that of a single user, songs that are close to the taste of the single user can be recommended from among songs that the single user does not have a singing history. In the second embodiment, more songs recommended by a recommendation technology suitable for each user can be presented, and songs recommended by other recommendation technologies can be presented without being biased toward a single recommendation technology, so that songs can be recommended efficiently. Therefore, the karaoke device 1 can efficiently recommend songs using a recommendation technology suitable for a group of users.

In addition, by using the second number of times the plurality of users have played the music, the number of individual songs to be recommended to each user based on the second information can be determined in consideration of the usage history of the plurality of users of the music recommendation based on the second information (approximate singing preference information). Therefore, it is possible to recommend music suitable for the plurality of users according to the usage history of each of the plurality of users of the music recommendation.
[Other embodiments]

In the above second embodiment, an example was described in which the second recommendation unit 18 calculates the number of individual songs for each of the multiple users based on the ratio of the number of second songs and the number of second performances of the multiple users as the breakdown of the second songs extracted from the approximate singing preference history information of the multiple users, and extracts the second songs of the calculated individual number of songs based on the approximate singing preference history information of each user, but the present invention is not limited to this example. For example, in another embodiment, the second recommendation unit 18 may extract songs that are common to the approximate singing preference history information of the multiple users as the second songs. Specifically, the second recommendation unit 18 may detect common songs from the approximate singing preference history information of users U1 to U4, and extract the top eight songs from the common songs in order of the total number of performances of other users that are the basis of the approximate singing preference history information.

The karaoke device 1 of the first embodiment above provides a first recommendation means based on singing history information of multiple users and a second recommendation means based on nationwide singing frequency information, and the karaoke device 1 of the second embodiment above provides a first recommendation means based on singing history information of multiple users and a second recommendation means based on similar singing preference history information of multiple users, but the present invention is not limited to these examples. For example, in another embodiment, the karaoke device 1 may be configured to provide a first recommendation means based on singing history information of multiple users, a second recommendation means based on nationwide singing frequency information, and a third recommendation means based on similar singing preference history information of multiple users.

In the first and second embodiments described above, an example was described in which various information is stored in the server device 2 and the karaoke device 1 acquires the various information from the server device 2 to perform song recommendations, but the present invention is not limited to this example, and the karaoke device 1 may be configured to store various information in the memory unit 11 and acquire the various information from the memory unit 11 to perform song recommendations.

The present invention may be modified as appropriate within the scope of the claims and the entire specification without violating the spirit or concept of the invention, and karaoke devices incorporating such modifications are also included in the technical concept of the present invention.

REFERENCE SIGNS LIST 1 karaoke device 2 server device 3 display device 6 remote control device 10 control unit 11 storage unit 15 login processing unit 16 acquisition unit 17 first recommendation unit 18 second recommendation unit 19 decision unit

Claims (5)

an acquisition unit that acquires first information estimated to be preferences of a plurality of users and second information estimated to be preferences of users other than the plurality of users in order to recommend songs to be performed by karaoke to the plurality of users;
a first recommendation unit that determines first music pieces to be recommended to the plurality of users based on the first information and recommends a predetermined first number of the first music pieces;
a second recommendation unit that determines second music pieces to be recommended to the plurality of users based on the second information and recommends a predetermined second number of the second music pieces;
a determination unit that acquires a first number of times that a song has been performed in response to a recommendation by the first recommendation unit and a second number of times that a song has been performed in response to a recommendation by the second recommendation unit for a predetermined number of times that a song has been performed in the past in response to a recommendation for a single user, and determines a ratio between the first number of songs and the second number of songs based on the first number of times that a song has been performed and the second number of times that a song has been performed for each of the multiple users. The karaoke device according to claim 1, characterized in that, when a second song is identical to the first song, the second recommendation unit recommends another second song different from the first second song based on the second information. The karaoke device according to claim 1 or 2, characterized in that the acquisition unit acquires singing history information of the plurality of users as the first information, and acquires nationwide singing frequency information as the second information. The karaoke device according to claim 3, characterized in that the first recommendation unit calculates the individual number of songs for each of the multiple users based on the ratio of the first number of songs and the first number of times the multiple users have played the songs, and extracts the first songs of the calculated individual number of songs based on the singing history information for each user. The karaoke device according to claim 1 or 2, characterized in that the acquisition unit acquires singing history information of the plurality of users as the first information, and acquires singing history information of other users who have similar tastes to each of the plurality of users as the second information.

Images