JP7517750B2 - Automatic music selection system for wedding ceremonies - Google Patents

Description

This invention relates to an automatic music selection system, and more specifically to an automatic music selection system for music to be played in the background at wedding ceremonies.

Conventionally, at various events such as weddings and funerals, music appropriate to the event is played in the background to liven up the event. In particular, at weddings and other events, there are many different events (e.g., the entrance of the bride and groom, the cutting of the wedding cake, the presentation of a bouquet to the parents, etc.), and it takes a lot of time for the user and the venue staff to discuss the selection of music appropriate to each event.

To assist with the selection of music to be played in the background during various events (hereinafter also referred to as scenes) at a wedding, a music selection support system for wedding reception broadcasts has been disclosed that presents a list of recommended songs according to the wedding reception scenes (events) at the wedding reception and also allows the music to be changed according to the preferences of the users, who are the bride and groom (see Patent Document 1).

A wedding simulator has also been disclosed that prepares a list of recommended songs for each scene, lists recommended songs that correspond to that scene, allows the user to listen to songs selected from the list, outputs a selection list of songs for each scene, and can create a CD or DVD of the selected songs based on this (see Patent Document 2).

JP 2014-123351 A JP 2005-004262 A

Ceremonial events such as weddings, especially weddings, are deeply meaningful to users who are the bride and groom, and due to the trend of marrying later in life in recent years, users who hold weddings are from a wide range of age groups. For this reason, in systems such as those in Patent Documents 1 and 2 above that present a list of recommended songs (or recommended song lists) and allow users to select from them, it is difficult to select music that satisfies users who are the bride and groom for various age groups by simply presenting a uniform list of recommended songs (or recommended song lists).

Furthermore, no matter how sentimental the person may be, if the music selection is too original, there is a risk that general attendees will not enjoy it (will not be able to empathize with it). Also, in recent years, there has been remarkable progress in technology such as virtual assistants that have artificial intelligence (AI) and can communicate two-way through conversation on a computer via a communication line (Internet line, etc.). In other words, the task of selecting music according to various events (scenes), which was previously performed by the organizers of various events in direct discussion with the users, the bride and groom, can now be fully performed by these virtual assistants.

The present invention aims to provide an automatic music selection system for weddings that allows a virtual assistant, such as a wedding planner, to select the music to be played in the background of the wedding ceremony on a computer-based system via a public communication line (such as the Internet).

The present invention relates to an automatic music selection system in which a system server operated by a wedding organizer, a staff terminal managed by the organizer's staff, and user terminals owned by multiple users who are the bride and groom are all connected to each other via a public communication line network so that they can communicate with each other. The system server has a music selection means for selecting music to be played in the background of various events in a conversational format between the users who are the bride and groom and a virtual assistant on the user terminal, a ranking means for determining a music selection image including a ranking of music to be presented to the users who are the bride and groom in the music selection means, and The system includes a music selection image transmission means for transmitting a music selection image in the music selection means to the user terminal, and the user terminal includes an image receiving means for receiving a music selection image in the music selection means from the system server, a voice output means for outputting the voice of the virtual assistant from the system server, and a voice input means for transmitting a voice uttered by the users who are the bride and groom to the system server, and the system server operates the virtual assistant in the music selection means by superimposing it on the music selection image using a 2D morphing technique, and provides natural language support. The ranking means determines a music selection image including a ranking of music to be presented to the user who is the bride and groom based on the age, sex, and music taste of the user who is the bride and groom, the music selection means proposes the music selection image determined by the ranking means to the user who is the bride and groom, and the music selection means presents music consisting of an image of a virtual assistant, a ranking for each event, and a music name selected for each event selected by the user who is the bride and groom to other users who are the bride and groom. and performs association analysis of similarities and co-occurrences of the music to determine music to be proposed to the users who are the bride and groom, and after the users who are the bride and groom have selected music to be played in the background of various events, if there is an event for which music has not been selected by the users who are the bride and groom, the staff member uses the staff terminal to talk with the users who are the bride and groom, who are operating the user terminal, to determine music to be played for the unselected event, and performs a final check of the music to be played for all events.

According to the present invention, music to be played in the background of various events can be selected through conversation between the virtual assistant and the users (the bride and groom) in the music selection means between the system server and the user terminal. This allows the music selection means of the present invention to be used as a follow-up for the user, and shortens the time previously required for meetings between the staff of the organizers of various events and the users (the bride and groom) to arrange a wedding reception to be held.

Furthermore, the results of the selection of music played in the background of various events by the music selection means can be finally confirmed (or confirmed) by conversation between the staff terminal and the user terminal, between the staff and the users who are the bride and groom. This allows the selection of music by the users who are the bride and groom required for the event to be confirmed and confirmed before the event date, making it possible to hold the event safely without being left to a machine (program).

The virtual assistant in the music selection means is operated using 2D morphing technology, overlaid on the music selection image, and natural language processing is used to establish a conversation between the users (the bride and groom) and the virtual assistant. This allows the conversation between the users (the bride and groom) and the virtual assistant to proceed smoothly, allowing the users (the bride and groom) to select the music to be played in the background of the event as if they were having a meeting with staff from the organizers of various events.

The 2D morphing technology is a computer graphics technique that smoothly transforms a character image (in this invention, an image of a virtual assistant) on an image and adds motion (movement) such as changes in the character or facial expression.

Natural Language Processing (NPL) is a set of technologies (a field of artificial intelligence and linguistics) that allows computers to process the natural language that humans use on a daily basis. In this way, by using 2D morphing and natural language processing technologies, the conversation between the bride and groom and the virtual assistant can be made to feel as if the bride and groom are having a natural conversation with a real person.

The music selection means also compares the music patterns selected by the users who are the bride and groom with the music patterns selected by other users, analyzes the similarity and co-occurrence of the music selected by the users, and determines the music to be proposed to the users who are the bride and groom. Association analysis, for example, is preferably used to analyze the similarity and co-occurrence of the music selected by the users who are the bride and groom, and this association analysis makes it possible to propose music that matches the preferences of the users who are the bride and groom.

Association analysis, also known as market basket analysis, is a method for finding rules for the association between two or more selected pieces of music. It is also a data mining method that analyzes the accumulated music selection status of each bride and groom user and proposes combinations of music that have strong similarities or co-occurrences, thereby extracting relationships (rules) between events that have strong statistical correlations. From the results of this association analysis, it is possible to analyze the music selection trends of the bride and groom users, such as which music suits the preferences of the bride and groom users. In this way, by encouraging the bride and groom users to select music based on the similarities and co-occurrences of the music between the bride and groom users, it is possible to select music that will be played in the background of the event with the bride and groom users' consent.

The ranking means also determines the ranking of music to be presented to users based on the age, sex, and musical tastes of the users who are the bride and groom. This makes it possible to select music to be played in the background of an event that suits a wide range of age groups of users who are the bride and groom.

In this way, when performing voice input and output using an agent, not only is the image of the agent processed so that it moves in sync with the conversation, but the content of the conversation can be processed using natural language in order to ensure that the conversation with the users (the bride and groom) is as natural as possible. This gives the users (the bride and groom) the feeling that they are conversing with real people, making it possible to naturally select the music that will be played in the background of various events.

This is also executed after the users, who are the bride and groom, have selected the music to be played at various events. If the music to be played at various events by the users, who are the bride and groom, has not yet been selected (i.e., is on hold), the staff operating the automatic music selection system will decide the music to be played at the unselected events by talking to the users, who are the bride and groom, who are operating the user terminal via the staff terminal, and can also give the users, who are the bride and groom, a final confirmation of the music to be played at all events.

In addition, the music selected by the users who are the bride and groom to be played at various events is first superimposed on a music selection image determined by the ranking means and transmitted to the user terminal as a virtual assistant, the virtual assistant is operated using 2D morphing technology, and natural language processing is performed to prompt the users who are the bride and groom to select music to be played in the background of various events through natural conversation between the users who are the bride and groom and the virtual assistant, and next, if there is an event for which music has not been selected, the pattern of music selected by the users who are the bride and groom is compared with the pattern of music selected by other users who are the bride and groom, and association analysis is performed on the similarities and co-occurrences of the music, and music that is close to the preferences of the users who are the bride and groom is superimposed on the virtual assistant and transmitted to the user terminal, the virtual assistant is operated using 2D morphing technology, and natural language processing is performed to prompt the users who are the bride and groom to select music to be played at various events for which music has not been selected through natural conversation between the users who are the bride and groom and the virtual assistant. Once the music selection process is complete, a music selection and confirmation process is performed, and if there is an event for which music has not been selected, the staff operating the automatic music selection system can decide the music to be played for that event through conversation with the users (the bride and groom) who are operating the user terminal via the staff terminal, and can also provide a final confirmation of the music to be played for all events to the users (the bride and groom).

In this way, the music selection process involves a two-stage process in which the users who are the bride and groom are prompted to select the music to be played in the background of various events, and ultimately, in the music selection and confirmation process by the staff, the music to be played at all events can be decided without omission through dialogue between the staff and the users who are the bride and groom. Therefore, for various events held at a wedding, the optimal music (background music) desired by the users who are the bride and groom can be decided with as little burden on the staff as possible, and ultimately, if there are events for which music has not yet been selected, it is decided through dialogue between the staff and the users who are the bride and groom, and the staff confirms the decided music with the users who are the bride and groom, so that the music to be played at various events held at weddings, funerals, and other ceremonies can be decided without omission.

1 is a diagram showing a configuration of an automatic music selection system according to an embodiment of the present invention; 2 is a block diagram illustrating the electrical configuration of a system server of the automatic music selection system according to the present embodiment. FIG. 3 is a flowchart of the automatic music selection system according to the present embodiment. 3 is a flowchart of the automatic music selection system according to the present embodiment. 11 is a diagram illustrating a correlation analysis in the music selection process of the present embodiment. FIG. 11 is a display example of image data on a user terminal of the automatic music selection system of the present embodiment. 11 is a display example of image data on a user terminal of the automatic music selection system of the present embodiment. 11 is a display example of image data on a user terminal of the automatic music selection system of the present embodiment.

The gist of the present invention is an automatic music selection system in which a system server operated by a wedding organizer, a staff terminal managed by the organizer's staff, and user terminals owned by multiple users who are the bride and groom are all connected to each other via a public communication line network so that they can communicate with each other, and the system server has a music selection means for selecting music to be played in the background of various events in a conversational format between the users who are the bride and groom and a virtual assistant, and a ranking means for determining a music selection image including a ranking of music to be presented to the users who are the bride and groom in the music selection means. and a music selection image transmission means for transmitting a music selection image in the music selection means to the user terminal, the user terminal being equipped with an image receiving means for receiving a music selection image in the music selection means from the system server, a voice output means for outputting the voice of the virtual assistant from the system server, and a voice input means for transmitting a voice uttered by the users who are the bride and groom to the system server, the system server being operated by the virtual assistant in the music selection means by superimposing it on the music selection image using 2D morphing technology, The ranking means determines a music selection image including a ranking of music to be presented to the user who is the bride and groom based on the age, sex, and music taste of the user who is the bride and groom, the music selection means proposes the music selection image determined by the ranking means to the user who is the bride and groom, and the music selection means presents the image of the virtual assistant selected for each event selected by the user who is the bride and groom, the ranking for each event, and the music name to other users who are the bride and groom. This is an automatic music selection system for selecting music at weddings, which performs association analysis of similarities and co-occurrences of music compared to music selected by a certain user to determine music to be proposed to the users who are the bride and groom, and after the users who are the bride and groom have selected music to be played in the background of various events, if there is an event for which music has not been selected by the users who are the bride and groom, the staff member uses the staff terminal to talk with the users who are the bride and groom, who are operating the user terminal, to determine the music to be played for the unselected event, and performs a final check of the music to be played for all events.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a diagram showing the configuration of an automatic music selection system of this embodiment. FIG. 2 is a block diagram explaining the electrical configuration of a system server of the automatic music selection system of this embodiment. FIG. 3 is a flowchart of the automatic music selection system of this embodiment. FIG. 4 is a flowchart of the automatic music selection system of this embodiment. FIG. 5 is a diagram explaining correlation analysis in the music selection process of this embodiment. FIG. 6 is an example of image data displayed on a user terminal of the automatic music selection system of this embodiment. FIG. 7 is an example of image data displayed on a user terminal of the automatic music selection system of this embodiment. FIG. 8 is an example of image data displayed on a user terminal of the automatic music selection system of this embodiment.

[1. Configuration of the automatic music selection system]
Hereinafter, an outline of the configuration of the automatic music selection system according to the present embodiment will be described with reference to FIG.

As shown in FIG. 1, the automatic music selection system 1 is connected to a system server 10 managed by an organizer 100 of various events, user terminals 20 carried by multiple users 200 who are the bride and groom, and staff terminals 30 managed by multiple staff members 300 of the organizer 100, all of which are communicatively connected to each other via a public communication line network 50.

Well-known computers are preferably used as the system server 10, the user terminal 20, and the staff terminal 30. Note that well-known computers are preferably desktop computers, notebook computers, tablet computers, etc., but any computer that has the function of enabling mutual communication via the public communication line network 50 will do. The user terminal 20 may be, for example, a smartphone, a tablet terminal, a mobile notebook computer, etc. The public communication line network 50 is a well-known internet line, a mobile phone communication line, a telephone line, a communication satellite line, etc.

The organizer 100 is the administrator of the system server 10 of the automatic music selection system 1, and is, for example, a business operator (manager of a wedding hall or funeral hall) that holds various events related to ceremonial occasions (e.g., weddings and funerals) or a company (e.g., an IT company) that has been entrusted with operation by a business operator that holds various events. The organizer 100 manages and operates the system server 10 of the automatic music selection system 1 in this embodiment. The multiple staff members 300 are multiple staff members 300 of the organizer 100 who support the holding of various events. The users 200, who are the bride and groom, are users of this system who are registered in the automatic music selection system 1.

Users 200, who are multiple brides and grooms in the automatic music selection system 1, use the automatic music selection system 1 of this embodiment to select music to be played in the background of various events that are held by them under contract with the organizer 100. In the following explanation, the selection of music to be played in the background of various events at a wedding ceremony (entrance of the bride and groom, cutting of the wedding cake, presentation of bouquets to the parents, etc.) will be explained as an example.

In the automatic music selection system 1, the users 200 who are the bride and groom select the music to be played in the background of various events through a conversation between the users 200 who are the bride and groom and the virtual assistant 23 while the music selection image in the music selection means transmitted from the system server 10 is displayed on the display screen of the user terminal 20 (see Figures 7 and 8). At this time, the virtual assistant 23 operates using 2D morphing technology simultaneously with the music selection image, and can establish a natural conversation between the users 200 who are the bride and groom and the virtual assistant 23 by performing natural language processing. This allows the users 200 who are the bride and groom to feel as if they are talking to a real person (e.g., staff 300), making it possible to naturally select the music to be played in the background of various events.

In the above-described configuration, the automatic music selection system 1 in this embodiment is operated by the bride and groom, who are the users 200, and the staff members 300, who register as members on a dedicated site set up on the system server 10 of the organizer 100 who manages the system, via the public communication line network 50 using their respective terminals (user terminal 20, staff terminal 30). The registered members, who are the bride and groom, the users 200 and the staff members 300, are then sent a dedicated ID and a password automatically generated by the dedicated site of the system server 10 at the time of member registration. Hereinafter, the registered members, who are the bride and groom, the users 200 and the staff members 300, use their dedicated ID and password to access the dedicated site set up on the system server 10, thereby executing the automatic music selection system 1.

[2. System Server Configuration]
The electrical configuration of the system server 10 in the automatic music selection system 1 of this embodiment will be described below with reference to Fig. 2. The system server 10 includes a storage unit 11, an input/output control unit 12, a control unit 13, an external communication I/F (InterFace) control unit 14, and the like.

The storage unit 11 is composed of a large-capacity storage device such as a HDD (Hard Disk Drive) or flash memory, and in this embodiment, various information (user information on the bride and groom, such as address, name, age, and music preferences) of multiple users 200 who are registered in the system, music data, music data selected by past customers, music ranking data according to events, etc. are stored in the storage unit 11. Note that since music data occupies a large amount of capacity, another storage device that stores big data on music may be used in addition to the system server 10.

The input/output control unit 12 controls the input and output of various data to and from external input/output devices such as a liquid crystal display device (not shown) connected to the system server 10, and a keyboard/mouse.

The control unit 13 is composed of a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), a flash memory, etc. (not shown). The CPU of the control unit 13 executes various programs pre-stored in the ROM or the memory unit 11, thereby functioning as a music selection process (music selection means) described below, etc.

The external communication I/F control unit 14 is connected to an external public communication line network 50, and controls communication with the user terminals 20 owned by the multiple users 200 who are the bride and groom in the automatic music selection system 1, and the staff terminals 30 owned by the multiple staff members 300, based on instructions from the control unit 13. Based on instructions from the control unit 13, the external communication I/F control unit 14 transmits a music selection image including an image of the virtual assistant 23 (see Figures 6 to 8) to the user terminals 20 owned by the users 200 who are the bride and groom, operates the virtual assistant 23 using 2D morphing technology, and establishes a natural conversation between the users 200 who are the bride and groom and the virtual assistant 23 by performing natural language processing.

[3. Music Selection Processing]
Hereinafter, the music selection process in the automatic music selection system 1 of this embodiment will be described with reference to Fig. 3 and Fig. 6 to Fig. 8. This music selection process is executed in the control unit 13 (hereinafter simply referred to as the control unit 13) of the above-mentioned system server 10. The music selection process also functions as the music selection means of this embodiment.

As shown in FIG. 3, when the user 200, who is the bride and groom, accesses the system server 10 via the user terminal 20, the control unit 13 that executes the music selection process transmits a music selection image to the user terminal 20 of the user 200, who is the bride and groom, who desires automatic music selection at various events (step S10). This process functions as a music selection image transmission means of this embodiment. By this process, as shown in FIG. 6, an image of the virtual assistant 23 is displayed on the display device 21 (liquid crystal display device) of the user terminal 20. The image of the virtual assistant 23 operates using 2D morphing technology, and a voice message 24 (a speech bubble in the figure) that has been processed using natural language is output from the speaker 25, which is the voice output means of the user terminal 20. The voice message 24 output by the virtual assistant 23 shown in FIG. 6 is the role of the virtual assistant 23 in the automatic music selection system 1, the selection of music to be played in the background according to various events, and the flow (procedure) of music selection in the music selection process.

The control unit 13 transmits the music ranked for each event to the user terminal 20 of the user 200, who is the bride and groom (step S11). With this process, as shown in FIG. 7, the display device 21 of the user terminal 20 displays the ranking for each event and the music titles, for example as the music ranking 22 for event 1, along with the image of the virtual assistant 23. The image of the virtual assistant 23 then operates using 2D morphing technology, and outputs a natural language processed voice message 24 from the speaker 25, which is the voice output means of the user terminal 20.

In addition, in the process of step S11, not only the ranked music (music rankings 22) but also a recommendation list (recommended, recommended, or recommended) from various perspectives calculated based on past data and a music list according to the event, such as a recommendation list from the staff in charge, can be sent to the user terminal 20 of the user 200 who is the bride and groom. As a result, the display device 21 of the user terminal 20 displays the music list as a recommendation list along with the virtual assistant 23 and the music rankings 22 for each event, so that the user 200 who is the bride and groom can be given a variety of options when selecting music.

The control unit 13 determines whether the bride and groom user 200 has selected music for all events (step S12), and if it is determined that the bride and groom user 200 has selected music for all events (step S12: Yes), the control unit 13 proceeds to step S13. On the other hand, if it is determined that the bride and groom user 200 has not selected music for all events (step S12: No), the control unit 13 proceeds to step S11. In this embodiment, the number of various events selected by the bride and groom user 200 is up to 10 (see FIG. 5). Since the ranked music is different for each event, the selection of music for each event is repeated up to 10 times. The number of various events is not limited to a maximum of 10, and may be more or less than that, but in this embodiment, a maximum of 10 events will be described as an example for ease of understanding.

In addition, the bride and groom user 200 selects music by sending the ranking and music name to the system server 10 via the microphone 26, which is the voice input means of the user terminal 20, while the image of the virtual assistant 23, the ranking for each event, and the music name are displayed on the display device 21 of the user terminal 20 shown in FIG. 7. Note that the bride and groom user 200 does not necessarily have to select music for each event. For example, by sending a hold, next selection, etc. to the system server 10 via the microphone 26 of the user terminal 20, the selection for the event is processed as an unselected song (i.e., '-') as shown in FIG. 5, and is stored in a specified area of the memory unit 11 of the system server 10.

The control unit 13 associates the music selected for each event with the event and stores it in a specified area of the memory unit 11 (step S13). The control unit 13 then determines whether music selection for all events has been completed (step S14). If it is determined that music selection for all events has been completed (step S14: Yes), the control unit 13 ends the music selection process. On the other hand, if it is determined that music selection for all events has not been completed (step S14: Yes), the control unit 13 proceeds to step S15.

In this process, the control unit 13 reads a specific area of the memory unit 11 shown in FIG. 5 and determines whether there are any events that have been processed as unselected music (i.e., '-'). This is to suggest music according to the event in a pattern different from the ranking for events for which no music has been selected.

The control unit 13 determines whether or not to suggest music according to the event in a pattern different from the ranking (step S15). If it is determined that the suggestion is not to be made (step S15: No), the control unit 13 ends the music selection process. On the other hand, if it is determined that the suggestion is to be made (step S15: Yes), the control unit 13 proceeds to step S16.

The control unit 13 analyzes, for each event, the similarity and co-occurrence between the music selected by the user 200 who is the bride and groom currently selecting music for the event and the music selected by the user 200 who is the bride and groom in the past for the event, and suggests to the user 200 who is the bride and groom a music selection based on the analysis results.

Here, in this embodiment, the determination of similarity and co-occurrence between the user 200 who is the bride and groom currently selecting music and the user 200 who is the bride and groom in the past is performed using the association (correlation) analysis shown in FIG. 5. Association analysis is also called market basket analysis, and is a method for searching for association rules between two or more selected music. In other words, as shown in FIG. 5, when comparing the music selection data of customers A to E (users 200 who are the bride and groom in the past) with the data of the unselected music "-" cells of customer X (user 200 who is the bride and groom currently selecting music), it can be seen that the correlation coefficients of customer C (correlation coefficient 1.000), customer E (correlation coefficient 0.612), and customer C (correlation coefficient 0.500), which are surrounded by dotted lines in the figure, are close to customer X. It can be said that the closer the correlation coefficients are, the more similar the grouping (sorting) tendencies are.

As a result, for customers C to E, whose correlation coefficients are close, a "1" is recorded in the cell for the song selected in event 5 (excluding songs not selected), so the recommendation level for customer X in event 5 is "1.00," and it can be said that music A matches customer X's taste in event 5.

Based on the results of the association (correlation) analysis described above, the control unit 13 proposes music a corresponding to event 5 to the user 200, who is the bride and groom (step S16). As a result, as shown in FIG. 8, the display device 21 of the user terminal 20 displays "music a" that matches the preferences of the user 200, who is the bride and groom, at event 5, simultaneously with an image of the virtual assistant 23. The image of the virtual assistant 23 then operates using 2D morphing technology, and outputs a natural language processed voice message 24 from the speaker 25, which is the voice output means of the user terminal 20.

Based on the above-mentioned association (correlation) analysis result, the control unit 13 determines whether or not the music a corresponding to the event 5 proposed to the user 200 who is the bride and groom has been selected by the user 200 who is the bride and groom (step S17). If the control unit 13 determines that the music a has not been selected by the user 200 who is the bride and groom (step S17: No), the control unit 13 ends the music selection process. On the other hand, if the control unit 13 determines that the music a has been selected by the user 200 who is the bride and groom (step S17: Yes), in step S18, the control unit 13 associates the music selected corresponding to the event with the event and stores it in a specified area of the storage unit 11 (step S18). When this process ends, the control unit 13 ends the music selection process.

The bride and groom, who are the users 200, select music by sending, for example, "select music" to the system server 10 via the microphone 26 of the user terminal 20 while the image of the virtual assistant 23 and music a corresponding to event 5 are displayed on the display device 21 of the user terminal 20 shown in FIG. 8. It should be noted that the bride and groom, who are the users 200, do not necessarily need to select music a corresponding to event 5. For example, by sending "on hold" or the like to the system server 10 via the microphone 26 of the user terminal 20, the music selection for the event is processed as unselected (i.e., '-') as shown in FIG. 5, and is stored in a specified area of the memory unit 11 of the system server 10.

[4. Song selection and confirmation by staff]
Hereinafter, the music selection and confirmation process by the staff in the automatic music selection system 1 of this embodiment will be described with reference to Fig. 4. This process is executed between the staff terminal 30 operated by the staff 300 and the user terminal 20 of the user 200 who is the bride and groom. In other words, this process is executed by voice conversation between the staff 300 and the user 200 who is the bride and groom.

As shown in FIG. 4, the staff terminal 30 of the staff member 300 who performs the music selection and confirmation process by the staff member is connected to the user terminal 20 of the user 200 who is the bride and groom (step S20). This process causes an image of the staff member 300 (or a video) to be displayed on the display device 21 (liquid crystal display device) of the user terminal 20.

The staff terminal 30 of the staff 300 obtains the music selection status (see FIG. 5) for each event of the user 200 who is the bride and groom from the system server 10, and determines whether the user 200 who is the bride and groom has finished selecting music for all events (i.e., all events performed by the user 200 who is the bride and groom) (step S21). If the staff terminal 30 determines that music selection for all events has been completed (step S21: Yes), it proceeds to step S24. On the other hand, if it determines that music selection for all events has not been completed (step S21: No), it proceeds to step S22.

While checking the music selection status (see FIG. 5) for each event of the bride and groom user 200 obtained in step S21 described above, the staff member 300 selects music for events for which music has not yet been selected in accordance with the requests of the bride and groom user 200 through a call with the bride and groom user 200 (step S22).

The staff member 300 determines whether there is an event for which music has not been selected (step S23), and if it is determined that there is an event for which music has not been selected (step S23: Yes), it repeats step S22 described above. If it is determined that there is no event for which music has not been selected (step S23: No), the staff member 300 performs a final confirmation of the music selection for all events with the users 200, who are the bride and groom (step S24), and ends the music selection and confirmation process by the staff member.

In the above-mentioned music selection and confirmation process by the staff, the staff 300 and the users 200 who are the bride and groom talk directly to each other, and the bride and groom selects music until there are no more events for which music has not been selected. However, the acquisition (step S21) of the music selection status (see Figure 5) for each event by the users 200 who are the bride and groom from the above-mentioned system server 10 other than this direct call is executed by a dedicated program that is pre-installed on the staff terminal 30 of the staff 300.

Now, referring to Figures 6 to 8, an example of a music selection image transmitted from the system server 10 and displayed on the display device 21 of the user terminal 20 in the music selection process of the above-mentioned system server 10 in the automatic music selection system 1 of this embodiment will be described. As shown in Figures 6 to 8, the user terminal 20 is preferably, for example, a notebook computer equipped with a display device 21 (liquid crystal display device), a speaker 25, and a microphone 26. Note that the user terminal 20 may be any terminal equipped with a function for accessing the system server 10 (intercommunication function), an image display function, a speaker 25, and a microphone 26.

As shown in FIG. 6, when the bride and groom, who are users 200, access the system server 10 via the user terminal 20, the music selection image sent from the system server 10 is displayed on the display device 21 of the user terminal 20 (image receiving means). Then, an image of the virtual assistant 23 is displayed superimposed on the music selection image. Note that the music selection image shown in the figure can display a photo of a currently popular music CD case (not shown). The image of the virtual assistant 23 operates using 2D morphing technology, and a voice message 24 (a speech bubble in the figure) processed by natural language processing is output from the speaker 25, which is the voice output means of the user terminal 20. Note that the voice message 24 output by the virtual assistant 23 shown in FIG. 6 is a message explaining the role of the virtual assistant 23 in the automatic music selection system 1.

As shown in FIG. 7, when the system server 10 transmits music ranked for each event to the user terminal 20, the received music rankings 22 are displayed on the display device 21 of the user terminal 20, superimposed on the music selection image.

The image of the virtual assistant 23 operates using 2D morphing technology, and outputs a natural language processed voice message 24 to the users 200 who are the bride and groom from the speaker 25, which is the voice output means of the user terminal 20. At this time, the voice message 24 output from the speaker 25 is a message that prompts the users 200 who are the bride and groom to select a song from the music rankings 22 displayed on the display device 21. In this state, when the users 200 who are the bride and groom say the "music name" they want to select from the music rankings 22, the voice of the users 200 who are the bride and groom is transmitted from the microphone 26, which is the voice input means, to the system server 10 and stored in a specified area of the memory unit 11 of the system server 10, and the users 200 who are the bride and groom select a song according to the event.

Note that it is not necessary for the bride and groom users 200 to select music for each event from the music rankings 22. For example, by sending "on hold," "next selection," etc. to the system server 10 via the microphone 26 of the user terminal 20, the selection for the event will be processed as an unselected song (i.e., '-') as shown in FIG. 5, and will be stored in a specified area of the memory unit 11 of the system server 10.

In addition, the music selection image in FIG. 7 may display not only the music rankings 22, but also music lists such as recommendation lists from various perspectives calculated based on past data and recommendation lists from staff in charge.

As shown in FIG. 8, the system server 10 analyzes (associates) for each event the music selected by the user 200 who is the bride and groom currently selecting music for the event, and the music selected by the user 200 who is the bride and groom in the past for events, and transmits music based on the analysis results to the user terminal 20. The received music name 22 is then displayed on the display device 21 of the user terminal 20, superimposed on the music selection image.

The image of the virtual assistant 23 operates using 2D morphing technology, and outputs a natural language processed voice message 24 to the users 200 who are the bride and groom from the speaker 25, which is the voice output means of the user terminal 20. At this time, the voice message 24 output from the speaker 25 is a message that prompts the user 200 who is the bride and groom to select the music name 22 displayed on the display device 21. In this state, when the users 200 who are the bride and groom say "select", the voice of the users 200 who are the bride and groom is transmitted from the microphone 26, which is the voice input means, to the system server 10 and stored in a specified area of the memory unit 11 of the system server 10, and the users 200 who are the bride and groom select the recommended music according to the event.

Note that it is not necessary for the bride and groom users 200 to select the recommended music. For example, by sending "on hold" or "no music selection" to the system server 10 via the microphone 26 of the user terminal 20, the music selection for the event will be processed as unselected (i.e., '-') as shown in Figure 5, and will be stored in a specified area of the memory unit 11 of the system server 10.

In the music selection images shown in Figures 6 to 8, it is desirable to synchronize the movement of the virtual assistant 23, which operates using 2D morphing technology and is displayed on the display device 21 of the user terminal 20, with the timing at which the natural language processed voice message 24 (speech bubble in the figure) is output from the speaker 25 of the user terminal 20. For example, in Figure 7, the virtual assistant 23 is made to bow, and the voice message 24 is output in accordance with that movement, giving the user 200, who is the bride and groom, the impression that they are having a more natural conversation with the virtual assistant 23.

Here, the ranking means in this embodiment will be explained. When the bride and groom users 200 register with the automatic music selection system 1, the bride and groom user information (age, gender, and music preferences for each bride and groom user 200) is registered in the memory unit 11 of the system server 10. At this time, the control unit 13 of the system server 10 determines the music ranking to be presented to the bride and groom users 200 based in advance on the age, gender, and music preferences of the bride and groom users 200. The music ranking determined here is displayed on the display device 21 of the user terminal 20 as the music ranking 22 shown in FIG. 7, together with the virtual assistant 23.

In this way, by determining the music rankings to be presented to the bride and groom user 200 based on the age, sex, and musical tastes of the bride and groom user 200, it is possible to select music to be played in the background of an event that suits the diverse age range of the bride and groom user 200. Note that the music rankings 22 shown in FIG. 7 are three, rankings 1 to 3, but this is just one example, and the number of rankings may be increased to five or ten. This increases the options available to the bride and groom user 200 when selecting music.

In the above-described embodiment, various events for the automatic music selection system 1 have been described using a wedding event as an example, but the present invention is not limited to this, and the automatic music selection system 1 of the present invention can be used for various events such as weddings, funerals, parties, etc.

Although the embodiments of the present invention have been described above, the specific configuration of the present invention is not limited to the above-mentioned embodiments, and the present invention also includes design changes and the like that do not deviate from the gist of the invention.

REFERENCE SIGNS LIST 1 Automatic music selection system 10 System server 20 User terminal 21 Display device 23 Virtual assistant 25 Speaker 26 Microphone 30 Staff terminal 50 Public communication line network 100 Organizer 200 Users who are the bride and groom 300 Staff

Claims (1)

In an automatic music selection system in which a system server operated by a wedding organizer, a staff terminal managed by the organizer's staff, and user terminals owned by multiple users who are the bride and groom are all connected to each other so that they can communicate with each other via a public communication line network, the system server comprises: a music selection means for selecting music to be played in the background of various events in a conversational format between the users who are the bride and groom and a virtual assistant in the user terminal; a ranking means for determining a music selection image including a ranking of music to be presented to the users who are the bride and groom in the music selection means; and a music selection image transmission means for transmitting the music selection image in the music selection means to the user terminal;
The user terminal includes an image receiving means for receiving a music selection image in the music selection means from the system server, a voice output means for outputting the voice of the virtual assistant from the system server, and a voice input means for transmitting the voice uttered by the users who are the bride and groom to the system server;
The system server operates the virtual assistant in the music selection means by superimposing it on the music selection image using 2D morphing technology, and establishes a conversation between the bride and groom, who are users, and the virtual assistant by performing natural language processing;
The ranking means determines a music selection image including a ranking of music to be presented to the users who are the bride and groom based on the age, sex, and music taste of the users who are the bride and groom, and the music selection means proposes the music selection image determined by the ranking means to the users who are the bride and groom,
The music selection means compares the music selected for each event by the users who are the bride and groom, which is composed of an image of a virtual assistant, a ranking for each event, and a music name, with music selected by other users who are the bride and groom, and performs association analysis of similarity and co-occurrence of the music to determine music to be proposed to the users who are the bride and groom;
This automatic music selection system for selecting music at weddings is characterized in that after the bride and groom users have selected music to be played in the background of various events, if there is an event for which the bride and groom users have not yet selected music, the staff member determines the music to be played for the unselected event by talking with the bride and groom users who are operating the user terminal via the staff terminal, and makes a final confirmation of the music to be played for all events.

Images