JP2023121414A - Music selection device, music selection method, and program - Google Patents

Abstract

To provide a music selection device that enables appropriate music selection in accordance with a surrounding environment.SOLUTION: A terminal (music selection device) 200 according to the present disclosure includes: an environment information acquisition unit 210 that acquires environment information concerning an environment surrounding a user; a calculation unit 230 that calculates an activity level of a human flow based on a human pace and a density of people obtained from the environment information; and a music selection unit 240 that selects music based on the activity level of the human flow and attribute information indicating an attribute of music.SELECTED DRAWING: Figure 2

Description

The present disclosure relates to a music selection device, music selection method, and program.

2. Description of the Related Art In recent years, with the spread of subscription-type music distribution services, it has become possible to easily appreciate music of various genres. In addition, due to technological advances in smartphones, earphones, headphones, and the like, users can enjoy listening to music with a sense of presence in various situations regardless of time and place.

Against this background, techniques for automatically selecting music in various situations are known. For example, Japanese Patent Laid-Open No. 2003-100000 selects a selection value from the surrounding conditions of the own vehicle and uses it as a keyword, judges the degree of matching between the song attribute value of each parameter of the song data and the keyword, and grades the score. Disclosed is a music selection/reproduction device for selecting and reproducing data.

JP 2008-176851 A

When the device disclosed in Patent Document 1 is installed in a vehicle or the like, the parameters used for automatic music selection may be parameters that change little over time. However, it is difficult to apply the technology disclosed in Patent Literature 1 when the surrounding environment changes over time, such as when the user moves on foot.

An object of the present disclosure is to provide a music selection device, a music selection method, and a program capable of appropriately selecting music according to changes in the surrounding environment in view of the above-described problems.

The music selection device according to the present disclosure is
an environment information acquisition unit that acquires environment information about the environment around the user;
a calculation unit that calculates the degree of activity of the flow of people based on the speed of people and the density of people obtained from the environmental information;
a song selection unit that selects a song based on the degree of activity of the flow of people and attribute information indicating attributes of the song;

The song selection method according to the present disclosure is
an environment information acquisition step of acquiring environment information about the environment surrounding the user;
a calculation step of calculating the degree of activity of the flow of people based on the speed of people and the density of people obtained from the environmental information;
a song selection step of selecting a song based on the degree of activity of the flow of people and attribute information indicating attributes of the song.

The program according to the present disclosure is
an environment information acquisition step of acquiring environment information about the environment surrounding the user;
a calculation step of calculating the degree of activity of the flow of people based on the speed of people and the density of people obtained from the environmental information;
A music selection step of selecting music based on the degree of activity of the flow of people and attribute information indicating attributes of the music is executed by a computer.

The music selection device, music selection method, and program according to the present disclosure enable appropriate music selection according to changes in the surrounding environment.

1 is a schematic diagram of a music selection system according to an embodiment; FIG. 1 is a block diagram showing the configuration of a music selection system according to an embodiment; FIG. It is a figure which shows an example of the parameter information concerning embodiment. FIG. 4 is a diagram showing an example of attribute information for music selection according to the embodiment; FIG. It is a figure which shows an example of the music information concerning embodiment. 4 is a flowchart showing music selection processing performed by the terminal according to the embodiment;

Embodiments of the present disclosure are described in detail below with reference to the drawings. In the drawings, the same or corresponding elements are labeled with the same reference numerals. Duplicate explanations are omitted as necessary for clarity of explanation.

First, an overview of a music selection system 1000 according to this embodiment will be described with reference to FIG. FIG. 1 is a schematic diagram of a music selection system 1000 according to this embodiment. As shown in FIG. 1, the music selection system 1000 includes a playback device 100 and a terminal 200.

The playback device 100 and the terminal 200 are communicably connected via a communication network (not shown). The communication network may be configured using wireless standards such as Bluetooth® and Wi-Fi®, for example. Alternatively, the playback device 100 and the terminal 200 may be configured to perform wired communication.

The playback device 100 is a playback device that plays back music. The reproducing device 100 is, for example, a wireless earphone that receives an audio signal from the terminal 200 and reproduces music. The user can listen to the reproduced music by wearing the reproducing device 100 on his or her ear.

The playback device 100 also has a detection function of detecting environment information about the environment around the user. The environment information may include, for example, imaging information obtained by imaging the surroundings of the user, audio information of sounds emitted around the user, and the like. Therefore, the playback device 100 includes a small camera capable of imaging the user's surroundings, a microphone capable of detecting the user's surrounding sounds, and the like.

The playback device 100 transmits the detected environment information to the terminal 200 . The terminal 200 receives the environment information and performs predetermined music selection processing to select music according to the surrounding environment of the user. The terminal 200 transmits an audio signal for playing back the selected music to the playback device 100 . The reproduction device 100 receives the audio signal and reproduces the music selected on the terminal 200 . Thereby, the user can listen to the music selected on the terminal 200 .

The user can change the surrounding environment by moving by walking or the like. In the music selection system 1000 , the playback device 100 detects environment information at predetermined time intervals and transmits it to the terminal 200 . When the terminal 200 acquires the environment information from the playback device 100, the terminal 200 can select music again accordingly. With such a configuration, in the music selection system 1000, the terminal 200 that has acquired the information from the playback device 100 can appropriately select music according to environmental changes around the user.

Next, the configuration of the music selection system 1000 according to this embodiment will be described with reference to FIG. FIG. 2 is a block diagram showing the configuration of the music selection system 1000. As shown in FIG. As shown in FIG. 2 , the music selection system 1000 includes a playback device 100 and a terminal (music selection device) 200 . Note that the unidirectional arrows shown in FIG. 2 simply indicate the flow of information (data, signals, etc.) and do not exclude bidirectionality of information.

First, the configuration of the playback device 100 will be described. The playback device 100 is a playback device capable of receiving an audio signal from the terminal 200 and playing back music. The playback device 100 is, for example, earphones, headphones, or shoulder speakers. The reproducing device 100 is not limited to these devices, and various devices capable of reproducing music may be used. In this embodiment, the playback device 100 will be described as an earphone as shown in FIG. Although FIG. 1 shows an example in which the playback device 100 is worn on one ear, the playback device 100 may be worn on both ears. By wearing the reproducing device 100 on the ear, the user can listen to the music being reproduced while moving. A piece of music may be a piece of music with lyrics, or a piece of music without lyrics.

Each configuration of the playback device 100 will be described with reference to FIG. As shown in FIG. 2 , the playback device 100 includes an imaging section 110 , a sound collecting section 120 , a sensor section 130 and an output section 140 .

The imaging unit 110 is an imaging device that captures an image of the user's surroundings. The imaging unit 110 is, for example, a visible light camera. The imaging unit 110 may be an infrared camera or other imaging device. The imaging unit 110 is provided in the playback device 100 so as to image the front of the user, for example. Thereby, the imaging unit 110 can capture an image of a range equivalent to the field of view of the user according to the movement of the user. The imaging unit 110 is not limited to this, and may be configured to be capable of imaging the left-right direction or the rear of the user. The imaging unit 110 transmits a captured image obtained by imaging to the terminal 200 together with date and time information. The captured image may be a still image or a moving image. The imaging unit 110 may transmit the captured images at predetermined time intervals.

The sound collector 120 is a sound collector that detects sounds around the user. Sound collector 120 is, for example, a microphone. The sound collector 120 detects human voices around the user, sounds emitted by vehicles, sounds emitted from buildings such as shops, and the like. The sound collecting unit 120 transmits sound information of the detected sound to the terminal 200 . The sound collector 120 may transmit audio information at predetermined time intervals.

The sensor unit 130 is a detection device that detects user information about the user. User information may include, for example, the user's biometric information. The biometric information is, for example, the user's body temperature, heart rate, or blood pressure. The user information is not limited to this, and may include other biometric information. The sensor unit 130 transmits the detected biometric information to the terminal 200 . The sensor unit 130 may transmit biological information at predetermined time intervals. In this embodiment, the sensor unit 130 detects the user's heart rate as biological information and transmits the detection result to the terminal 200 .

Although FIG. 2 shows the sensor unit 130 inside the playback device 100 , the sensor unit 130 may be provided outside the playback device 100 . For example, the sensor unit 130 may be a wearable terminal capable of detecting biological information such as heart rate. Moreover, the sensor unit 130 may be configured to detect a plurality of different types of biological information. For example, the sensor unit 130 may detect heart rate and body temperature and transmit both detection results to the terminal 200 .

The output unit 140 is an output device that outputs music selected on the terminal 200 . The output unit 140 is, for example, a speaker. The output unit 140 reproduces the selected music according to the audio signal transmitted from the terminal 200 .

With continued reference to FIG. 2, the configuration of terminal 200 will be described. The terminal 200 is an information processing device that receives environment information and user information from the playback device 100 and performs predetermined music selection processing based on part or all of the information. The terminal 200 may be a smart phone, a mobile phone terminal, a tablet terminal, a PC (Personal Computer), or the like. Terminal 200 may be, for example, a wearable terminal such as a smartwatch. The terminal 200 selects music according to the surrounding environment of the user by performing predetermined music selection processing. The terminal 200 transmits an audio signal of the selected music to the reproduction device 100, and causes the reproduction device 100 to reproduce the selected music.

As shown in FIG. 2 , terminal 200 includes environment information acquisition section 210 , user information acquisition section 220 , calculation section 230 , music selection section 240 , input/output section 270 , imaging section 280 and storage section 290 .

The environment information acquisition unit 210 acquires environment information about the surrounding environment of the user. Environmental information may include imaging information and audio information. Here, imaging information is information including a captured image acquired by capturing an image of the user's surroundings. Also, the voice information is voice information acquired by detecting voices uttered around the user. The environment information acquisition unit 210 acquires imaging information including the captured image captured by the imaging unit 110 from the playback device 100 . Also, the environment information acquisition unit 210 acquires the audio information acquired by the sound collection unit 120 from the playback device 100 .

Note that the environment information acquisition unit 210 may acquire a captured image acquired by the imaging unit 280 included in the terminal 200 in addition to acquiring the captured image acquired by the imaging unit 110 as described above. For example, the environment information acquisition unit 210 determines whether or not a captured image can be acquired from the imaging unit 110. If it is determined that a captured image can be acquired from the imaging unit 110, the environment information acquisition unit 210 converts the captured image into environmental information as described above. to get as When it is determined that the captured image cannot be acquired from the imaging unit 110, the environment information acquisition unit 210 switches the acquisition destination of the captured image from the imaging unit 110 to the imaging unit 280, and stores the captured image acquired by the imaging unit 280 as the environment information. to get as

For example, the environment information acquiring unit 210 may determine that the captured image cannot be acquired from the imaging unit 110 when the imaging unit 110 is blocked by a shield such as the user's hair. The environment information acquisition unit 210 compares, for example, the average luminance value of each pixel in the captured image acquired by the imaging unit 110 with a predetermined threshold. Based on the comparison result, the environment information acquisition unit 210 determines that the imaging unit 110 is in a shielded state and cannot acquire a captured image from the imaging unit 110 . The shielding object is not limited to the user's hair, and can be assumed to be, for example, a hat or an umbrella. Not limited to this, the environment information acquisition section 210 may determine whether or not the captured image from the imaging section 110 can be acquired using other determination conditions.

In this way, by switching the acquisition destination of the captured image to the imaging unit 280 when the captured image cannot be acquired from the imaging unit 110, the environment information acquisition unit 210 can stably acquire the captured image as the environment information. can be done. Similarly, the environment information acquisition unit 210 determines whether or not the audio information from the sound collection unit 120 can be acquired, and depending on the determination result, sets the acquisition destination of the audio information to the sound collection provided in the terminal 200. (not shown).

The user information acquisition unit 220 acquires user information about the user. User information may include, for example, the user's biometric information, browsing information, or mood information. The biological information is the user's heart rate detected by the sensor unit 130 and the like. The user information acquisition unit 220 receives the biological information detected by the sensor unit 130 from the playback device 100 and acquires it as user information.

The browsing information is information such as characters and images that the user is browsing. Browsing information may include information related to the user's mood. The browsing information is, for example, display information included in the display screen displayed on the input/output unit 270 . For example, the displayed information may include information about areas that the user likes or dislikes. The field can be anything, such as food, sports, or movies. The user information acquisition unit 220 acquires, for example, character information and image information included in display information as user information. In addition, the user information acquisition section 220 may acquire browsing information acquired from an image captured by the imaging section 110 as user information. The user information acquisition unit 220 may, for example, acquire viewing information from the content of posters, digital signage, and the like that the user is viewing.

Mood information is information indicating the user's mood that the user himself/herself is feeling. Mood information may be represented by, for example, "Low" or "High". For example, if the user's mood is "calm," "relaxed," or "sad," the mood information is represented as "Low." Also, for example, when the user's mood is "excited", "active", or "pleasant", the mood information is represented by "High". The mood information may indicate the degree of mood, such as "slightly low" or "slightly high".

The user information acquisition unit 220 displays, for example, a selection screen for receiving input of the user's mood information on the input/output unit 270 . The selection screen may include, for example, a "Low" button and a "High" button. The user information acquisition unit 220 causes the input/output unit 270 to display a message such as "Please select your current mood", receives the user's response, and acquires mood information. Although two options of "Low" and "High" are used here, three or more options may be provided. Also, the mood information may be digitized, or may be represented by expressions other than those described above.

The calculator 230 uses the environment information acquired by the environment information acquirer 210 and the user information acquired by the user information acquirer 220 to calculate parameter values for a plurality of parameters related to music selection. A plurality of parameters related to music selection are pre-stored in the storage unit 290 as parameter information 291 .

FIG. 3 is a diagram showing an example of the parameter information 291. As shown in FIG. For example, the parameter information 291 is information that associates parameter IDs, parameter names, parameter values, scores, and music selection attribute names. A parameter ID is information for identifying a parameter. The parameter name is information indicating the name of the parameter. Parameter values are values that can be selected for each parameter. As shown, multiple parameter values can be selected for a parameter. The score is the score associated with each parameter value. Scores are used to specify music selection attributes for making music selections. The attribute name for music selection is information indicating the name of the attribute for music selection.

As shown in FIG. 3, the parameter information 291 includes, as parameters, P1 "Atmosphere of people", P2 "Atmosphere of building", P3 "Speed of people", P4 "Concentration of people", P5 "Concentration of building and P6 "mood information". In the following, each parameter may be indicated only by symbols P1 to P6.

The calculator 230 calculates the parameter values of P1 to P5 based on the environmental information. Further, the calculation unit 230 calculates the parameter value of P6 based on the user information. Here, the calculation method of each parameter value in the calculation unit 230 will be described together with the contents of each parameter.

Four parameter values of "casual", "business", "Japanese style", and "western style" are set for P1 "people's atmosphere", and the score corresponding to each parameter value is 1 to 4 points. Also, in the case of "Other" which does not correspond to any of these parameter values, the corresponding score is 0 points. The calculation unit 230 calculates parameter values using well-known machine learning or the like based on the environmental information.

In addition, the same parameter values and scores as those of P1 are set for P2 "Atmosphere of building". Calculation unit 230 calculates parameter values based on environmental information using well-known machine learning or the like, similar to P1.

Three parameter values of "slow", "normal", and "fast" are set for P3 "person's speed", and the score corresponding to each parameter value is 1 to 3 points. For example, the calculator 230 obtains the speed of the person based on the motion vector of the person detected from the captured image. Specifically, first, the calculation unit 230 recognizes a person included in the captured image using a well-known image recognition technique or the like. Next, the calculation unit 230 obtains the difference between the motion vectors of the person at predetermined time intervals, and obtains the degree of change in the motion vector from the difference. Thereby, the calculation unit 230 calculates the speed of the person recognized in the captured image. When a plurality of people are recognized in the captured image, the calculator 230 performs similar processing on each person to obtain the velocities of the plurality of people in the captured image.

The calculation unit 230 calculates the parameter value of P3, for example, by comparing the determined speed of the person with a threshold value. For example, the calculation unit 230 compares the calculated speed of the person with two thresholds to calculate the parameter value. For example, the calculation unit 230 determines “fast” when the speed of the person obtained is equal to or greater than the first threshold, “slow” when less than the second threshold, and “normal” when none of the above applies. to calculate the parameter value. The calculation unit 230 is not limited to this, and may calculate the parameter value using well-known machine learning or the like.

Three parameter values are set for P4 “People Density”: “Scattered”, “Normal”, and “Dense”, and points corresponding to each parameter value are 1 to 3. It is a point. The calculator 230 obtains the density of people based on at least one of the imaging information and the audio information. For example, when obtaining the density of people based on a captured image, the calculation unit 230 recognizes people included in the captured image using image recognition technology or the like. The calculation unit 230 obtains the density of people based on the number of recognized people.

The calculation unit 230 calculates the parameter value of P4, for example, by comparing the number of recognized people with a threshold. For example, the calculator 230 compares the number of recognized people with two thresholds to calculate the parameter value. For example, the calculation unit 230 is “crowded” when the number of recognized people is equal to or greater than the first threshold, “scattered” when the number is less than the second threshold, and Calculate a parameter value such as "Normal". The calculation unit 230 is not limited to this, and may calculate the parameter value using well-known machine learning or the like.

Further, the calculation unit 230 may obtain the density of people using voice information. The calculator 230 can obtain the density of people using a well-known speech recognition technique. For example, the calculation unit 230 obtains the sum of the strengths of voice information in a frequency band with many conversation sounds, crowd sounds, noises, etc., and obtains the density of people around the user according to the magnitude of the obtained sum. You can The calculator 230 may calculate the parameter value by comparison with the threshold in the same manner as described above. Further, the calculation unit 230 may calculate parameter values using well-known machine learning or the like.

Note that the calculation unit 230 may obtain the density of people using both the imaging information and the audio information. As a result, the calculation unit 230 can more accurately obtain the density of surrounding people.

The same parameter values and scores as P4 are set for P5 “building density”. The calculation unit 230 may calculate the parameter value of P5 by, for example, using the area of the sky in the captured image acquired by the environment information acquisition unit 210 to obtain the proportion of buildings in the captured image. Alternatively, the calculation unit 230 may calculate parameter values using well-known machine learning or the like.

Two parameter values, "Low" and "High", are set for P6 "mood information", and the score corresponding to each parameter value is 1 to 2 points. The calculation unit 230 calculates the parameter value of P6 using the user's biological information, browsing information, or mood information acquired as user information. The calculation unit 230 may use a plurality of information among these as user information. The calculation unit 230 may calculate parameter values using well-known machine learning or the like.

In this embodiment, it is assumed that a trained model for calculating each parameter value is generated in advance by machine learning. For machine learning, for example, a well-known machine learning method such as deep learning may be used. When environment information (for example, imaging information) is acquired by the environment information acquisition unit 210, the calculation unit 230 can calculate parameter values of P1 to P5 using a pre-generated trained model. Similarly, when the user information acquisition unit 220 acquires user information (eg, biological information), the calculation unit 230 can calculate the parameter value of P6 using a pre-generated trained model.

Also, as shown in FIG. 3, each parameter is associated with a music selection attribute name. The attribute name for music selection indicates the name of the attribute for music selection used for selecting music. In this embodiment, three music selection attributes are set: "genre", "tempo", and "key". Here, the correspondence between each parameter and the music selection attribute will be briefly described.

P1 "Atmosphere of people" and P2 "Atmosphere of building" are associated with "genre" related to the atmosphere of music. Also, P3 "People's Speed" is associated with "Tempo" related to the speed of music.

Also, P4 "People density" and P5 "Building density" are associated with "Tempo". For example, when there are many people and buildings around, it is assumed that the user feels busy and busy, and when there are few people and buildings, it is assumed that the user feels lonely and quiet. This makes it easier for the music selection unit 240 to select music, for example, up-tempo music when the density of people and buildings is high, and ballad music when the density is low.

P6 "mood information" is associated with "tempo" and "key". This is because it is assumed that the "tempo" is related to the user's mood and the speed of music suitable for this. Also, as for the "key", it is assumed that the user's mood is related to the key height of the music suitable for this mood. For example, it is assumed that high-pitched music has a high frequency, is likely to stimulate the user, and can further amplify the user's uplifted mood. Therefore, when the “mood information” is “High”, music with a high key is more likely to be selected in the music selection unit 240 . In addition, low-pitched music has a low frequency and is likely to give sleepiness and a relaxed feeling, and is assumed to be able to further stabilize the calm mood of the user. Therefore, when the “mood information” is “Low”, music with a low key is more likely to be selected in the music selection unit 240 .

Note that the parameter information 291 shown in FIG. 3 is just an example, and the correspondence between each parameter and the music selection attribute is not limited to that shown in the figure. For example, P1 "human atmosphere" is associated with "genre", but may be associated with "tempo" or "key". Also, P1 may be associated with two or more of these. The same is true for other parameters.

The calculation unit 230 totals the scores corresponding to the parameters P1 to P6 for each attribute for music selection. Here, if the scores corresponding to the parameters P1 to P6 are expressed as S1 to S6, respectively, the score for P1 "Atmosphere of people" is S1, the score for P2 "Atmosphere of building" is S2, and the score for P3 "People's speed" is S1. The score for P4 is S3, the score for P4 "People density" is S4, the score for P5 "Building density" is S5, and the score for P6 "Mood information" is S6.

The score corresponding to each attribute for music selection is represented by the following formula. The calculation unit 230 calculates the following formulas (1) to (3) to calculate the total score corresponding to each music selection attribute.
“Genre”=S1+S2 (1)
"Tempo" = S3 + S4 + S5 + S6 (2)
"Key" = S6 (3)

The calculation unit 230 refers to the music selection attribute information 292 stored in the storage unit 290, and acquires the music selection attribute value corresponding to each music selection attribute based on the total score calculated by the above calculation.

FIG. 4 is a diagram showing an example of the music selection attribute information 292. As shown in FIG. The music selection attribute information 292 is, for example, information in which a music selection ID, a music selection attribute name, a total score, and a music selection attribute value are associated with each other. The calculation unit 230 refers to the music selection attribute information 292 and acquires the music selection attribute values of the “genre”, “tempo”, and “key” attributes. For example, if the total score for "genre" is 2, the calculator 230 acquires "J-POP, K-POP" as the attribute value for music selection. Further, for example, when the total score of "tempo" is 6 points, the calculation unit 230 acquires "mid ballad" as the music selection attribute value. Further, for example, when the total score of "key" is 1 point, the calculation unit 230 acquires the key "low song" as the attribute value for music selection.

In this way, the calculation unit 230 can acquire the music selection attribute values for selecting music in the music selection unit 240 for each attribute of “genre”, “tempo”, and “key”.

In the above description, the calculation unit 230 calculates parameter values for all the parameters P1 to P6 shown in FIG. 3, and calculates the attribute values for music selection based on the calculation results, but the present invention is not limited to this. . For example, the calculator 230 may calculate the music selection attribute value using only some of the parameters P1 to P6.

For example, the calculation unit 230 may calculate only parameters P3 “speed of people” and P4 “density of people” shown in FIG. By using P3 and P4 as parameters, the calculation unit 230 can calculate the activity level of the flow of people in the surrounding environment of the user. As a result, the music selection unit 240 can select music according to the activity level of the flow of people. In the following description, P3 and P4 may be collectively expressed as P10 "the activity level of the flow of people".

Returning to FIG. 2, the description is continued. The music selection unit 240 selects music from the music information 293 stored in the storage unit 290 based on the music selection attribute value acquired by the calculation unit 230 . The song information 293 is information about songs that can be selected by the song selection unit 240 .

FIG. 5 is a diagram showing an example of the music information 293. As shown in FIG. The song information 293 is information in which, for example, song IDs, song titles, artist names, song data, and attribute information are associated with each other. A song ID is information for identifying a song. The song title is information indicating the title of the song. The artist name is information indicating the name of the artist performing the music. The music data is information indicating the sound source data of the music.

Attribute information is information indicating attributes of a song. Attribute information may include, for example, "genre", "tempo", and "key" information. The attribute information corresponds to the contents of the music selection attribute information 292 described above. "Genre" is information indicating the genre of a song, such as J-POP, K-POP, enka, and classical music. "Tempo" is information indicating the tempo of a song, such as ballad, mid-ballad, and up-tempo. "Key" is information about the height of the key of the music.

In this embodiment, the music information 293 is described as being stored in the storage unit 290 in advance, but the present invention is not limited to this. The music information 293 may be stored in a predetermined server provided outside the terminal 200 .

The music selection unit 240 specifies the music selection attribute value acquired by the calculation unit 230 as a music selection condition. The music selection unit 240 refers to the music information 293 and determines whether or not there is a music that matches the specified music selection condition. For example, in the example of the total score described above, the music selection unit 240 selects "J-POP, K-POP" as the "genre", "mid ballad" as the "tempo", and "low song" as the "key". is specified as a music selection condition. The music selection unit 240 determines whether or not the music information 293 contains music that matches the music selection condition.

When determining that there is a song that matches the song selection condition, the song selection unit 240 identifies the song as a song selection candidate. The music selection unit 240 may identify multiple music selection candidates. Also, the music selection section 240 may specify, as a music selection candidate, a piece of music whose degree of matching with the music selection condition is equal to or greater than a predetermined value. Therefore, the music selection section 240 may select music that does not completely match the music selection condition as a candidate for music selection.

The music selection unit 240 selects a music piece to be reproduced in the reproduction device 100 when there are a plurality of music selection candidates. For example, the music selection unit 240 may select the music that has the highest degree of matching with the music selection condition as the music to be reproduced. The music selection unit 240 transmits the audio signal of the music to be played back to the playback device 100 so that the playback device 100 can play back the selected playback song. As a result, the music selected by the terminal 200 is played back on the playback device 100 .

Also, the music selection unit 240 may monitor changes in the user's surrounding environment and change the music being played according to the change in the user's surrounding environment. For example, the calculation unit 230 determines whether or not a song is being played, and if the song is being played, a parameter indicating the surrounding environment of the user after the start of playback of the song (for example, P10 “People flow activity degree”) is newly calculated. The music selection unit 240 compares the attribute information for music selection obtained from the newly calculated parameter values with the attribute information of the music being reproduced. If the degree of matching between the two is less than the predetermined value, the music selection unit 240 terminates the music being reproduced at a predetermined timing, selects a new music according to the current surrounding environment of the user, and reproduces it on the reproduction device 100. Let

The predetermined timing may be, for example, the timing at which the piece of music being reproduced ends, or the timing at which a specific performance section ends. The specific performance section is, for example, A melody, B melody, chorus, or the like. Not limited to these, good break timings may be appropriately set in order to switch songs to be played back.

For example, assume that the playback device 100 is playing a song a. The calculation unit 230 newly calculates the parameter value of P10 at the present time after the start of reproduction of the music piece a. The calculation unit 230 totals the points corresponding to the newly calculated parameter values of P10 to calculate the total points. The calculation unit 230 newly acquires an attribute value for music selection (attribute information for music selection) based on the total score.

The music selection unit 240 compares the newly acquired attribute value for music selection with the attribute value (attribute information) of the music piece a while the music piece a is being reproduced. The music selection unit 240 determines the degree of matching between the two, and if the degree of matching is less than a predetermined value, ends the music piece a being played at a predetermined timing. If the degree of matching between the two is equal to or higher than the predetermined value, the music selection unit 240 does not perform any particular processing and continues the reproduction of the music piece a. When ending the reproduction of the music piece a, the music selection unit 240 selects a new music piece b based on the newly acquired attribute value for music selection, and starts the reproduction of the music piece b when the music piece a ends.

By doing so, the terminal 200 can newly select music corresponding to the surrounding environment information and cause the reproduction device 100 to reproduce the music when the music corresponding to the surrounding environment of the user is not reproduced. Although the P10 parameter is used here, other parameters may be used.

Returning to FIG. 2, the description is continued. The input/output unit 270 is an input device that receives input from the user. The input/output unit 270 receives input of mood information from the user, for example. The input/output unit 270 is an output device for outputting characters, images, and the like. The input/output unit 270 may be, for example, a touch panel that can be operated by being touched by a user's finger or the like. The imaging unit 280 is an imaging device capable of imaging the surroundings of the terminal 200 . The imaging unit 280 is, for example, a visible light camera, like the imaging unit 110 .

The storage unit 290 is a storage device in which programs for realizing each function of the terminal 200 are stored. The storage unit 290 also stores the above-described parameter information 291 , music selection attribute information 292 , and music information 293 . In addition, although the storage unit 290 is shown inside the terminal 200 in FIG. 2, the storage unit 290 may be provided on a predetermined server connected to the terminal 200 via a communication network. The terminal 200 can realize the music selection process described above by communicating with the server via the network.

Note that the configuration shown in FIG. 2 is merely an example, and the music selection system 1000 may be configured using a device or the like in which multiple configurations are integrated. For example, the functions of the playback device 100 and the terminal 200 may be integrated into the same device. For example, the playback device 100 may have each function of the terminal 200 . By doing so, the user can select and reproduce music according to the surrounding environment by simply wearing the reproduction device 100 without carrying the terminal 200 .

Also, for example, each functional unit in the playback device 100 and the terminal 200 may perform distributed processing using a plurality of devices. As described above, storage unit 290 may be provided in an external server. The same applies to functional units other than the storage unit 290 . Further, for example, a device other than the terminal owned by the user may include each functional unit of the terminal 200 . By doing so, even if the user does not carry the terminal 200, a similar effect can be obtained.

Next, processing performed by the terminal 200 will be described with reference to FIG. FIG. 6 is a flowchart showing music selection processing performed by the terminal 200 . It is assumed that the reproducing device 100 constantly detects environmental information around the walking user and transmits the environmental information to the terminal 200 . The environmental information includes imaging information and audio information. It is also assumed that the reproducing device 100 detects user information and constantly transmits the user information to the terminal 200 .

First, the environment information acquisition unit 210 acquires environment information transmitted from the playback device 100 (S101). Next, the user information acquisition unit 220 acquires user information transmitted from the playback device 100 (S102). Note that the order of steps S101 and S102 may be reversed.

Subsequently, the calculation unit 230 calculates parameter values corresponding to each parameter based on the environment information and the user information (S103). The calculation unit 230 may calculate parameter values from the environment information and the user information using a well-known machine learning method. For example, the calculation unit 230 calculates P10 “People flow activity level” from P3 “People speed” and P4 “People density” shown in FIG. 3, and calculates a parameter value corresponding to P10.

Subsequently, the calculator 230 calculates the score of each parameter based on the parameter value (S104). The calculation unit 230 adds up the points of each parameter to calculate the total points for each attribute for music selection, and obtains the attribute value for music selection from the total points (S105). Then, the music selection unit 240 refers to the music information 293, and selects music using the music selection attribute value as a music selection condition (S106). Specifically, the music selection unit 240 determines whether or not there is a music piece in the music information 293 that matches the music selection condition.

The music selection unit 240 transmits an audio signal corresponding to the selected music to the reproduction device 100 to reproduce the selected music (S107). With such music selection processing, the music selection system 1000 can appropriately select music according to the surrounding environment of the user and reproduce the music.

Although not shown in FIG. 6, the music selection unit 240 monitors whether or not the music being played corresponds to the surrounding environment of the user, and always selects music suitable for the user's surrounding environment. You may make it reproduce|regenerate. For example, when the music is being reproduced, the calculation unit 230 newly calculates P10 after the music is started to be reproduced, and acquires a new attribute value for music selection. The music selection unit 240 compares the newly acquired attribute value for music selection with the attribute value of the music being played. If the degree of matching between the two is less than the predetermined value, the music selection unit 240 ends the music being reproduced at a predetermined timing, and causes the reproduction device 100 to reproduce the newly selected music.

As described above, in the music selection system 1000 according to this embodiment, in the terminal 200, the environment information acquisition section 210 and the user information acquisition section 220 acquire environment information and user information, respectively. The environmental information may include at least imaging information out of imaging information and audio information. The calculation unit 230 calculates various parameters as shown in FIG. 3 and the parameter values of each parameter based on the environment information and the user information.

For example, the calculator 230 obtains the speed of the person based on the motion vector of the person detected from the imaging information. Also, the calculation unit 230 obtains the density of people based on at least one of the imaging information and the audio information. The calculator 230 calculates the degree of activity of the flow of people based on the speed of people and the density of people. The calculation unit 230 acquires the music selection attribute value used for music selection from the total score corresponding to the parameter value corresponding to the degree of activity of the flow of people. The calculation unit 230 acquires the attribute values for music selection using some or all of the atmosphere of surrounding people, the atmosphere of the building, the density of the building, and the user's mood information, in addition to the activity level of the flow of people. good too.

The music selection unit 240 uses the music selection attribute value acquired by the calculation unit 230 as a music selection condition, and selects music that matches the music selection condition. The music selection unit 240 transmits an audio signal corresponding to the selected music to the reproduction device 100 and causes the reproduction device 100 to reproduce the music. With such a configuration, the terminal 200 can automatically select an appropriate song according to the user's surrounding environment and the user's mood, and allow the playback device 100 to play the selected song.

In addition, the terminal 200 can select a new song according to the surrounding environment of the user during playback of the song, terminate the song being played at a predetermined timing, and play back the newly selected song. . As a result, the music selection system 1000 can realize automatic music selection corresponding to the details of changes in the surrounding environment.

<Hardware configuration example>
Each functional configuration unit of the playback device 100 and the terminal 200 described above may be implemented by hardware (eg, hardwired electronic circuit, etc.) that implements each functional configuration unit, or may be implemented by combining hardware and software. It may be implemented by a combination (eg, a combination of an electronic circuit and a program that controls it). For example, the present disclosure can also implement arbitrary processing by causing a CPU (Central Processing Unit) to execute a computer program.

A program includes instructions (or software code) that, when read into a computer, cause the computer to perform one or more of the functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or tangible storage medium. By way of example, and not limitation, computer readable media or tangible storage media may include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drives (SSD) or other memory technology, CDs -ROM, digital versatile disc (DVD), Blu-ray disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disc storage or other magnetic storage device. The program may be transmitted on a transitory computer-readable medium or communication medium. By way of example, and not limitation, transitory computer readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

It should be noted that the present disclosure is not limited to the above embodiments, and can be modified as appropriate without departing from the spirit of the present disclosure. For example, in the above description, an up-tempo song is set to correspond to a high degree of activity in the flow of people, but conversely, a ballad song may correspond. Also, the parameters used for song selection and the points corresponding to each parameter may be appropriately set according to the user's preference.

100 playback device 110 imaging unit 120 sound collection unit 130 sensor unit 140 output unit 200 terminal (music selection device)
210 environment information acquisition unit 220 user information acquisition unit 230 calculation unit 240 music selection unit 270 input/output unit 280 imaging unit 290 storage unit 291 parameter information 292 attribute information for music selection 293 music information 1000 music selection system

Claims (5)

an environment information acquisition unit that acquires environment information about the environment around the user;
a calculation unit that calculates the degree of activity of the flow of people based on the speed of people and the density of people obtained from the environmental information;
A music selection device, comprising: a music selection unit that selects music based on the degree of activity of the flow of people and attribute information indicating attributes of the music. the environment information includes at least the imaging information of imaging information and audio information;
The speed of the person is obtained based on a motion vector of the person detected from the imaging information,
The music selection device according to claim 1, wherein the density of people is obtained based on at least one of the imaging information and the audio information. If the song is being played,
The calculation unit newly calculates the degree of activity of the flow of people after the start of reproduction of the music,
The music selection unit compares the attribute information for music selection obtained from the newly calculated degree of activity of the flow of people with the attribute information of the song being played. 3. The music selection device according to claim 1, wherein the music being reproduced is terminated at a predetermined timing, and a music corresponding to the newly calculated degree of activity of the flow of people is selected and reproduced. an environment information acquisition step of acquiring environment information about the environment surrounding the user;
a calculation step of calculating the degree of activity of the flow of people based on the speed of people and the density of people obtained from the environmental information;
a song selection step of selecting a song based on the degree of activity of the flow of people and attribute information indicating an attribute of the song. an environment information acquisition step of acquiring environment information about the environment surrounding the user;
a calculation step of calculating the degree of activity of the flow of people based on the speed of people and the density of people obtained from the environmental information;
A program for causing a computer to execute a song selection step of selecting a song based on the degree of activity of the flow of people and attribute information indicating attributes of the song.

Images