JP7330635B2 - karaoke device - Google Patents

Description

The present invention relates to a karaoke machine.

2. Description of the Related Art A technique is known in which suitable music is emitted as BGM (Back-Ground Music) between karaoke performances (between songs) at a night bar such as a karaoke bar (see, for example, Patent Document 1). The technique described in Patent Literature 1 collects singing histories of karaoke performances from many karaoke machines, creates a popular song list for each time period, selects songs from the popular song list, and performs BGM performance. Considering the difference in the customer base due to the performance scene such as the time zone, BGM is selected according to the preference of the customer base for each performance scene, thereby effectively encouraging the user who listens to the BGM to reserve the music. It is

JP 2004-212564 A

By the way, the group users of the karaoke box are of course acquainted with each other, and in many cases, the group users enter and leave the room together. However, users of night bars such as karaoke bars often do not know each other, and often enter and leave the bar separately. For this reason, the users may not know each other's tastes, and may have trouble finding the first reserved song for the karaoke performance. When urging a user to reserve a song using the technology described in Patent Document 1, even if it is suitable as BGM, it is a song that the user cannot sing karaoke, or a song that other users do not like. There is a possibility that it will be.

SUMMARY OF THE INVENTION An object of the present invention is to provide a karaoke apparatus capable of effectively urging the user to make a reservation for the music by emitting a music piece suitable for the taste of the user who is there as BGM. be.

The main invention for achieving the above object is a karaoke device that is installed in a store, performs karaoke according to the reservation of music, and can play BGM (Back-Ground Music) when there is no reservation for the music. an acquisition unit that acquires a singing history corresponding to the user identification information of the user photographed at the time of entering the store by the photographing means, and outputs the singing history in association with the user identification information; A storage unit that stores the output user identification information and singing history in association with each other, and deletes the singing history corresponding to the user identification information of the user photographed by the photographing means when leaving the store; A karaoke machine, comprising: a generation unit for generating a music list to be played as BGM based on the singing history stored in the storage unit when leaving the store and leaving the store.

According to the present invention, the singing history of the user is stored in the storage unit from the user identification information of the user who entered the store, and the singing history of the user is stored in the storage unit from the user identification information of the user who has left the store. removed from Since only the singing histories of users who are in the store are stored in the storage unit, a music list of BGM performances corresponding to the members of the users is generated from the singing histories. Therefore, there is a high possibility that the user will be able to sing karaoke, and the user can be effectively urged to make a reservation for the music by sounding the music that suits the taste of the user who is there as BGM. .

1 is a configuration diagram of a karaoke device according to a first embodiment; FIG. It is a figure which shows an example of the user's presence situation of 1st Embodiment. It is a figure which shows an example of the user's singing log|history of 1st Embodiment. It is a figure which shows an example of the number of times of singing for every music of the user of 1st Embodiment. It is a figure which shows an example of the music list of 1st Embodiment. It is a figure which shows the modification of the music list of 1st Embodiment. 4 is a flow chart showing BGM playing operation of the first embodiment. It is a block diagram of the karaoke apparatus of 2nd Embodiment. FIG. 11 is a diagram showing an example of a music list according to the second embodiment; FIG.

<First Embodiment>
A karaoke apparatus 20 according to the first embodiment will be described with reference to FIG. FIG. 1 is a configuration diagram of a karaoke device 20 according to the first embodiment.

As shown in FIG. 1, a karaoke device 20 of the first embodiment is installed in a night bar such as a karaoke bar, and is communicably connected to a server device 10 installed in a data center or the like via a network. there is The karaoke device 20 is configured to perform karaoke according to the reservation of music, and to perform BGM when no music is reserved. The server device 10 manages the singing history of the user, provides the singing history of the user who entered the store to the karaoke device 20, and uses the musical piece according to the preference of the user who is there as BGM for karaoke. The music is selected by the device 20 .

The karaoke machine 20 includes a karaoke main body 21 , a monitor 22 , a speaker 23 , a microphone 24 and a remote control device 25 . The monitor 22 displays lyrics telops along with a background image in accordance with the karaoke performance of the music. The speaker 23 emits the user's singing voice together with the musical performance sound. The microphone 24 converts the user's singing voice into a singing voice signal and outputs the singing voice signal to the karaoke main body 21 . The remote control device 25 is connected to the karaoke main body 21 via wireless communication so as to be able to transmit and receive, and accepts various operations by the user such as music reservation for the karaoke main body 21 .

When music is reserved by the remote control device 25 and karaoke performance is started by the karaoke main body 21, the lyric telop and the background image are displayed on the monitor 22 based on the lyric telop data and the background image data. Also, the accompaniment sound signal of the karaoke performance and the singing voice signal input from the microphone 24 to the karaoke main body 21 are mixed at an appropriate ratio by the mixer, and this mixed signal is amplified by the amplifier and emitted from the speaker 23 . Thus, when the user sings along with the karaoke performance, the singing voice is emitted from the speaker 23 together with the performance sound.

Also, the karaoke machine 20 is provided with a photographing means 26 for photographing the user's face. A photographing means 26 photographs a user who has entered the store, a user who has left the store, and a user who is singing, and outputs face image data to the karaoke main body 21.例文帳に追加The state of being in the store is managed by the face image data when the user enters and leaves the store, and the user's singing record is managed by the face image data when the user sings. Note that the photographing means 26 may be composed of a plurality of cameras installed at locations where the user's face can be photographed when entering the store, when leaving the store, and when singing. In particular, the user's face when entering and leaving the store may be photographed by an omnidirectional camera or a semi-spherical camera installed near the entrance.

When the karaoke main body 21 recognizes the presence of the store based on the face image data input from the photographing means 26, it acquires the singing history of the users who are present in the store from the server device 10 and generates a music list for BGM performance. do. Until the music is reserved by the remote control device 25, the karaoke main body 21 sequentially plays the BGM of the music according to the music list. Even in a place where users who do not know each other gather, such as a night bar such as a karaoke bar, a plurality of users who are present at the place emit music according to their tastes as BGM, and listen to the BGM. The user is prompted to reserve the music.

The karaoke main body 21 is provided with a reservation section 31 , a karaoke performance section 32 , an image processing section 33 , an acquisition section 34 , a storage section 35 , a generation section 36 and a BGM performance section 37 . The reservation unit 31 registers the music ID received from the remote control device 25 in the reservation queue. In the reservation queue, music IDs of reserved music are arranged in order of registration. The karaoke performance unit 32 sequentially reads out the music IDs from the reservation queue and reproduces the music data corresponding to the music IDs. During the karaoke performance, lyrics telops and background images are displayed on the monitor 22 by the karaoke main body 21 in synchronization with the reproduction of the music data.

The image processing unit 33 performs various image processing on the face image data input from the photographing unit 26, and outputs a user ID as user identification information. In this case, a face area extraction process for extracting a face area from face image data, a feature amount extraction process for extracting a feature amount from the face area, a user ID specifying process for specifying a user ID from the feature amount, and the like are performed. In addition to the above processing, size adjustment, contrast adjustment processing, and the like may be performed. Facial area extraction processing includes a method using edge detection of face image data, a method using pixel values (color values) of face image data, a method using pattern matching, a method using neural networks, and a combination of these methods. A known method, such as the method described above, is employed.

Known methods such as SIFT (Scale-Invariant Feature Transform) and SURF (Speed-Upped Robust Feature) are adopted as the feature amount extraction processing. As the feature amount of the face, for example, the points that show contour features of the face such as the inner corners of the eyes, the outer corners of the eyes, the wings of the nose, the corners of the mouth, the tip of the chin, and the like, which show large changes in shading, are extracted. In addition, the karaoke machine 20 is provided with a store-specific customer management database in which user's reference feature amount and user ID are registered in advance. The image processing unit 33 compares the feature amount extracted from the face image data with the reference feature amount in the customer management database, and specifies the user ID associated with the reference feature amount similar to this feature amount. The similarity of face information is determined using known methods using matching and neural networks.

The user ID specified from the face image data at the time of entering the store is output from the image processing unit 33 to the acquisition unit 34, and the user ID specified from the face image data at the time of leaving the store is output from the image processing unit 33 to the storage unit 35. output to The user ID specified from the face image data at the time of singing is transmitted from the image processing unit 33 to the server device 10 together with the date of singing and the music ID. The server device 10 manages the song history for each user ID, and the song history of the server device 10 is updated by the song history transmitted from the image processing unit 33 . The facial image data at the time of entering the store, leaving the store, and singing is determined by, for example, the installation position of the camera that captured the facial image data.

The acquisition unit 34 acquires from the server device 10 the singing history corresponding to the user ID of the user (entering the store) photographed at the time of entering the store. In this case, a request signal including the user ID is transmitted from the acquisition unit 34 to the server device 10 . In the server device 10, the user ID stored in the server and the user ID included in the request signal are collated, and the singing history associated with the same user ID as the request signal is extracted and acquired from the server device 10. A response signal including the singing history is transmitted to the section 34 . Acquiring the singing history from the response signal, the acquiring unit 34 associates the singing history with the user ID and outputs it to the storage unit 35 .

The storage unit 35 stores the user ID (the user ID of the person who entered the store) output from the acquisition unit 34 in association with the singing history. In addition, the storage unit 35 deletes the singing history corresponding to the user ID of the user (person leaving the store) photographed when leaving the store. In this case, the user ID of the person entering the store stored in the storage unit 35 and the user ID of the person leaving the store output from the image processing unit 33 are collated, and are associated with the same user ID as the person leaving the store. Singing history is deleted. In this way, only the singing history of each user who is in the store is left in the storage unit 35, and the karaoke device 20 manages the user's presence in the store.

The generation unit 36 generates a music list to be played as BGM based on the singing history stored in the storage unit 35 when the user enters and leaves the store. In this case, scores are given to songs extracted from the user's singing history, and a song list is generated in the order of BGM performance based on the scores. In the song list, song IDs of songs are arranged in order of BGM performance. In this embodiment, a score is given to each song based on the number of times of singing (the number of times of karaoke performance), and BGM is performed in order from the number of times of singing. For songs with the same number of times of singing, the song IDs are arranged in the song list in the order of extraction from the singing history.

The BGM performance unit 37 sequentially reads out the music IDs from the music list and reproduces the music data corresponding to the music IDs in the same manner as karaoke performance. In this case, the music data is played by a performance processing method for BGM performance, such as making the volume lower than that of the karaoke performance. In this way, a music list is generated based on the singing histories of users who are in the store, and BGM is performed according to the music list.

The processing of each part of the karaoke device 20 may be realized by software using a processor, or may be realized by a logic circuit (hardware) formed in an integrated circuit or the like. When a processor is used, various processes are performed by the processor reading and executing programs stored in the memory. For example, a CPU (Central Processing Unit) is used as the processor. In addition, the memory is composed of one or a plurality of storage media such as ROM (Read Only Memory), RAM (Random Access Memory), etc., depending on the application.

Next, the processing operation of the karaoke device 20 will be described with a specific example. FIG. 2 is a diagram showing an example of a store presence status of users according to the first embodiment. FIG. 3 is a diagram showing an example of a user's singing history according to the first embodiment. FIG. 4 is a diagram showing an example of the number of times a user sings each piece of music according to the first embodiment. FIG. 5 is a diagram showing an example of a music list according to the first embodiment. FIG. 6 is a diagram showing a modification of the music list of the first embodiment. 2-6, description will be made using the reference numerals in FIG. 1 as appropriate.

As shown in FIG. 2, when Karaoke Snack S opens at 17:00 on December 20, 2019, user U1 enters Karaoke Snack S at 17:00. The state of the user U1 entering the store is photographed by the photographing means 26, and the user ID1 corresponding to the face image data of the user U1 is output to the acquisition section 34 by the image processing section 33. User ID 1 is sent to In this way, it can be considered that the face image data of user U1 is actually user ID1. The same applies to the face image data of user U2 and user ID2, the face image data of user U3 and user ID3, and the face image data of user U4 and user ID4.

As shown in FIG. 3, the user ID 1 and the singing history H1 are pre-registered in the server device 10 in association with each other. The singing history H1 includes at least the song IDs and singing dates of songs sung by the user U1. Similarly, in the server device 10, user ID2 and singing history H2, user ID3 and singing history H3, and user ID4 and singing history H4 are registered in advance in a state of being associated with each other. When the user ID 1 is transmitted from the acquiring unit 34 to the server device 10 , the singing history H 1 associated with the user ID 1 is returned from the server device 10 to the acquiring unit 34 .

As shown in FIGS. 4 and 5A, the music list L1 is generated by the generation unit 36 based on the singing history H1 in the storage unit 35 when the user U1 enters the store. Specifically, from the singing history H1, the number of times of singing for each song that the user U1 has sung during a predetermined period (in the present embodiment, the last three months) is extracted (see the line U1 in FIG. 4). ). The number of times user U1 sang each song is as follows: song X01 is 6 times, song X03 is 8 times, song X04 is 2 times, song X05 is 4 times, song X06 is 5 times, song X07 is 4 times, and song X09 is 4 times. 3 times, music X11 3 times, music X13 5 times, music X15 3 times, and music X16 2 times.

A score is calculated based on a predetermined condition (the number of times of singing in this embodiment) for the songs X01, X03, X04, X05, X06, X07, X09, X11, X13, X15, and X16 extracted from the singing history H1 by the generation unit 36. A music list L1 is generated in the performance order of the BGM performance based on the score. The order of performance of the music list L1 is music X03, X01, X06, X13, X05, X07, X09, X11, X15, X04, X16. When songs X06 and X13 and songs X05 and X07 are sung the same number of times, the performance order is set in the order of extraction.

Until the music is reserved by the user U1, the BGM performance of the music is performed by the BGM playing section 37 according to the music list L1. When music is reserved by the user U1, a karaoke performance is performed by the karaoke performance section 32 according to the operation of the user U1. For example, when music A is reserved by user U1 during BGM performance of music X01, BGM performance of music X01 is stopped while karaoke performance of music A is being performed. Also, if there is no reservation for another song after the karaoke performance of the song A, the BGM performance of the song X06 next to the song X01 is performed according to the song list L1.

As shown in FIG. 2, when the user U2 enters the karaoke snack bar S at 17:30, the photographing means 26 captures the state of the user U2 entering the store, and the image processing section 33 captures the face image of the user U2. A user ID 2 corresponding to the data is output to the acquisition unit 34 . The user ID2 is transmitted from the acquiring unit 34 to the server device 10, and the singing history H2 (see FIG. 3) associated with the user ID2 is returned from the server device 10 to the acquiring unit 34. FIG. The user ID2 and the singing history H2 are output from the acquisition unit 34 to the storage unit 35 in a state of being associated with each other, and the storage unit 35 stores the singing histories H1 and H2 associated with the user ID1 and ID2.

As shown in FIGS. 4 and 5B, the music list L2 is generated by the generating unit 36 based on the singing histories H1 and H2 in the storage unit 35 when the user U2 enters the store. Specifically, the total number of singing times for each piece of music that users U1 and U2 have sung in a predetermined period is extracted from singing histories H1 and H2 (see lines U1 and U2 in FIG. 4). At this time, the total number of times of singing is not extracted for the songs X03, X05, X09, and X15 that the user U2 has never sung even though the user U1 has sung them for a predetermined period of time. Only the number of singing times of songs that users U1 and U2 have experience singing is extracted from singing histories H1 and H2.

The total number of singing times for each song by the users U1 and U2 is 8 times for the song X01 (6 times for the user U1, 2 times for the user U2), and 5 times for the song X04 (2 times for the user U1, 2 times for the user U2). U2 3 times), music X06 11 times (user U1 5 times, user U2 6 times), music X07 11 times (user U1 4 times, user U2 7 times), music X11 6 times (user U1 3 times, user U2 3 times), song X13 12 times (user U1 5 times, user U2 7 times), song X16 4 times (user U1 2 times, user U2 2 times).

A generating unit 36 assigns scores to songs X01, X04, X06, X07, X11, X13, and X16 extracted from singing histories H1 and H2 based on the number of times of singing, and songs are played in the order of BGM performance based on the scores. A list L2 is generated. The performance order of the song list L2 is the order of songs X13, X06, X07, X01, X11, X04, and X16. In this way, when the user U2 enters the store, the music list L2 is generated in consideration of the singing histories H1 and H2 of the users U1 and U2, and the BGM performance of the music is performed according to the music list L2 until the music is reserved. done.

If there is a song for which BGM performance was performed in the previous song list, it is preferable that the BGM performance order of the song is lowered when the current song list is generated. For example, when the BGM performance of songs X03, X01, and X06 has already been performed according to the song list L1, the order of performance of the song list L2 is songs X13, X07, X11, X04, X16, X01, and X06. X03 is not originally included in the music list L2). In other words, it is desirable that the generating unit 36 perform a correction process to reduce the score of the music for which the BGM performance was performed in the previous music list when generating the current music list.

As shown in FIG. 2, when the user U3 enters the karaoke snack bar S at 18:30, the state of the user U3 entering the store is photographed by the photographing means 26, and the face image of the user U3 is photographed by the image processing section 33. A user ID 3 corresponding to the data is output to the acquisition unit 34 . User ID3 is transmitted from the acquiring unit 34 to the server device 10, and the singing history H3 (see FIG. 3) associated with the user ID3 is sent back from the server device 10 to the acquiring unit 34. FIG. The user ID3 and the singing history H3 are output from the acquisition unit 34 to the storage unit 35 in a state of being associated with each other, and the storage unit 35 stores the singing histories H1, H2, and H3 associated with the user ID1, ID2, and ID3. remembered.

As shown in FIGS. 4 and 5(C), the generating unit 36 generates a music list L3 based on the singing histories H1, H2, H3 in the storage unit 35 when the user U3 enters the store. Specifically, from the singing histories H1, H2, and H3, the total number of singing times for each piece of music that the users U1, U2, and U3 have sung in a predetermined period is extracted (rows of U1, U2, and U3 in FIG. 4). ). At this time, even if users U1 and U2 have sung within a predetermined period of time, the total number of singing times is not extracted for songs X07 and X13 that user U3 has never sung. Only the number of times the users U1, U2, and U3 have sung songs that they have sung are extracted from the singing histories H1, H2, and H3.

The total number of singing times for each song by the users U1, U2, and U3 is 11 times for the song X01 (6 times for the user U1, 2 times for the user U2, and 3 times for the user U3), and 12 times for the song X04 ( user U1 2 times, user U2 3 times, user U3 7 times), song X06 13 times (user U1 5 times, user U2 6 times, user U3 2 times), Song X11 played 11 times (user U1 played 3 times, user U2 played 3 times, user U3 played 5 times), and song X16 played 8 times (user U1 played 2 times, user U2 played 2 times, user U2 played 5 times). U3 is 4 times).

A generating unit 36 assigns scores to songs X01, X04, X06, X11, and X16 extracted from singing histories H1, H2, and H3 based on the number of times of singing, and creates a song list L3 in the order of BGM performance based on the scores. is generated. The performance order of the song list L3 is the order of songs X06, X04, X01, X11, and X16. In this way, when the user U3 enters the store, the song list L3 is generated in consideration of the singing histories H1, H2, and H3 of the users U1, U2, and U3. BGM performance is performed.

As shown in FIG. 2, when the user U4 enters the Karaoke Snack S at 19:00, the image of the user U4 entering the store is photographed by the photographing means 26, and the face image of the user U4 is captured by the image processing section 33. A user ID 4 corresponding to the data is output to the acquisition unit 34 . The user ID4 is transmitted from the acquiring unit 34 to the server device 10, and the singing history H4 (see FIG. 3) associated with the user ID4 is returned from the server device 10 to the acquiring unit 34. FIG. The user ID 4 and the singing history H4 are output from the acquisition unit 34 to the storage unit 35 in a state of being associated with each other, and the storage unit 35 stores the singing histories H1, H2, H2, H3 and H4 are stored.

As shown in FIGS. 4 and 5(D), the generating unit 36 generates a music list L4 based on the singing histories H1, H2, H3, and H4 in the storage unit 35 when the user U4 enters the store. Specifically, the total number of songs sung by users U1, U2, U3, and U4 is extracted from the singing histories H1, H2, H3, and H4 (see FIG. 4). At this time, even if users U1, U2, and U3 have sung within a predetermined period of time, the total number of times of singing is not extracted for song X04 that user U4 has never sung. Only the number of times the users U1, U2, U3, and U4 have sung songs that they have sung are extracted from the singing histories H1, H2, H3, and H4.

The total number of singing times for each song by users U1, U2, U3, and U4 is 16 times for song X01 (6 times for user U1, 2 times for user U2, 3 times for user U3, and 5 times for user U4). times), music X06 17 times (user U1 5 times, user U2 6 times, user U3 2 times, user U4 4 times), music X11 18 times (user U1 3 times , user U2 3 times, user U3 5 times, user U4 7 times), song X16 15 times (user U1 2 times, user U2 2 times, user U3 4 times, 7 times for user U4).

A generating unit 36 gives scores to songs X01, X06, X11, and X16 extracted from singing histories H1, H2, H3, and H4 based on the number of times of singing, and creates a song list L4 in the order of BGM performance based on the scores. is generated. The performance order of the song list L4 is the order of songs X11, X06, X01, and X16. In this way, when the user U4 enters the store, the song list L4 is generated in consideration of the singing histories H1, H2, H3, and H4 of the users U1, U2, U3, and U4. BGM performance of music is performed according to the list L4.

As shown in FIG. 2, when the user U1 leaves the Karaoke Snack S at 19:30, the photographing means 26 captures an image of the user U1 leaving the store. A user ID 1 corresponding to the data is output to the storage unit 35 . Singing history H1 associated with user ID1 is deleted by storage unit 35, and singing histories H2, H3 and H4 associated with user ID2, ID3 and ID4 are stored in storage unit 35. Thus, after the user U1 leaves the karaoke bar, the karaoke device 20 manages the singing histories H2, H3, and H4 of the users U2, U3, and U4 who are present at the karaoke snack bar.

As shown in FIGS. 4 and 5(E), the generating unit 36 generates a music list L5 based on the singing histories H2, H3, H4 in the storage unit 35 when the user U1 leaves the store. Specifically, the total number of songs sung by the users U2, U3, and U4 in a predetermined period of time is extracted from the singing histories H2, H3, and H4 (rows of U2, U3, and U4 in FIG. 4). ). At this time, the total number of singing times is also extracted for songs X08 and X14 that have never been sung by user U1 but have been sung by users U2, U3, and U4 in a predetermined period of time. Only the number of times the users U2, U3, and U4 have sung songs that they have sung are extracted from the singing histories H2, H3, and H4.

The total number of singing times for each song by the users U2, U3, and U4 is 10 times for the song X01 (2 times for the user U2, 3 times for the user U3, and 5 times for the user U4), and 12 times for the song X06 ( user U2 6 times, user U3 2 times, user U4 4 times), song X08 20 times (user U2 3 times, user U3 8 times, user U4 9 times), Song X11 played 15 times (user U2 played 3 times, user U3 played 5 times, user U4 played 7 times), song X14 played 8 times (user U2 played 1 time, user U3 played 6 times, user 1 time for U4), and 13 times for music X16 (2 times for user U2, 4 times for user U3, and 7 times for user U4).

A generating unit 36 gives scores to songs X01, X06, X08, X11, X14, and X16 extracted from singing histories H2, H3, and H4 based on the number of times of singing, and songs are played in the order of BGM performance based on the scores. A list L5 is generated. The performance order of the song list L5 is the order of songs X08, X11, X16, X06, X01 and X14. In this way, when the user U1 leaves the store, the music list L5 is generated in consideration of the singing histories H2, H3, and H4 of the users U2, U3, and U4. BGM performance is performed.

As shown in FIG. 2, when the user U4 leaves the Karaoke Snack S at 20:30, the photographing means 26 takes a picture of the user U4 leaving the shop, and the image processing section 33 takes a face image of the user U4. A user ID 4 corresponding to the data is output to the storage unit 35 . The storage unit 35 deletes the singing history H4 associated with the user ID4, and the storage unit 35 stores the singing histories H2 and H3 associated with the user ID2 and ID3. Thus, after the users U1 and U4 leave the karaoke bar, only the singing histories H2 and H3 of the users U2 and U3 who are present at the karaoke bar S are managed by the karaoke device 20. FIG.

As shown in FIGS. 4 and 5(F), the generating unit 36 generates a music list L6 based on the singing histories H2 and H3 in the storage unit 35 when the user U4 leaves the store. Specifically, the total number of singing times for each piece of music that users U2 and U3 have sung in a predetermined period is extracted from singing histories H2 and H3 (see lines U2 and U3 in FIG. 4). At this time, the total number of singing times is also extracted for songs X04 and X10 that have never been sung by user U4 but have been sung by users U2 and U3 in a predetermined period of time. Only the number of singing times of songs that users U2 and U3 have experience singing is extracted from singing histories H2 and H3.

The total number of singing times for each song by users U2 and U3 is 5 times for song X01 (2 times for user U2, 3 times for user U3) and 10 times for song X04 (3 times for user U2, 3 times for user U3). U3 7 times), music X06 8 times (user U2 6 times, user U3 2 times), music X08 11 times (user U2 3 times, user U3 8 times), music X10 6 times (user U2 4 times, user U3 2 times), song X11 8 times (user U2 3 times, user U3 5 times), song X14 7 times (user U2 1 time, user U3 6 times), and song X16 6 times (user U2 2 times, user U3 4 times).

Scores are given to the songs X01, X04, X06, X08, X10, X11, X14, and X16 extracted from the singing histories H2 and H3 by the generator 36 based on the number of times of singing, and the order of BGM performance based on the scores. to generate a music list L6. The performance order of the song list L6 is the order of songs X08, X04, X06, X11, X14, X10, X16, and X01. In this way, when the user U4 leaves the store, the music list L6 is generated in consideration of the singing histories H2 and H3 of the users U2 and U3, and until the music is reserved, the music is played according to the music list L6. done.

As shown in FIG. 2, when the user U2 leaves the Karaoke Snack S at 21:30, the photographing means 26 captures an image of the user U2 leaving the store, and the image processing section 33 captures the face image of the user U2. A user ID 2 corresponding to the data is output to the storage unit 35 . The storage unit 35 deletes the singing history H2 associated with the user ID2, and the storage unit 35 stores the singing history H3 associated with the user ID3. Thus, after the users U1, U2, and U4 leave the karaoke bar, only the singing history H3 of the user U3 who is in the karaoke bar S is managed by the karaoke device 20. FIG.

As shown in FIGS. 4 and 5(G), the music list L7 is generated by the generation unit 36 based on the singing history H3 in the storage unit 35 when the user U2 leaves the store. Specifically, the number of times of singing for each piece of music that the user U3 has sung in a predetermined period is extracted from the singing history H3 (see the row of U3 in FIG. 4). The total number of singing times for each song by user U3 is: song X01 three times, song X02 four times, song X04 seven times, song X06 two times, song X08 eight times, song X10 two times, and song X11. is 5 times, song X12 is 2 times, song X14 is 6 times, and song X16 is 4 times.

A score is given to the music pieces X01, X02, X04, X06, X08, X10, X11, X12, X14, and X16 extracted from the singing history H3 by the generation unit 36 based on the number of times of singing, and BGM performance is performed based on the score. A music list L7 is generated in order of performance. The performance order of the song list L7 is the order of songs X08, X04, X14, X11, X02, X16, X01, X06, X10, and X12. In this way, when the user U2 leaves the store, the song list L7 is generated in consideration of the singing history H3 of the user U3, and the BGM performance of the song is performed according to the song list L7 until the song is reserved.

As shown in FIG. 2, when the user U3 leaves the Karaoke Snack S at 22:00, the photographing means 26 captures an image of the user U3 leaving the store, and the image processing section 33 captures the face image of the user U3. A user ID 3 corresponding to the data is output to the storage unit 35 . The storage unit 35 deletes the singing history H3 associated with the user ID3, and the storage unit 35 does not store the singing history of any user. Therefore, the karaoke device 20 recognizes that there is no user in the karaoke snack bar S, and the BGM performance of the songs according to the song list L7 is canceled and the song list L7 is deleted.

Note that the generation unit 36 may not include a karaoke-played song in the song list until all the users who were present during the karaoke performance of the song have left the store. For example, at 18:00 (see FIG. 2) while the users U1 and U2 are in the store, if either of the users U1 and U2 performs a karaoke performance of the music piece X06, the reservation of the music piece X06 that has already been performed karaoke is performed. is not recommended while the users U1 and U2 are in the store. Therefore, the generation unit 36 generates a music list without including the music X06 so that the BGM performance of the music X06 is not performed until the users U1 and U2 leave the store.

For example, as shown in the modified example of the music list of FIGS. 6(C) to 6(G), when user U3 enters the store (18:30), music X04, X01, X11, and X16 are played in order of performance. A music list L3 is generated. When the user U4 enters the store (19:00), a music list L4 is generated in the performance order of the music pieces X11, X01, and X16. When the user U1 leaves the store (19:30), a music list L5 is generated in the performance order of the music pieces X08, X11, X16, X01, and X14. When the user U4 leaves the store (20:30), a music list L6 is generated in the performance order of the music pieces X08, X04, X11, X14, X10, X16, and X01.

Furthermore, when the user U2 leaves the store (21:30), a music list L7 is generated in the performance order of the music pieces X08, X04, X14, X11, X02, X16, X01, X06, X10, and X12. Since users U1 and U2 have left the store, the generating unit 36 generates a music list including music X06. In this way, the music list L3, L4, L5, and L6 in which one of the users U1 and U2 is present does not include the music piece X06 that has been performed karaoke, and the user U1 and U2 leave the store. The music list L7 includes the music X06, and a more appropriate music is emitted as BGM.

Next, the processing operation of the karaoke device 20 will be described. FIG. 7 is a flow chart showing the BGM playing operation of the first embodiment. Note that the flowchart shown in FIG. 7 shows an example, and the processing operation of the karaoke device 20 is not limited to this flowchart. Further, in FIG. 7, the reference numerals in FIG. 1 are appropriately used for description.

As shown in FIG. 7, when the image of the user entering the store is photographed by the photographing means 26 (Yes in step S01), the image processing unit 33 obtains the user ID x of the person entering the store according to the face image data at the time of entering the store. is output (step S02). If the user's entry into the store is not captured (No in step S01), the process proceeds to step S07. Next, the user IDx is transmitted from the karaoke device 20 to the server device 10 (step S03), the singing history Hx corresponding to the user IDx is returned from the server device 10 to the karaoke device 20, and the acquiring unit 34 Hx is acquired (step S04). Next, the storage unit 35 associates and stores the user ID x of the person entering the store and the singing history Hx (step S05), and the generating unit 36 generates a music list based on the singing history H (step S06). .

Next, when the image of the user leaving the store is captured by the photographing means 26 (Yes in step S07), the image processing unit 33 outputs the user IDy of the person leaving the store according to the face image data at the time of leaving the store. (Step S08). If the image of the user leaving the store is not captured (No in step S07), the process proceeds to step S10. Next, in the storage unit 35, the singing history Hy associated with the user IDy of the person who left the store is deleted (step S09). Next, a music list is generated by the generator 36 based on the singing history H (step S10). Next, when karaoke is not being played or BGM is being played (Yes in step S11) and there is no song reservation (Yes in step S12), the BGM playing unit 37 plays the song as BGM according to the song list ( step S13). Then, the processing from step S01 to step S13 is repeated until the karaoke machine 20 stops operating (step S14).

As described above, according to the first embodiment, the singing history of the user is stored in the storage unit 35 from the user ID of the user who entered the store, and the singing history of the user is stored from the user ID of the user who left the store. is deleted from the storage unit 35. Since only the singing histories of users who are in the store are stored in the storage unit 35, a music list of BGM performances corresponding to the members of the users is generated from the singing histories. Therefore, there is a high possibility that the user will be able to sing karaoke, and the user can be effectively urged to make a reservation for the music by sounding the music that suits the taste of the user who is there as BGM. .

<Second embodiment>
A karaoke device 40 of the second embodiment will be described. FIG. 8 is a configuration diagram of the karaoke device 40 of the second embodiment. FIG. 9 is a diagram showing an example of a music list according to the second embodiment. The karaoke machine 40 of the second embodiment differs from the karaoke machine 20 of the first embodiment in that the song list is generated in consideration of the user's singing record. Therefore, for the second embodiment, the description of the configuration similar to that of the first embodiment will be omitted.

As shown in FIG. 8, the karaoke machine 40 of the second embodiment is configured in substantially the same manner as the karaoke machine 20 (see FIG. 1) of the first embodiment, performs karaoke according to the reservation of the music, It is configured to perform BGM performance when no music is reserved. The karaoke machine 40 includes a karaoke main body 41 , a monitor 42 , a speaker 43 , a microphone 44 , a remote control device 45 and a photographing means 46 . The karaoke main body 41 is provided with a reservation unit 51, a karaoke performance unit 52, an image processing unit 53, an acquisition unit 54, a storage unit 55, a counting unit 58, a generation unit 56, and a BGM performance unit 57. It is

Aggregating unit 58 aggregates the singing record for each user based on the user ID of the user photographed during singing by photographing means 46 . In this case, the tallying unit 58 is provided with a timing means for timing the singing time. The user ID of the singer is output from the image processing unit 53 to the tallying unit 58, and the total singing time is timed as the singing performance for each user ID (user) by the tallying unit 58. It should be noted that, instead of measuring the singing time by the timing means, the music data may include performance time information. The total singing time is counted by obtaining the performance time information from the music data by the counting unit 58 .

The generating unit 56 generates a music list to be played as BGM based on the singing history stored in the storage unit 55 when the user enters and leaves the store. In this case, when a score is assigned to a song extracted from the user's singing history, the score is corrected according to the user's singing record, and the song is played in the BGM performance order based on the corrected score. A list is generated. In this embodiment, the score (the number of times of singing) of a user with a long total singing time is corrected with a small weighting factor, and the score of a user with a short total singing time is corrected with a large weighting factor.

For example, as shown in FIG. 9A, when the user U3 enters the karaoke snack S at 18:30, the counting unit 58 determines that the total singing time of the user U1 is 30 minutes, the total singing time of the user U2 is 30 minutes, and the total singing time of the user U2 is 30 minutes. The singing record is totaled assuming that the time is 20 minutes and the total singing time of the user U3 is 0 minutes. The weighting factor for the user with the shortest total singing time is set to 2.0, the weighting factor for the user with the longest total singing time is set to 0.5, and the weighting factor for the other users is set to 1.0. Therefore, the weighting factor for the number of singing times of user U1 is set to 0.5, the weighting factor for the number of singing times for user U2 is set to 1.0, and the weighting factor for the number of singing times for user U3 is set to 2.0.

As shown in FIG. 9B, when the user U3 enters the store, the generation unit 56 generates music pieces X01, X04, X06, X11, and X16 that the users U1, U2, and U3 have sung in a predetermined period. The number of singing times is extracted. When the songs extracted from the singing histories H1, H2, and H3 are given scores based on the number of times of singing, the number of times of singing is corrected for each song by a weighting coefficient. The number of singing times of user U1 with the longest total singing time is multiplied by a weighting factor of 0.5, the number of singing times of user U2 with the second total singing time is multiplied by a weighting factor of 1.0, and the total singing time is The number of singing times of the shortest user U3 is multiplied by a weighting factor of 2.0.

When the score for each song is corrected by the weighting factor by the generating unit 56, a music list L8 is generated in the performance order of the BGM performance based on the corrected score. The total score for each song of users U1, U2, and U3 is 18.0 for song X04, 14.5 for song X11, 12.5 for song X06, 11.0 for song X01, and 11.0 for song X16. The order of performance of the music list L8 is music X04, X11, X06, X01, X16. In this way, a song list L8 is generated in which the singing history H3 of the user U3 with the shortest total singing time is given a higher degree of importance.

Further, as shown in FIG. 9(C), when the user U4 leaves the karaoke snack S at 20:30, the totaling unit 58 determines that the total singing time of the user U2 is 35 minutes, and the total singing time of the user U3 is 35 minutes. The singing results are aggregated with a time of 45 minutes. User U2's total singing time of 35 minutes is the shortest among the users, so the weighting for the number of singing times of user U2 is set to 2.0. Since user U3's total singing time of 45 minutes is the longest among the users, the weighting for the number of singing times of user U3 is set to 0.5.

As shown in FIG. 9D, when the user U4 leaves the store, the generation unit 56 generates songs X01, X04, X06, X08, X10, X11, and X14 that the users U2 and U3 have sung during a predetermined period. , X16, the number of singing times is extracted. When the songs extracted from the singing histories H2 and H3 are scored based on the number of times of singing, the number of times of singing is corrected for each song by a weighting coefficient. The number of singing times of user U3 with the longest total singing time is multiplied by a weighting factor of 0.5, and the number of singing times of user U2 with the shortest total singing time is multiplied by a weighting factor of 2.0.

When the score for each song is corrected by the weighting factor by the generating unit 56, a music list L9 is generated in the performance order of the BGM performance based on the corrected score. The total score for each song of users U2 and U3 is 13.0 for song X06, 10.0 for song X08, 9.5 for song X04, 9.0 for song X10, 8.5 for song X11, and 8.5 for song X16. is 6.0, music X01 is 5.5, and music X14 is 5.0, and the order of performance of music list L8 is music X06, X08, X04, X10, X11, X16, X01, and X14. In this way, a music list L9 is generated in which the importance of the singing history H2 of the user U2 with the shortest total singing time is increased.

As described above, according to the second embodiment, there is a high possibility that the user will be able to sing karaoke, and music that matches the tastes of the users who are present is emitted as BGM. At this time, music suitable for the user who sings relatively little is selected as BGM, and the user can be urged to reserve the music.

In the second embodiment, the total singing time of the users is totaled by the totalizing unit, and the score is corrected by the weighting coefficient according to the total singing time by the generating unit, but the configuration is not limited to this. It suffices that the totaling section totalizes the user's singing performance, and the generating section corrects the score according to the singing performance. For example, the total number of songs sung by the user may be totaled as the performance of singing by the counting unit, and the score may be corrected by a weighting factor according to the total number of songs sung. In this case, a counter is provided in the tallying unit, and the number of songs sung by the user is counted and tallied as the singing record. Alternatively, the user's singing end elapsed time (non-singing time) may be tallied as a singing performance by the counting unit, and the score may be corrected by a weighting coefficient according to the singing end elapsed time. In this case, the totalizing unit is provided with a timer, and the elapsed time from the end of the user's singing is measured and totaled as the singing record.

Further, in the first and second embodiments, the server device is configured to manage the singing history for each user ID, but the present invention is not limited to this configuration. The karaoke machine may be provided with a management section for managing the singing history of the user, and the management section of the karaoke machine may manage the singing history for each user ID. In this case, every time a user ID corresponding to face image data during singing is output from the image processing section to the management section, the singing history is updated for each user ID by the management section. Therefore, the acquiring unit acquires the singing history corresponding to the user ID of the user photographed when entering the store from the managing unit.

In addition, in the first and second embodiments, the generating unit assigns scores to songs extracted from the user's singing history, and generates a song list in the order of BGM performance based on the scores. Not limited. For example, a music list may be generated in which the order of extracting music from the singing history is the order of BGM performance, or a music list may be generated in which the music from the singing history is randomly arranged in the order of BGM performance. good too.

In addition, in the first and second embodiments, all songs that the user has sung in the last three months are extracted from the singing history by the generation unit, but the present invention is not limited to this configuration. For example, the generation unit may extract all songs that the user has sung in the last six months from the singing history, or extract all songs that the user has sung in the last six months. A predetermined number (for example, top 5 songs) may be extracted from the singing history in descending order of the number of songs sung.

In addition, the generation unit uses the singing history of songs sung from the present until a predetermined period ago to generate the music list, but the predetermined period may be changed according to the number of users in the store. For example, if the number of users in the store is 1, songs that have been sung by the users in the past three months from the present are extracted from the singing history, and the number of users in the store is 2. In the case of , songs that have been sung by the user up to four months ago are extracted from the singing history. In addition, when the number of users in the store is 3, the songs sung by the users up to 5 months ago are extracted from the singing history, and the number of users in the store is 4. In the case of , songs that have been sung by the user up to six months ago from the present may be extracted from the singing history. As a result, it is possible to avoid a decrease in the number of songs to be extracted as the number of users in the store increases.

Further, in the first and second embodiments, the song ID and the date of singing are included in the song history, but the present invention is not limited to this configuration. The singing history may include the scoring results of the songs, and the generating unit may extract the songs based on the scoring results included in the singing history. In this case, the karaoke main body is provided with scoring means for scoring the user's singing.

Further, in the first and second embodiments, the karaoke machine stores a customer management database dedicated to the store in which the feature amount extracted from the face image data is associated with the user ID, and the user corresponding to the face image data is stored in the karaoke machine. Although the ID is used as user identification information, the configuration is not limited to this. The user identification information may be face image data itself. In this case, the karaoke machine and the server device appropriately perform collation processing suitable for the type of user identification information.

Further, in the first and second embodiments, a function of generating a music list for BGM performance may be added to the karaoke machine by installing a program on the karaoke machine. This program is stored in a storage medium. The storage medium is not particularly limited, but non-transitory storage media such as optical discs, magneto-optical discs, and flash memories may be used.

Also, although the present embodiment has been described, other embodiments may be obtained by combining the above-described embodiments and modifications in whole or in part.

Moreover, the technology of the present invention is not limited to the above-described embodiments, and may be variously changed, replaced, and modified without departing from the spirit of the technical idea. Furthermore, if the technical idea can be realized in another way due to advances in technology or another derived technology, the method may be used for implementation. Therefore, the claims cover all implementations that may fall within the scope of the technical concept.

20, 40: karaoke devices 21, 41: karaoke main body 26, 46: photographing means 33, 53: image processing unit 34, 54: acquisition unit 35, 55: storage unit 36, 56: generation unit 37, 57: BGM performance unit 58: Aggregation part

Claims (5)

A karaoke device that is installed in a store, performs karaoke according to the reservation of music, and can perform BGM (Back-Ground Music) when there is no reservation of the music,
An acquisition unit that acquires a singing history corresponding to the user identification information of the user photographed at the time of entering the store by the photographing means, and outputs the singing history in association with the user identification information;
A storage unit that associates and stores the user identification information and singing history output from the acquisition unit, and deletes the singing history corresponding to the user identification information of the user photographed by the photographing means when leaving the store;
A karaoke machine, comprising: a generating unit for generating a list of songs to be played as BGM based on the singing history stored in the storage unit when a user enters and leaves the store. 2. The karaoke apparatus according to claim 1, wherein the generating unit does not include a song that has already been karaoke-played in the song list until all users who were present during the karaoke-play of the song leave the store. 3. The generating unit according to claim 1, wherein the generating unit assigns scores to the music pieces extracted from the user's singing history, and generates a music list in order of BGM performance based on the scores. karaoke equipment. a totaling unit that totalizes the singing performance for each user based on the user identification information of the user photographed during singing by the photographing means,
4. The generating unit according to claim 3, wherein the generating unit corrects the score of each piece of music according to the user's singing record, and generates the music list in the performance order of the BGM performance based on the corrected score. karaoke equipment. The generating unit uses a singing history of songs sung from the present to a predetermined period ago to generate the music list, and changes the predetermined period according to the number of users who are in the store. The karaoke apparatus according to any one of claims 1 to 4.

Images