阅读说明：本技术 一种音乐推荐播放方法以及车载资讯娱乐系统 (music recommendation playing method and vehicle-mounted infotainment system ) 是由 邹振盛 于 2018-05-31 设计创作，主要内容包括：本发明涉及一种音乐推荐播放方法以及车载资讯娱乐系统。该方法包括：第一获取步骤,获取用户的声音及表情；第一标定步骤,基于所述第一获取步骤获取到用户的声音以及表情给用户的情绪进行标定作为第一情绪标定值；推荐步骤,基于所述第一情绪标定值以规定的推荐方式推荐与所述情绪标定值相对应类型的音乐。根据本发明的音乐推荐播放方法,不需要用户手动输入或者调整,能够自动推荐适合用户情绪的音乐,而且,能够自动根据用户的表情、声音的反馈来学习调整并以改善用户情绪为目的。(the invention relates to a music recommendation playing method and a vehicle-mounted infotainment system. The method comprises the following steps: a first acquisition step of acquiring the voice and expression of a user; a first calibration step of calibrating the voice and the emotion of the user, which are acquired based on the first acquisition step, as a first emotion calibration value; recommending, namely recommending the music of the type corresponding to the emotion calibration value in a specified recommending mode based on the first emotion calibration value. According to the music recommending and playing method, manual input or adjustment of a user is not needed, music suitable for the emotion of the user can be automatically recommended, and the music recommending and playing method can automatically learn and adjust according to the feedback of the expression and the sound of the user and aims to improve the emotion of the user.)

1. a music recommendation playing method is characterized by comprising the following steps:

a first acquisition step of acquiring the voice and expression of a user;

A first calibration step of calibrating the voice and the emotion of the user, which are acquired based on the first acquisition step, as a first emotion calibration value; and

Recommending, namely recommending the music of the type corresponding to the emotion calibration value in a specified recommending mode based on the first emotion calibration value.

2. the music recommendation playing method according to claim 1,

Further comprising, after the recommending step:

A second obtaining step of obtaining the sound and expression of the user after the music recommended in the recommending step is played;

A second calibration step of calibrating the emotion of the user based on the voice and the expression of the user acquired in the second acquisition step to serve as a second emotion calibration value; and

Recommending a self-learning step, wherein if the second emotion calibration value is superior to the first emotion calibration value, the recommending step is considered to be effective, and if the second emotion calibration value is not superior to the first emotion calibration value, the self-learning is carried out to adjust a recommending mode.

3. the music recommendation playing method according to claim 1,

The prescribed way of recommending is to adapt the recommendation to the type of music so that the user's mood tends to calm from excitement or so that it tends to be pleasurable from sadness.

4. The music recommendation playing method according to claim 3,

in the recommending step, in the case where the first emotion calibration value is indicative of an excited emotion, recommending music that makes the excited emotion calm; and recommending music which enables the sad emotion to be joyful in the case that the first emotion calibration value is the sad emotion.

5. the music recommendation playback method according to claim 1, further comprising:

And a user habit self-learning step of recording and self-learning music manually selected by the user corresponding to the first emotion calibration value, and modifying the specified recommendation mode according to the self-learning result.

6. A vehicle-mounted infotainment system is characterized in that,

A microphone for acquiring a user's voice;

The camera is used for acquiring the expression of the user;

the first calibration module is used for calibrating the emotion of the user obtained by the microphone and the camera based on the voice and the expression of the user to serve as a first emotion calibration value;

The recommending module is used for recommending the music of the type corresponding to the emotion calibration in a specified recommending mode based on the first emotion calibration value; and

and the playing module is used for playing the recommended music or playing the music selected by the user.

7. The in-vehicle infotainment system according to claim 6, further comprising:

The second calibration module is used for calibrating the emotion of the user based on the voice and the expression of the user acquired by the camera and the microphone after the recommended music is played to serve as a second emotion calibration value;

And the recommendation self-learning module is used for considering the recommendation of the recommendation module to be effective if the second emotion calibration value is superior to the first emotion calibration value, and performing self-learning to adjust the recommendation mode if the second emotion calibration value is not superior to the first emotion calibration value.

8. The infotainment system according to claim 6, characterized in that,

The prescribed way of recommending is to adapt the recommendation to the type of music so that the user's mood tends to calm from excitement or so that it tends to be pleasurable from sadness.

9. the infotainment system according to claim 8, characterized in that,

in the recommending module, when the first emotion calibration value represents excited emotion, recommending music which enables excited emotion to be calm; and recommending music which enables the sad emotion to be joyful in the case that the first emotion calibration value is the sad emotion.

10. The infotainment system according to claim 6, further comprising:

And the user habit self-learning module is used for recording and self-learning music manually selected by the user corresponding to the first emotion calibration value or the second emotion calibration value, and modifying the specified recommendation mode according to the self-learning result.

11. A music recommendation playing system is characterized in that,

the acquisition module is used for acquiring expressions and sounds of a user;

the first calibration module calibrates the voice and the emotion of the expression of the user acquired by the acquisition module to serve as a first emotion calibration value;

the recommending module is used for recommending the music of the type corresponding to the emotion calibration value in a specified recommending mode based on the first emotion calibration value; and

and the playing module is used for playing the recommended music or playing the music selected by the user.

12. the music recommendation playback system according to claim 6, further comprising:

the second calibration module is used for calibrating the emotion of the user based on the voice and the expression of the user acquired by the camera and the microphone after the recommended music is played to serve as a second emotion calibration value;

And the recommendation self-learning module is used for considering the recommendation of the recommendation module to be effective if the second emotion calibration value is superior to the first emotion calibration value, and performing self-learning to adjust the recommendation mode if the second emotion calibration value is not superior to the first emotion calibration value.

13. The music recommendation playing system according to claim 6, further comprising:

And the user habit self-learning module is used for recording and self-learning music manually selected by the user corresponding to the first emotion calibration value or the second emotion calibration value, and modifying the specified recommendation mode according to the self-learning result.

14. a computer-readable medium, on which a computer program is stored, the computer program, when being executed by a processor, implementing the music recommendation playing method of any one of claims 1 ~ 6.

15. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the music recommendation playing method of any one of claims 1 ~ 6 when executing the computer program.

Technical Field

the invention belongs to the technical field of automobiles, and particularly relates to a music recommendation playing method and a vehicle-mounted information entertainment system.

Background

currently, the current vehicle-mounted infotainment system generally plays music selected by a user through the manual operation of a screen of the infotainment system by the user, namely, the interaction mode between people and a vehicle in the vehicle is still a stage of needing a driver or passengers to manually operate a central control screen.

further, even when music is played in a vehicle, the emotion of the user in the vehicle is not noticed.

Disclosure of Invention

in view of the above, the present invention is directed to a music recommendation playing method and a vehicle infotainment system that can recommend appropriate music based on the situation of a user.

The music recommendation playing method of the invention is characterized in that,

A first acquisition step of acquiring the voice and expression of a user;

a first calibration step of calibrating the voice and the emotion of the user, which are acquired based on the first acquisition step, as a first emotion calibration value;

Recommending, namely recommending the music of the type corresponding to the emotion calibration value in a specified recommending mode based on the first emotion calibration value.

optionally, the method further comprises, after the recommending step:

a second obtaining step of obtaining the sound and expression of the user after the music recommended in the recommending step is played;

A second calibration step of calibrating the emotion of the user based on the voice and the expression of the user acquired in the second acquisition step to serve as a second emotion calibration value;

Recommending a self-learning step, wherein if the second emotion calibration value is superior to the first emotion calibration value, the recommending step is considered to be effective, and if the second emotion calibration value is not superior to the first emotion calibration value, the self-learning is carried out to adjust a recommending mode.

optionally, the prescribed manner of recommendation is to adapt the recommendation to the type of music so as to make the user's mood calm from excitement or so as to make it happy from sadness.

Optionally, in the recommending step, in a case where the first emotion calibration value is indicative of an excited emotion, recommending music that makes the excited emotion calm; and recommending music which enables the sad emotion to be joyful in the case that the first emotion calibration value is the sad emotion.

optionally, further comprising:

And a user habit self-learning step of recording and self-learning music manually selected by the user corresponding to the first emotion calibration value, and modifying the specified recommendation mode according to the self-learning result.

the vehicle-mounted infotainment system of the invention is characterized in that,

A microphone for acquiring a user's voice;

the camera is used for acquiring the expression of the user;

the first calibration module is used for calibrating the emotion of the user obtained by the microphone and the camera based on the voice and the expression of the user to serve as a first emotion calibration value;

The recommending module is used for recommending the music of the type corresponding to the emotion calibration in a specified recommending mode based on the first emotion calibration value; and

And the playing module is used for playing the recommended music or playing the music selected by the user.

Optionally, the method further comprises:

the second calibration module is used for calibrating the emotion of the user based on the voice and the expression of the user acquired by the camera and the microphone after the recommended music is played to serve as a second emotion calibration value;

and the recommendation self-learning module is used for considering the recommendation of the recommendation module to be effective if the second emotion calibration value is superior to the first emotion calibration value, and performing self-learning to adjust the recommendation mode if the second emotion calibration value is not superior to the first emotion calibration value.

optionally, the prescribed manner of recommendation is to adapt the recommendation to the type of music so as to make the user's mood calm from excitement or so as to make it happy from sadness.

optionally, in the recommending module, when the first emotion calibration value is indicative of an excited emotion, recommending music that makes the excited emotion calm; and recommending music which enables the sad emotion to be joyful in the case that the first emotion calibration value is the sad emotion.

optionally, further comprising:

and the user habit self-learning module is used for recording and self-learning music manually selected by the user corresponding to the first emotion calibration value or the second emotion calibration value, and modifying the specified recommendation mode according to the self-learning result.

the music recommendation playing system of the invention is characterized in that,

the acquisition module is used for acquiring expressions and sounds of a user;

The first calibration module calibrates the voice and the emotion of the expression of the user acquired by the acquisition module to serve as a first emotion calibration value;

The recommending module is used for recommending the music of the type corresponding to the emotion calibration value in a specified recommending mode based on the first emotion calibration value; and

And the playing module is used for playing the recommended music or playing the music selected by the user.

optionally, the method further comprises:

the second calibration module is used for calibrating the emotion of the user based on the voice and the expression of the user acquired by the camera and the microphone after the recommended music is played to serve as a second emotion calibration value;

and the recommendation self-learning module is used for considering the recommendation of the recommendation module to be effective if the second emotion calibration value is superior to the first emotion calibration value, and performing self-learning to adjust the recommendation mode if the second emotion calibration value is not superior to the first emotion calibration value.

optionally, further comprising:

And the user habit self-learning module is used for recording and self-learning music manually selected by the user corresponding to the first emotion calibration value or the second emotion calibration value, and modifying the specified recommendation mode according to the self-learning result.

The computer-readable medium of the present invention, on which a computer program is stored, is characterized in that the computer program realizes the above-mentioned music recommendation playing method when being executed by a processor.

The computer device of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and is characterized in that the processor implements the above music recommendation playing method when executing the computer program.

according to the music recommending and playing method, the music recommending and playing system and the vehicle-mounted infotainment system, the music suitable for the emotion of the user can be automatically recommended without manual input or adjustment of the user, and the music recommending and playing method, the music recommending and playing system and the vehicle-mounted infotainment system can automatically learn and adjust according to the feedback of the expression and the sound of the user and aim to improve the emotion of the user.

Other features and advantages of the methods and apparatus of the present invention will be more particularly apparent from or elucidated with reference to the drawings described herein, and the following detailed description of the embodiments used to illustrate certain principles of the invention.

Drawings

Fig. 1 is a flowchart of a music recommendation playing method according to an embodiment of the present invention.

FIG. 2 is a block diagram showing the structure of a vehicle infotainment system according to an embodiment of the present invention.

Detailed Description

The following description is of some of the several embodiments of the invention and is intended to provide a basic understanding of the invention. It is not intended to identify key or critical elements of the invention or to delineate the scope of the invention.

the main technical idea of the music recommending and playing method is that the sound and the label of a user in the driving process are collected, the emotion of the user is classified and scored (for example, angry 8.5 and excitement 7) according to the expression of the user and the sound (including voice and tone) of the user through a deep learning algorithm, the existing music classification database is labeled or adopted through music data, and a recommending algorithm is used, so that songs suitable for the mood and emotion of the user are recommended from a huge song database on the internet under the condition of vehicle networking.

Moreover, the voice and expression data of the user can be continuously monitored in the playing process, and the recommendation algorithm can be automatically learned and adjusted. For example, when the user hears a song, the emotion changes from negative emotion to positive emotion (e.g. sadness to happiness), or the score of positive emotion increases, or the score of negative emotion decreases, the algorithm considers that the piece of music is favorable for the user's emotion in this case, and if there is no effect, the song is not played in this request case, and the recommendation result becomes more and more accurate through the user's use of training.

therefore, in the music recommendation playing method of the present invention, the user does not need to manually input or adjust, but can automatically learn and adjust according to the feedback of the expression and sound of the user, so as to improve the emotion of the user.

Fig. 1 is a flowchart of a music recommendation playing method according to an embodiment of the present invention.

As shown in fig. 1, a music recommendation playing method according to an embodiment of the present invention includes:

First acquisition step S100: acquiring a user's voice through, for example, a microphone, and acquiring a user's voice through, for example, a camera;

a first calibration step S200: calibrating the user' S voice and emotion expressed by the expression based on the first obtaining step S100 to serve as a first emotion calibration value;

Recommendation step S300: recommending music of a type corresponding to the emotion calibration value in a specified recommendation mode based on the first emotion calibration value;

Second acquisition step S400: after the music recommended by the recommending step is played, acquiring the voice of the user through a microphone and acquiring the expression of the user through a camera;

A second calibration step S500: calibrating the emotion given to the user based on the voice and the expression of the user acquired in the second acquisition step S400 to serve as a second emotion calibration value; and

recommending a self-learning step S600, if the second emotion calibration value is superior to the first emotion calibration value, considering the recommending step to be effective, and if the second emotion calibration value is not superior to the first emotion calibration value, performing self-learning to adjust a recommending mode.

in the first calibration step S200 and the second calibration step S500, as a method for calibrating the emotion of the user to obtain an emotion calibration value, for example, manual annotation data (manually identifying the emotion of the voice and labeling and scoring) may be collected and provided to the machine for deep learning, and emotion keywords may be extracted according to the result of voice recognition, for example, "i am happy," when the user talks to other people, such keywords may also be used as a reference for calibrating the emotion of the user.

in addition, as a calibration value of emotion, the following classifications may be made and a numerical value may be calibrated for these classifications. For example, according to the seven human emotions, the following categories can be simply classified:

and (3) happiness: including love, joy, liking, happiness, joy, excitement, etc.;

rage: including anger, irritation, irritability, complaints of hate, etc.;

grief: including sadness, compassion, sadness, or sadness;

Music: including joyful, happy, satisfied, etc.;

Surprisingly: comprises surprise-by-stroke, surprise, panic, palpitation, surprise, exclamation, surprise, excitement and the like;

Terrorism: including panic, fear, worry, fear, etc.;

thinking: including thoughts, thought thoughts, smoothies, etc.

in a recommending step S300, music of a type corresponding to the emotion rating is recommended in a prescribed recommendation manner based on the first emotion rating. Here, the principle of the so-called prescribed recommendation method is that, instead of enhancing the user's existing mood, it is obviously inappropriate to play sad music when the user's mood is low, and it is obviously unsafe for the user to drive a car to play exciting music when the user's mood is high. The recommendation mode of the invention has the principle that the mood of the user tends to be pleasant and calm, the sense similar to endorphin secretion is generated, the user recommends playing soft and soft music to make the mood of the user change well when the user is sad, and the user recommends gentle and calm music to make the user calm when the user is excited and excited.

naturally, the usual habits of the user may also be considered, for example, if the user manually selects (searches) some songs with bright and strong rhythm when enjoying, or selects sadly music when sadness exists, the system records and learns, modifies the algorithm parameters of the recommendation method, and plays the songs that the user wants to hear in the mood at that time when recommending next time.

the music recommendation playing method of the present invention is explained above, and the music recommendation playing system of the present invention is explained next. In the following, a case where the music recommendation/playback system of the present invention is mounted on a vehicle will be described as an example, and in this example, a vehicle-mounted infotainment system of the vehicle is the music recommendation/playback system of the present invention.

FIG. 2 is a block diagram showing the structure of a vehicle infotainment system according to an embodiment of the present invention.

as shown in FIG. 2, a vehicle infotainment system according to an embodiment of the present invention includes:

A microphone 100 for acquiring a user's voice;

The camera 200 is used for acquiring the expression of the user;

The first calibration module 200 is used for calibrating the voice and emotion of the user acquired by the microphone 100 and the camera 200 based on the expression of the voice and the emotion of the user, and the first emotion calibration value is used as a first emotion calibration value;

a recommending module 300 for recommending a type of music corresponding to the mood calibration value in a prescribed recommending manner based on the first mood calibration value, wherein the prescribed recommending manner is to adapt the recommendation to the type of music so that the mood of the user tends to calm from excitement or so that the user tends to pleasure from sadness, for example, in the case where the first mood calibration value is indicative of excitement mood, the recommendation is to recommend music so that the excitement tends to calm; recommending music which enables sad emotions to be joyful when the first emotion calibration value is the sad emotion;

a playing module 400, configured to play the recommended music or play the music selected by the user;

A second calibration module 500, configured to calibrate, as a second emotion calibration value, emotion of the user based on the voice and expression of the user acquired by the camera and the microphone after the recommended music is played;

A recommendation self-learning module 600, which considers the recommendation of the recommendation module to be valid if the second mood calibration value is better than the first mood calibration value, and performs self-learning to adjust the recommendation mode if the second mood calibration value is not better than the first mood calibration value; and

the user habit self-learning module 700 records and self-learns music manually selected by the user corresponding to the first emotion calibration value or the second emotion calibration value, and modifies the self-learning result into the prescribed recommendation mode.

The present invention also provides a computer readable medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the music recommendation playing method described above.

the invention also provides computer equipment which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, and is characterized in that the processor realizes the music recommendation playing method when executing the computer program.

According to the music recommending and playing method, the music recommending and playing system and the vehicle-mounted infotainment system, the music suitable for the emotion of the user can be automatically recommended without manual input or adjustment of the user, and the music recommending and playing method, the music recommending and playing system and the vehicle-mounted infotainment system can automatically learn and adjust according to the feedback of the expression and the sound of the user and aim to improve the emotion of the user.

the above examples mainly illustrate the music recommendation playing method, the music recommendation playing system and the vehicle infotainment system of the present invention. Although only a few embodiments of the present invention have been described in detail, those skilled in the art will appreciate that the present invention may be embodied in many other forms without departing from the spirit or scope thereof. Accordingly, the present examples and embodiments are to be considered as illustrative and not restrictive, and various modifications and substitutions may be made therein without departing from the spirit and scope of the present invention as defined by the appended claims.