JP7843203B2 - In-vehicle terminals - Google Patents

Description

This invention relates to an in-vehicle terminal.

In recent years, it has become possible to access a variety of services by installing dedicated application software on mobile devices such as smartphones.

For example, there are karaoke apps that allow users to access services similar to those of a karaoke machine on their mobile devices (see Non-Patent Document 1). Using the karaoke app described in Non-Patent Document 1, users can enjoy singing karaoke along with the karaoke music emitted from their mobile devices. Furthermore, the mobile device can evaluate the user's karaoke performance based on the singing voice input via a sound collection means such as a microphone.

Karaoke@DAM for smartphones, [searched August 21, 2022], Internet <URL: https://www.clubdam.com/spkdam/>

Drivers of private vehicles can sing karaoke while driving by using the aforementioned karaoke app. However, because drivers need to concentrate on driving, they may not be able to sing as well as they would in a karaoke establishment.

The object of this invention is to provide an in-vehicle terminal that can evaluate karaoke singing, taking into account that the person singing karaoke is driving a vehicle.

One invention for achieving the above objective is an in-vehicle terminal mounted in a vehicle, comprising: a performance processing unit that performs karaoke of a song selected by the driver of the vehicle; a determination unit that determines the degree of concentration of the driver on driving based on driver video data obtained by photographing the driver from a photographing means, and determines whether the degree of concentration satisfies a first predetermined condition; and an evaluation unit that determines an evaluation of the karaoke singing performed by the driver, and corrects the evaluation if it is determined that the degree of concentration satisfies the first predetermined condition.
Other features of the present invention will be revealed in the specification and drawings described below.

According to this invention, it is possible to evaluate karaoke singing while taking into account that the person singing karaoke is driving a vehicle.

This figure shows a vehicle and an in-vehicle terminal according to an embodiment. This is a diagram showing an in-vehicle terminal according to an embodiment. This flowchart shows the processing of an in-vehicle terminal according to the embodiment. This figure shows an in-vehicle terminal relating to Modification 1.

<Implementation>
An in-vehicle terminal according to an embodiment will be described with reference to Figures 1 to 3.

==In-vehicle terminals==
An in-vehicle terminal is a device installed in a vehicle. An in-vehicle terminal can be a smartphone or tablet owned by the user, or a dedicated computer pre-installed in the vehicle. The in-vehicle terminal has functions similar to those found in typical smartphones, such as a music player. The user is the driver of the vehicle. The vehicle is a privately owned car or similar vehicle owned by the driver.

In this embodiment, the in-vehicle terminal has dedicated application software (hereinafter referred to as "karaoke app") installed for using the karaoke performance function. The karaoke performance function is a function that performs karaoke on the in-vehicle terminal. The karaoke app can be obtained, for example, by downloading it from a designated website.

As shown in Figure 1, the in-vehicle terminal M according to this embodiment is installed in a vehicle C driven by driver D. A karaoke application is installed on the in-vehicle terminal M.

As shown in Figure 2, the in-vehicle terminal M comprises a storage means 10, a communication means 11, a display means 12, an input means 13, a sound emission means 14, a sound collection means 15, a shooting means 16, and a control means 17. Each component is connected to bus B via an interface (not shown).

[Memory means, communication means, display means, input means, sound emission means, sound collection means, photographic means]
The storage means 10 is a storage device that stores various types of data. The storage means 10 stores terminal identification information. The terminal identification information is information unique to each in-vehicle terminal, such as a terminal ID for identifying the in-vehicle terminal. The communication means 11 provides an interface for communicating with an external server device or the like (not shown). The display means 12 is a display that shows various types of information. The input means 13 is configured for the driver to input various instructions. Note that the display means 12, which is configured in a touch panel format, may also function as the input means 13. The sound emission means 14 is configured for emitting sound, such as a speaker. The sound collection means 15 is configured for collecting sound emitted by the driver, such as a microphone. The shooting means 16 is configured for photographing a subject, such as a camera. In this embodiment, the shooting means 16 includes an in-camera for photographing the driver.

[Control means]
The control means 17 performs various controls on the in-vehicle terminal M. The control means 17 includes a CPU and memory (neither of which are shown). The CPU realizes various functions by executing programs stored in the memory.

In this embodiment, when the karaoke application is launched on the in-vehicle terminal M, the control means 17 functions as a performance processing unit 100, a determination unit 200, and an evaluation unit 300.

(Performance Processing Department)
The performance processing unit 100 plays karaoke versions of songs selected by the vehicle driver.

When the karaoke app is launched, the in-vehicle terminal M displays a song selection screen on the display means 12. The driver D selects the desired song via the input means 13. The in-vehicle terminal M transmits the song identification information of the selected song, associated with its own terminal identification information, to the server device (not shown). The song identification information is unique to each song, such as a song ID used to identify the song.

The server device (not shown) transmits song data corresponding to the received song identification information to the in-vehicle terminal M. The song data is assigned song identification information. The song data includes karaoke performance data, reference data, section information, etc. Karaoke performance data is data for performing karaoke (i.e., the data that forms the basis of the karaoke performance sound). Karaoke performance data is in a format playable by the music player function or karaoke application on the in-vehicle terminal M. Reference data is data indicating the main melody of the song being performed karaoke. Section information indicates the performance section. The performance section is the section in which the karaoke performance takes place. The performance section includes both singing sections and non-singing sections. Singing sections are sections in a song where lyrics to be sung are set (for example, the A section, B section, and chorus of the first verse). Non-singing sections are sections in a song where lyrics to be sung are not set, such as the intro, interlude, and outro.

The performance processing unit 100 uses the karaoke performance function provided by the karaoke application to perform karaoke based on the karaoke performance data included in the received song data. The karaoke performance sound is emitted from the sound emission means 14 (or other sound emission means such as speakers installed in the vehicle). Driver D can sing karaoke along with the karaoke performance using the sound collection means 15 (or other sound collection means such as a headset attached to the in-vehicle terminal). The in-vehicle terminal M outputs singing audio data corresponding to the singing voice of driver D to the evaluation unit 300.

Furthermore, the storage means 10 may store multiple song data sets in advance. In this case, the performance processing unit 100 can read the song data of the selected song from the storage means 10 and perform karaoke based on the karaoke performance data included in that song data.

(Judgment Department)
The determination unit 200 determines the driver's level of concentration on driving based on the driver video data obtained by photographing the driver from the photography means, and determines whether the level of concentration satisfies the first predetermined condition.

The determination unit 200 outputs a start signal to the recording means 16 when, for example, the karaoke performance of a song begins. The recording means 16 starts recording the driver based on the start signal. The recording means 16 sequentially outputs the driver video data obtained from recording the driver to the determination unit 200. Meanwhile, the determination unit 200 outputs an end signal to the recording means 16 when the karaoke performance of the song ends. The recording means 16 ends recording the driver based on the end signal.

The driver's level of concentration while driving can be determined using known technologies, such as the Drive Chart (Omron Social Solutions Co., Ltd.) or the technology described in Japanese Patent Publication No. 2022-042239. The level of concentration can be expressed as a numerical value, for example, from 0.0 (low concentration) to 10.0 (high concentration).

The level of concentration is determined at least once at predetermined timings from the start to the end of the karaoke performance of the song. For example, the judgment unit 200 can determine the level of concentration one minute after the start of the karaoke performance. Furthermore, the judgment unit 200 can determine the level of concentration multiple times at predetermined intervals, such as every 15 seconds or every 30 seconds, after the start of the karaoke performance.

The first predetermined condition is a criterion for determining whether or not to perform an evaluation correction in the evaluation unit 300. The first predetermined condition is pre-set, for example, "concentration level is 9.0 or higher."

Specifically, after a karaoke version of a song begins, the recording device 16 records the driver and outputs the resulting driver video data to the determination unit 200. The determination unit 200 analyzes the driver video data acquired from the recording device 16 and obtains the driver's eye opening. The determination unit 200 then determines the driver's level of concentration based on the eye opening. For example, a high eye opening indicates that the driver is highly focused on driving. In this case, the concentration level determined by the determination unit 200 will be high.

The determination unit 200 determines whether the calculated concentration level satisfies the first predetermined condition and outputs the determination result to the evaluation unit 300. The determination unit 200 may also output the calculated concentration level along with the determination result to the evaluation unit 300.

Here, the determination unit 200 according to this embodiment determines the degree of concentration for each singing section of the song and determines whether the degree of concentration for each singing section satisfies the first predetermined condition.

Specifically, the determination unit 200 identifies singing sections based on section information included in the song data. The determination unit 200 analyzes the driver video data corresponding to the identified singing section (driver video data output from the filming means 16 during karaoke performance of the identified singing section) and determines the level of concentration. The determination unit 200 then determines, for each singing section, whether the determined level of concentration satisfies the first predetermined condition.

(Evaluation Department)
The evaluation unit 300 requests an evaluation of the karaoke singing performed by the driver.

The evaluation of karaoke singing can utilize known methods. For example, the evaluation unit 300 can evaluate the skill level of the karaoke singing by comparing the singing voice data corresponding to the singing voice accompanying the karaoke performance with reference data indicating the main melody of the song being played, and then indicating the skill level with a numerical value from 0 to 100, where 100 is the maximum score.

Furthermore, the evaluation unit 300 corrects the evaluation if it determines that the concentration level satisfies the first predetermined condition.

The evaluation correction is a process performed assuming that the driver may not be able to sing karaoke as well as usual because they are more focused on driving. In other words, the evaluation correction is performed in a way that makes the desired evaluation higher. The evaluation correction can be performed in various ways. For example, if the evaluation unit 300 determines that the level of concentration meets the first predetermined condition, it can correct the evaluation by adding a predetermined number (3 points, 5 points, etc.) to the desired evaluation or by multiplying it by a predetermined ratio (1.2 times, 1.5 times, etc.). Alternatively, the evaluation unit 300 may perform the evaluation correction only if the number of times the level of concentration meets the first predetermined condition is certain or more (5 times, 10 times, etc.). Or, the evaluation unit 300 may change the content of the correction according to the difference between the level of concentration and the first predetermined condition. If the difference between the concentration level and the first predetermined condition is large (for example, if the concentration level is 9.8 against the first predetermined condition of "concentration level of 9.0 or higher"), the evaluation unit 300 corrects the evaluation by adding 5 points to the obtained evaluation. On the other hand, if the difference between the concentration level and the first predetermined condition is small (for example, if the concentration level is 9.1 against the first predetermined condition of "concentration level of 9.0 or higher"), the evaluation unit 300 corrects the evaluation by adding 3 points to the obtained evaluation.

The evaluation unit 300 presents the corrected karaoke singing evaluation to the driver D, for example, by displaying it on the display screen of the display means 12.

Here, the evaluation unit 300 according to this embodiment corrects the evaluation for a given singing section if it determines that the concentration level obtained in that singing section satisfies the first predetermined condition.

The evaluation unit 300 refers to the judgment results for each singing section output from the judgment unit 200. If it is determined that the concentration level obtained in a certain singing section satisfies the first predetermined condition, the judgment unit 300 corrects the evaluation for that singing section.

For example, if the evaluation unit 300 determines that the concentration level obtained in a certain singing section satisfies the first predetermined condition, it corrects the evaluation by adding 5 points to the evaluation of that singing section. Here, suppose the evaluation for a certain singing section was "69.5". In this case, the evaluation unit 300 adds 5 points to that evaluation, correcting the evaluation of the singing section to "74.5".

As another example, if the evaluation unit 300 determines that the concentration level obtained in a certain singing section satisfies a first predetermined condition, it can correct the evaluation by compressing the difference between the evaluation of the singing section immediately preceding the current singing section and the evaluation of the current singing section to one-tenth of the original value. Here, suppose the evaluation of a certain singing section is "69.5" and the evaluation of the preceding singing section is "83.6". In this case, the evaluation unit 300 corrects the evaluation of the current singing section to "82.2" by compressing the evaluation difference of "14.1" to one-tenth of the original value.

Alternatively, if the evaluation unit 300 determines that the concentration level obtained in a certain singing section satisfies the first predetermined condition, it can correct the evaluation by performing linear interpolation using the evaluation of the singing section immediately preceding the singing section and the evaluation of the singing section immediately following the singing section. Here, suppose the evaluations for three consecutive singing sections corresponding to a certain singing section are "69.5," "67.2," and "72.3," respectively, with the evaluation of the preceding singing section being "83.6" and the evaluation of the following singing section being "79.6." In this case, the evaluation unit 300 corrects the evaluation "69.5" to "82.6," the evaluation "67.2" to "81.6," and the evaluation "72.3" to "80.6" by performing linear interpolation. Note that the preceding and following singing sections mentioned above are singing sections in which the concentration level was determined not to satisfy the first predetermined condition.

The evaluation unit 300 obtains evaluations for all singing sections and then calculates statistical values (such as the average value) for each singing section. The evaluation unit 300 presents these calculated statistical values to the driver D as an evaluation of the karaoke singing, for example, by displaying them on the display screen of the display means 12.

==Regarding the operation of the in-vehicle terminal==
Next, with reference to Figure 3, a specific example of the operation of the in-vehicle terminal M in this embodiment will be described. Figure 3 is a flowchart showing the operation of the in-vehicle terminal M. In this example, driver D, as shown in Figure 1, sings karaoke using the in-vehicle terminal M while driving vehicle C. A karaoke application is installed on the in-vehicle terminal M. In this example, the level of concentration and an evaluation of the karaoke singing are obtained for each singing section.

The performance processing unit 100 starts karaoke playback of song X selected by driver D of vehicle C (start of karaoke playback of song; step 10). Driver D sings along to the karaoke playback. The shooting means 16 shoots driver D and outputs the driver video data to the judgment unit 200.

The determination unit 200 determines the driver D's level of concentration on driving for each singing section of song X, based on the driver video data (determining the level of concentration for each singing section; step 11). The determination unit 200 then determines whether the determined level of concentration satisfies the first predetermined condition and outputs the determination result to the evaluation unit 300.

Meanwhile, the evaluation unit 300 obtains an evaluation of driver D's karaoke singing for each singing section of song X (evaluating karaoke singing for each singing section; step 12). Note that steps 11 and 12 may be performed in reverse order or simultaneously.

Here, if the determination unit 200 determines that the level of concentration in a certain singing section, as determined in step 11, satisfies the first predetermined condition (i.e., if the result is Y in step 13), the evaluation unit 300 corrects the evaluation for that singing section (correction of evaluation; step 14).

The in-vehicle terminal M repeatedly performs steps 11 through 14 until the evaluation of all vocal sections of song X is complete (if the result is Y in step 15).

After the karaoke performance ends, the evaluation unit 300 calculates statistical data for each singing section (including the corrected karaoke singing evaluation). The evaluation unit 300 displays the calculated statistical data on the display means 12, thereby presenting the evaluation of the driver D's karaoke singing of song X (presentation of karaoke singing evaluation; step 16).

Specifically, driver D operates the input means 13 of the in-vehicle terminal M to launch the karaoke application. The in-vehicle terminal M displays a song selection screen on the display means 12. Driver D selects the desired song X via the input means 13. The in-vehicle terminal M retrieves the song data for song X from the server device (not shown).

The performance processing unit 100 uses the karaoke performance function provided by the karaoke application to perform karaoke performance of song X based on the karaoke performance data included in the received song data. Driver D sings along to the karaoke performance. The in-vehicle terminal M outputs singing audio data corresponding to the singing voice of driver D to the evaluation unit 300.

Here, we assume that song X is a song with a BPM of 120 and in 4/4 time. Furthermore, song X consists of 12 performance sections (totaling 96 measures): "Intro (8 measures)", "Verse 1 A-section (8 measures)", "Verse 1 B-section (8 measures)", "Verse 1 Chorus (8 measures)", "Verse 2 A-section (8 measures)", "Verse 2 B-section (8 measures)", "Verse 2 Chorus (8 measures)", "Interlude (8 measures)", "Verse 3 A-section (8 measures)", "Verse 3 B-section (8 measures)", "Verse 3 Chorus (8 measures)", and "Outro (8 measures)". The total performance time is 3 minutes and 12 seconds.

In this example, one measure (2 seconds) is considered one singing section. Specifically, the first verse (A section) consists of singing sections S01-S08, the first verse (B section) consists of singing sections S09-S16, the first chorus consists of singing sections S17-S24, the second verse (A section) consists of singing sections S25-S32, the second verse (B section) consists of singing sections S33-S40, the second chorus consists of singing sections S41-S48, the third verse (A section) consists of singing sections S49-S56, the third verse (B section) consists of singing sections S57-S64, and the third chorus consists of singing sections S65-S72. The non-singing sections consist of a total of 24 measures, including the intro, interlude, and outro.

The recording means 16 begins recording driver D at the same time that the karaoke performance of song X by the performance processing unit 100 begins. The recording means 16 outputs the driver video data obtained from recording driver D to the determination unit 200.

The determination unit 200 calculates the concentration level for each singing section of song X, starting from section S01. The determination unit 200 then determines whether the calculated concentration level satisfies the first predetermined condition. The determination unit 200 outputs the determination result to the evaluation unit 300. In this example, it is assumed that the concentration level satisfies the first predetermined condition in singing sections S27 to S29.

Meanwhile, the evaluation unit 300 evaluates driver D's karaoke singing, starting from the singing section S01 of song X.

In this example, it is determined that the level of concentration in singing sections S27 to S29 satisfies the first predetermined condition. Therefore, the evaluation unit 300 corrects the evaluation for singing sections S27 to S29 by compressing the difference between the evaluation of the singing section S26 immediately preceding singing section S27 and the evaluations of each singing section S27 to S29 to one-tenth of the original value.

For example, suppose the evaluation of singing section S26 is "83.6", the evaluation of singing section S27 is "69.5", the evaluation of S28 is "67.2", and the evaluation of S29 is "72.3". In this case, the evaluation unit 300 corrects the evaluation of singing section S27 to "82.2" by compressing the difference of "14.1" between the evaluation of singing section S26 "83.6" and the evaluation of singing section S27 "69.5" to one-tenth. Similarly, the evaluation unit 300 corrects the evaluation of singing section S28 to "82.0" by compressing the difference of "16.4" between the evaluation of singing section S26 "83.6" and the evaluation of singing section S28 "67.2" to one-tenth. Furthermore, the evaluation unit 300 corrects the evaluation of singing section S29 to "82.5" by compressing the difference of "11.3" between the evaluation of singing section S26 ("83.6") and the evaluation of singing section S29 ("72.3") to one-tenth of that difference.

After the karaoke performance of song X is completed, the evaluation unit 300 calculates statistical values for each singing section S01 to S72 (corrected evaluations for singing sections S27 to S29). The evaluation unit 300 presents these calculated statistical values to driver D as an evaluation of their karaoke performance of song X by displaying them on the display screen of the display means 12.

As is clear from the above, the in-vehicle terminal M according to this embodiment is mounted on a vehicle C. The in-vehicle terminal M includes: a performance processing unit 100 that performs karaoke performance of a song selected by the driver D of the vehicle C; a determination unit 200 that determines the driver D's level of concentration on driving based on driver video data obtained by filming the driver D from the filming means 16, and determines whether the level of concentration satisfies a first predetermined condition; and an evaluation unit 300 that determines an evaluation of the karaoke performance by the driver D, and corrects the evaluation if it is determined that the level of concentration satisfies the first predetermined condition.

Generally, when a person is concentrating on driving a vehicle, they are less likely to sing karaoke well compared to singing karaoke in a karaoke bar or similar establishment. However, according to the in-vehicle terminal M of this embodiment, if the driver's level of concentration on driving meets the first predetermined condition, that is, if the driver is concentrating on driving, the evaluation can be corrected. Therefore, the driver can enjoy singing karaoke while concentrating on driving and obtain an appropriate evaluation. In other words, according to the in-vehicle terminal M of this embodiment, the evaluation of karaoke singing can be made taking into account that the person singing karaoke is driving a vehicle.

Furthermore, in the in-vehicle terminal M according to this embodiment, the determination unit 200 determines the level of concentration for each singing section of a song, and determines whether the level of concentration for each singing section satisfies a first predetermined condition. If the evaluation unit 300 determines that the level of concentration for a particular singing section satisfies the first predetermined condition, it corrects the evaluation for that singing section. Such an in-vehicle terminal M allows for a more detailed evaluation of karaoke singing according to the driver's level of concentration for each singing section.

<Variation 1>
In the example of the embodiment, when performing evaluation correction, driving information indicating the vehicle's specific driving conditions can be used.

==In-vehicle terminals==
As shown in Figure 4, the in-vehicle terminal M comprises a storage means 10, a communication means 11, a display means 12, an input means 13, a sound emission means 14, a sound collection means 15, a shooting means 16, a control means 17, and an acceleration sensor 18. Each component is connected to bus B via an interface (not shown).

[Accelerometer]
The acceleration sensor 18 is a sensor that detects acceleration acting on the vehicle C. The acceleration sensor 18 can utilize known sensors, such as a capacitive sensor that detects acceleration in one axis direction, or an analog three-axis acceleration sensor that detects acceleration in three mutually orthogonal axis directions. The acceleration sensor 18 outputs acceleration data corresponding to the detected acceleration to the acquisition unit 400 (described later).

[Method of photography]
In this modified example, the shooting means 16 includes an in-camera for shooting the driver and an out-camera for shooting the outside of the vehicle. For example, if a smartphone, which is an in-car terminal, is mounted on the dashboard, the in-camera can be used to shoot the driver, and the out-camera can be used to shoot the outside of the vehicle in the direction of travel.

[Control means]
In this embodiment, when the karaoke application is launched on the in-vehicle terminal M, the control means 17 functions as a performance processing unit 100, a determination unit 200, an evaluation unit 300, and an acquisition unit 400 (see Figure 4).

(Acquisition Department)
The acquisition unit 400 acquires driving information indicating a special driving state of vehicle C based on acceleration data acquired from the acceleration sensor 18 or external video data obtained by photographing the outside of the vehicle acquired from the shooting means 16.

The acquisition unit 400 outputs a start signal to the acceleration sensor 18 when the karaoke performance of the song begins. The acceleration sensor 18 starts detecting the acceleration of vehicle C based on the start signal. The acceleration sensor 18 sequentially outputs the detected acceleration data to the acquisition unit 400. On the other hand, the acquisition unit 400 outputs a stop signal to the acceleration sensor 18 when the karaoke performance of the song ends. The speed sensor 18 stops detecting the acceleration of vehicle C based on the stop signal. The acquisition unit 400 also outputs a start signal to the shooting means 16 (outside camera) when the karaoke performance of the song begins. The shooting means 16 starts shooting the outside of vehicle C based on the start signal. The shooting means 16 (outside camera) sequentially outputs the outside video data obtained by shooting the outside of the vehicle to the acquisition unit 400. On the other hand, the acquisition unit 400 outputs a stop signal to the shooting means 16 (outside camera) when the karaoke performance of the song ends. The shooting device 16 (outside camera) terminates shooting of the exterior of vehicle C based on the termination signal.

Special driving conditions refer to situations other than normal driving, such as "sudden acceleration," "sudden braking," "sharp turns," "lane changes," and "waiting for emergency vehicles." Driving information can be acquired by various methods. For example, the acquisition unit 400 can acquire special driving conditions such as "sudden acceleration" as driving information based on acceleration data acquired from the acceleration sensor 18, using the technology described in Japanese Patent Application Publication No. 2020-034751. Alternatively, the acquisition unit 400 can acquire special driving conditions such as "lane changes" as driving information based on external video data corresponding to the video captured by the shooting means 16 (outside camera) outside the vehicle C, using the technology described in Japanese Patent Application Publication No. 2022-021517. The acquisition unit 400 outputs the acquired driving information to the evaluation unit 300. Note that if special driving conditions cannot be obtained, the acquisition unit 400 does not output driving information to the evaluation unit 300.

In this case, as in the example of the first embodiment, when determining the level of concentration and evaluation for each singing section of a song, the acquisition unit 400 acquires driving information for each singing section.

(Evaluation Department)
The evaluation unit 300 in this embodiment performs corrections according to the driving information.

The evaluation can be corrected in accordance with driving information in various ways. For example, as described in the first embodiment, if the evaluation unit 300 determines that the concentration level satisfies a first predetermined condition, it corrects the evaluation by adding a predetermined numerical value (3 points, 5 points, etc.) to the obtained evaluation or by multiplying it by a predetermined ratio (1.2 times, 1.5 times, etc.). In this case, if driving information is output from the acquisition unit 400, the evaluation unit 300 can perform a correction that takes the driving information into account by increasing the value to be added or the ratio to be multiplied.

Furthermore, as described in the first embodiment, if the concentration level obtained in a certain singing section is determined to satisfy the first predetermined condition, the evaluation unit 300 can change the content of the correction when correcting the evaluation for that singing section, depending on whether or not driving information is available.

Specifically, the evaluation unit 300 refers to the judgment results for each singing section output from the determination unit 200 and the driving information output from the acquisition unit 400. If the concentration level obtained in a certain singing section is determined to satisfy the first predetermined condition, and driving information is output from the acquisition unit 400, the determination unit 300 corrects the evaluation for that singing section based on the first process. On the other hand, if the concentration level obtained in a certain singing section is determined to satisfy the first predetermined condition, but driving information is not output from the acquisition unit 400, the determination unit 300 corrects the evaluation for that singing section based on the second process.

For example, if the evaluation unit 300 determines that the concentration level obtained in a certain singing section satisfies the first predetermined condition, and if driving information is output from the acquisition unit 400, it corrects the evaluation by compressing the difference between the evaluation of the singing section immediately preceding the current singing section and the evaluation of the current singing section to one-tenth. Here, suppose the evaluation of a certain singing section is "69.5" and the evaluation of the preceding singing section is "83.6". In this case, the evaluation unit 300 corrects the evaluation of the current singing section to "82.2" by compressing the evaluation difference of "14.1" to one-tenth. The process of "compressing the difference between the evaluation of the singing section immediately preceding the current singing section and the evaluation of the current singing section to one-tenth" is an example of the first process.

On the other hand, if the evaluation unit 300 determines that the concentration level obtained in a certain singing section satisfies the first predetermined condition, but no driving information is output from the acquisition unit 400, it corrects the evaluation by compressing the difference between the evaluation of the singing section immediately preceding the singing section and the evaluation of the singing section in question to 5/10. Here, suppose the evaluation of a certain singing section is "69.5" and the evaluation of the singing section immediately preceding it is "83.6". In this case, the evaluation unit 300 corrects the evaluation of the singing section to "76.6" by compressing the difference of "14.1" to 5/10. The process of "compressing the difference between the evaluation of the singing section immediately preceding the singing section and the evaluation of the singing section in question to 5/10" is an example of the second process. Note that if driving information is output, it is assumed that the driver is more focused on driving. Therefore, the first process (when driving information is output) performs a correction that results in a higher evaluation compared to the second process (when driving information is not output).

Similar to the embodiment, the evaluation unit 300 calculates statistical values for each singing section and presents these calculated statistical values to the driver D as an evaluation of the karaoke singing, for example, by displaying them on the display screen of the display means 12.

As is clear from the above, the in-vehicle terminal M in this modified example has an acquisition unit 400 that acquires driving information indicating a special driving state of the vehicle C based on acceleration data acquired from the acceleration sensor 18 or external video data obtained by photographing the area outside the vehicle C acquired from the imaging means 16. The evaluation unit 300 in this modified example performs corrections according to the driving information. When the vehicle is in a special driving state such as "sudden acceleration" or "lane change," the driver is particularly focused on driving. According to the in-vehicle terminal M in this modified example, by performing corrections based on the driving information, it becomes possible to perform evaluations that better take into account the state of heightened concentration while driving.

<Modified Example 2>
In the example of the embodiment, it is necessary to avoid neglecting driving due to becoming too engrossed in singing karaoke.

(Judgment Department)
The determination unit 200 in this modified example can determine whether the concentration level satisfies a second predetermined condition.

The second predetermined condition is a criterion for determining whether or not to stop the karaoke performance in the performance processing unit 100. The second predetermined condition is pre-set, for example, "concentration level is less than 7.0".

The determination unit 200 determines whether the concentration level, obtained using the same method as in the embodiment, satisfies the second predetermined condition, and outputs the determination result to the performance processing unit 100.

Here, when determining the level of concentration for each singing section of a song, the determination unit 200 determines whether the level of concentration for each singing section satisfies the second predetermined condition.

(Performance Processing Department)
In this modified version, the performance processing unit 100 stops the karaoke performance of the song when it is determined that the level of concentration meets the second predetermined condition.

The performance processing unit 100 checks the judgment result output from the judgment unit 200. If the judgment result satisfies the second predetermined condition, the performance processing unit 100 stops the karaoke performance of the song. At this time, the performance processing unit 100 can display text such as "Karaoke performance will be stopped because it may interfere with driving" on the display means 12, or emit a similar message from the sound emission means 14.

As is clear from the above, in the in-vehicle terminal M according to this modified example, the determination unit 200 determines whether the level of concentration meets the second predetermined condition. If the performance processing unit 100 determines that the level of concentration meets the second predetermined condition, it stops the karaoke performance of the song. Such an in-vehicle terminal M can prevent the driver from becoming distracted while driving.

<Other>
The above embodiments are presented as examples and do not limit the scope of the invention. The above configurations can be combined as appropriate, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The above embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents.

100 Performance Processing Unit 200 Judgment Unit 300 Evaluation Unit 400 Acquisition Unit C Vehicle M In-vehicle Terminal

Claims (4)

An in-vehicle terminal installed in a vehicle,
A performance processing unit that performs karaoke-style performance of a song selected by the driver of the vehicle,
A determination unit determines the degree of concentration of the driver on driving based on driver video data obtained by filming the driver from the filming means, and determines whether the degree of concentration satisfies a first predetermined condition,
An evaluation unit for determining the evaluation of karaoke singing performed by the driver, and an evaluation unit for correcting the evaluation when it is determined that the level of concentration satisfies the first predetermined condition,
A typical in-vehicle terminal. The determination unit determines the degree of concentration for each singing section of the song, and determines whether the degree of concentration for each singing section satisfies the first predetermined condition.
The in-vehicle terminal according to claim 1, characterized in that the evaluation unit corrects the evaluation for a certain singing section if it determines that the concentration level obtained in a certain singing section satisfies the first predetermined condition. The system includes an acquisition unit that acquires driving information indicating a special driving state of the vehicle based on acceleration data acquired from an acceleration sensor or external video data obtained by photographing the outside of the vehicle from a camera,
The in-vehicle terminal according to claim 1, characterized in that the evaluation unit performs the correction according to the driving information. The determination unit determines whether the concentration level satisfies a second predetermined condition,
The in-vehicle terminal according to any one of claims 1 to 3, characterized in that the performance processing unit stops the karaoke performance of the song when it determines that the level of concentration satisfies the second predetermined condition.