CN107766561A - Method, device, storage medium and terminal equipment for music recommendation - Google Patents

Abstract

The embodiment of the application discloses a music recommendation method, a music recommendation device, a storage medium and terminal equipment. The method comprises the following steps: acquiring leisure habit information of a preset number of users, and acquiring music playing records of the users to form a sample training set; training the sample training set to obtain a mapping model of the leisure habit information and the favorite music types; acquiring the leisure habit information of the current user, inputting the leisure habit information into the mapping model, and determining the favorite music type to be recommended; and recommending music according to the favorite music type to be recommended. According to the technical scheme, the effect of optimizing the music recommendation mode of the terminal equipment can be achieved.

Description

Method, device, storage medium and terminal equipment for music recommendation

technical field

The embodiments of the present application relate to the computer field, and in particular to a music recommendation method, device, storage medium, and terminal equipment.

Background technique

Terminal equipment is gradually becoming intelligent, which brings many conveniences to people's life. Among them, listening to music through terminal equipment such as mobile phones has become one of the functions favored by customers.

However, the existing music recommendation model is too monotonous, such as classifying according to music release time, user listening popularity, and emotion, which is difficult to meet users' multi-dimensional needs for music. The current music recommendation brings users a poor experience and needs to be improved.

Contents of the invention

Embodiments of the present application provide a music recommendation method, device, storage medium, and terminal device, which can optimize the music recommendation method of the terminal device.

In the first aspect, the embodiment of the present application provides a method for music recommendation, which includes

Collect leisure habit information of a preset number of users, and obtain music playing records of the users to form a sample training set;

Carry out training to described sample training set, obtain the mapping model of leisure habit information and preferred music type;

Obtain the leisure habit information of the current user, input the mapping model, and determine the type of favorite music to be recommended;

Perform music recommendation according to the type of preferred music to be recommended.

In the second aspect, the embodiment of the present application provides a music recommendation device, which includes:

The sample training set determination module is used to collect the leisure habit information of a preset number of users, and obtain the music playing records of the users to form a sample training set;

The mapping model determination module is used to train the sample training set to obtain the mapping model of leisure habit information and preferred music type;

The preferred music type determination module is used to obtain the leisure habit information of the current user, input the mapping model, and determine the preferred music type to be recommended;

The music recommendation module is used for performing music recommendation according to the type of preferred music to be recommended.

In a third aspect, the embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method for recommending music as described in the embodiment of the present application is implemented.

In the fourth aspect, the embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the implementation of the present application is implemented. The music recommendation method described in the example.

In the technical solution provided by the embodiment of the present application, a sample training set is formed by collecting the leisure habit information of a preset number of users and obtaining the music playing records of the users; training the sample training set to obtain the leisure habit information and A mapping model of music preferences; obtaining the leisure habit information of the current user, inputting the mapping model, and determining the music preferences to be recommended; performing music recommendation according to the music preferences to be recommended. By adopting the technical solution provided by this application, the effect of optimizing the way of music recommendation of the terminal device can be achieved.

Description of drawings

FIG. 1 is a schematic flow diagram of a method for music recommendation provided in an embodiment of the present application;

FIG. 2 is a schematic flowchart of another method for music recommendation provided by the embodiment of the present application;

FIG. 3 is a schematic flowchart of another method for music recommendation provided by an embodiment of the present application;

FIG. 4 is a schematic flowchart of another method for music recommendation provided by an embodiment of the present application;

FIG. 5 is a schematic flowchart of another method for music recommendation provided by an embodiment of the present application;

FIG. 6 is a structural block diagram of an apparatus for music recommendation provided by an embodiment of the present application;

FIG. 7 is a schematic structural diagram of a terminal device provided in an embodiment of the present application.

Detailed ways

The technical solution of the present application will be further described below in conjunction with the accompanying drawings and through specific implementation methods. It should be understood that the specific embodiments described here are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, only some structures related to the present application are shown in the drawings but not all structures.

Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the steps as sequential processing, many of the steps may be performed in parallel, concurrently, or simultaneously. Additionally, the order of steps may be rearranged. The process may be terminated when its operations are complete, but may also have additional steps not included in the figure. The processing may correspond to a method, function, procedure, subroutine, subroutine, or the like.

Fig. 1 is a schematic flowchart of a method for music recommendation provided by an embodiment of the present application. The method can be executed by an apparatus for music recommendation, wherein the apparatus can be implemented by software and/or hardware, and generally can be integrated into a terminal device. As shown in Figure 1, the method includes:

S101. Collect leisure habit information of a preset number of users, and obtain music playing records of the users to form a sample training set.

Wherein, the leisure habit information of a preset number of users is collected, and the preset number may be 50 users, 100 users, 1000 users or even more. The manner in which the terminal device collects the leisure habit information may be to obtain the data of the leisure habit information of a preset number of users by accessing the server. Among them, the leisure habit information can be the type of leisure and entertainment places that the user often frequents. For example, it can be detected that the user searches for food, movie tickets, etc. It is the type that is used to watching the latest movies on the line. Correspondingly, the location service can also be used to determine the frequent location of the user during leisure time. Apart from being at home, whether he often goes to sports venues, various parks, or some lively leisure places such as bars or karaoke halls. location, and then determine the user's current leisure habit information. The advantage of this technical solution is that some trivial information fragments of the user's terminal equipment can be used, and these information fragments can just reflect some habitual information of the user, and integrate them as a follow-up music recommendation based on these information The foundation can not only improve the user's interest in music recommendation, but also improve the utilization rate of some information of the terminal equipment and achieve effective output effects.

Wherein, the music playback record may be local music of the terminal device used by the user, or may be a playback record generated by the user logging in through an account or listening to online music through the terminal device. If the user logs in and listens to some songs on another terminal device through the account, the user can log in to the current terminal device to obtain the playback records of the trial listening to the songs logged in and auditioned on another terminal device, including the tracks and the audition. Duration and other information, and recorded as music playback.

The above leisure habit information and music playing records are used as a sample training set to achieve the effect of determining the type of music the user likes from the user's leisure habit information.

S102. Perform training on the sample training set to obtain a mapping model between leisure habit information and preferred music types.

Among them, a machine learning method can be used to obtain a mapping model between the user's leisure habit information and the type of music he likes. Correspondingly, the cyclic neural network in neural network training can be used for learning. The advantage of this setting is that according to the characteristics and usage of the neural network itself, when improving the training samples and training results, it generally involves the function of one of them. Changes, adjustments to the connection relationship of a certain node, and the type of neural network that can be changed at will in different scenarios make the processing method more flexible, and can also adapt to further improvements by developers on the basis of model training.

Among them, since the number of collected samples is large enough, it can be considered that the songs appearing in the user's music playback records can reflect the songs acceptable to the user, and then use the information to determine the user's preference for the current music genre. For example, if it is determined from the user's leisure habit information that the user's favorite leisure place is a coffee shop, among the 100 songs in the user's music playback records, 80 are songs sung by male singers, then the user's music preference type can be obtained. Preference is given to songs sung by male singers. For example, among all the songs, 70 are sad songs, it can be determined that the user prefers more sad songs. In the user's music playing records, it is possible to determine the respective proportions of various types of preferences of the user, and then comprehensively determine the type of music the user prefers. In this way, a mapping relationship between users who like to enjoy life and various music genres can be established, and then through training a large number of user data, the preferences of various music genres corresponding to each leisure habit information can be obtained. Among them, it is worth noting that the music type can be single-dimensional. For example, according to the type of music, it can be classified into ethnic, popular, and bel canto, etc.; according to the emotional style, it can be light music, prairie style, rock and country music, etc.; Types can also be multidimensional. So for the same song can be tagged by different genres.

S103. Obtain the leisure habit information of the current user, input the mapping model, and determine the type of favorite music to be recommended.

Wherein, the leisure habit information of the current user may be the leisure habit information of the user currently using the terminal device, and the specific acquisition method may be the same as the above method, which will not be repeated here.

Input the leisure habit information of the current user into the mapping model to obtain the music preference type corresponding to the leisure habit information of the current user, wherein the degree of preference for different types of music can be identified by a method similar to a score, such as for a new The preference data for online music can be 60 points, and the preference data for a certain old song can be 75 points.

S104. Perform music recommendation according to the type of preferred music to be recommended.

In combination with the above example, according to the scores of the preference data of different types of music, the music to be recommended can be rearranged according to the score from high to low, and recommended according to the rearranged order. Among them, in the recommendation process, the popularity of music and the online time can also be used as reference factors, and after all the data are integrated, they can be arranged and the recommendation list can be output.

In the technical solution provided by the embodiment of the present application, a sample training set is formed by collecting the leisure habit information of a preset number of users and obtaining the music playing records of the users; training the sample training set to obtain the leisure habit information and A mapping model of music preferences; obtaining the leisure habit information of the current user, inputting the mapping model, and determining the music preferences to be recommended; performing music recommendation according to the music preferences to be recommended. By adopting the technical solution provided by this application, the effect of optimizing the way of music recommendation of the terminal device can be achieved.

On the basis of the above technical solution, optionally, training the sample training set to obtain a mapping model of leisure habit information and preferred music type includes: inputting each leisure habit information into the mapping model, and corresponding The user's historical playing records are input into the mapping model for training; after training, the mapping relationship between leisure habit information and music type tag weight is obtained as the mapping model. Wherein, the music type tag user reflects the type of music, and there may be one or multiple type tags for the same music. Since the user cannot evaluate each song in the process of listening to music, the user's music playback record cannot be obtained directly through the user's evaluation or downloading, etc., so users with different leisure habit information can obtain information from the music The playback record reflects a weight value of the music type tag that the user likes. The higher the weight, the more the user likes it, and the lower the weight, the less the user likes it. The advantage of this setting is that model training can be used to determine the music type tag weight corresponding to the user's leisure habit information based on the music playback records of a large number of users, which can provide a data basis for recommended music, making the recommended music more in line with the user's personal preferences, thus Improve the user's audition effect on recommended music and improve the user's experience.

Fig. 2 is a schematic flow chart of another music recommendation method provided in the embodiment of the present application. As shown in Fig. 2, the method includes:

S201. Acquire location information of a user in a preset leisure time period.

Wherein, the location information may be location information obtained by opening the positioning component. It can also be the location information selected or searched by the user in the application program or webpage, or it can be the location information data determined by obtaining the positioning service opened by the user when opening an application program. For example, on a Sunday afternoon, if a user purchases a movie ticket through a group buying software, when opening the group buying software, since the location service is set to be enabled, the location function will be automatically turned on to locate the user's location. Determine the user's location information after the information, such as the user's current location information is a certain shopping mall, and the item of the group purchase is a KTV singing group purchase coupon, then two kinds of preference leisure place categories of the user can be determined simultaneously from the user's location information.

S202. Determine the user's preferred leisure place category according to the location information.

Among them, the leisure place type at the user's current location can be determined as the preferred leisure place type according to the user's current location information, and the leisure place type at the user's intended location can also be determined according to the intended location input by the user in the terminal device as the preferred leisure place type .

The location information can be obtained in several ways in the above examples. According to the location information, determining the user's preferred leisure place can be based on the user's leisure place during the leisure time. For example, from Monday to Friday from 7:00 pm to 10:00 pm, and all day on Saturday and Sunday, here is just an example. Leisure time can be determined according to the user's work and rest habits. For example, a user shifts all day from Monday to Wednesday , Thursday to Sunday are holidays, and the user's leisure time can also be determined according to the user's location information. For example, by using location information, it can be determined that the user is at work when he or she activates location services multiple times throughout the day from Monday to Wednesday, while from Thursday to Sunday, it appears at home and other locations, and does not appear at work. The leisure time is Thursday to Sunday. After the leisure time period is determined, the user's preferred leisure place category can be determined according to the location information of the user during the leisure time period.

S203. Determine the leisure habit information of the user according to the category of the preferred leisure place.

In the embodiment of the present application, optionally, the preferred leisure place category includes: reading leisure place, sports leisure place, communication leisure place and happy leisure place; the user's leisure habit information includes: Love reading and leisure habits, love sports and leisure habits, love making friends and leisure habits and love singing and dancing leisure habits.

Wherein, the reading leisure places may include libraries in various places, such as city libraries and university libraries. Sports leisure places may include various sports venues, such as basketball courts, football fields, and badminton halls. Communication leisure places can include various coffee shops, western restaurants and so on. Happy leisure places can include various bars, game places and so on. The advantage of this setting is that the user's hobby type can be determined according to the user's frequent choice of leisure, and then the music type can be recommended according to the user's hobby type, so that the recommended music can be more in line with the user's personality.

S204. Acquire the user's music playing record, and form a sample training set with the acquired user's leisure habit information and the user's music playing record.

S205. Perform training on the sample training set to obtain a mapping model between leisure habit information and preferred music types.

S206. Obtain the leisure habit information of the current user, input the mapping model, and determine the type of preferred music to be recommended.

S207. Perform music recommendation according to the type of preferred music to be recommended.

This technical solution is based on the above-mentioned technical solutions. This technical solution provides a method for determining the user's leisure habit information according to the user's location information. The data acquisition method of this method is simple and accurate, so that the music recommendation provided by this application The method is highly feasible, and the data source is closer to the user's life, which can improve the user's acceptance of music recommendation.

On the basis of the above technical solution, optionally, according to the preferred leisure place category, determining the user's leisure habit information includes: according to the preferred leisure place category, and the leisure period of the preferred leisure place category in a preset cycle The frequency and time of occurrence of all preferred leisure place categories in the user are determined to determine the leisure habit information of the user. Among them, the leisure period can be determined according to the determination method described in the above-mentioned technical solution, and the preset period can be one day, one week, half a month, one month and a longer period of time. In the leisure period of the preset period, preference The frequency of occurrence of the leisure place category can be the frequency or number of occurrences of the location of the leisure place in the leisure period of the preset cycle; , or the amount of time spent at a casual location. According to the above two methods, the user's preferred leisure style can be determined, and then the user's leisure habit information can be determined. For example, the user's location information can determine that the user goes to the bar twice a week, and it can be determined that the user has a leisure habit of loving singing and dancing. . Correspondingly, during the music recommendation process, more explosive music with a strong sense of rhythm can be recommended.

Fig. 3 is a schematic flow chart of another music recommendation method provided in the embodiment of the present application. As shown in Fig. 3, the method includes:

S301. Collect leisure habit information of a preset number of users, and acquire music playing records of the users to form a sample training set.

S302. Obtain the historical playing time of the music in the historical playing record of the corresponding user.

Wherein, the historical playback time may be the time when each piece of music in the playback record starts playing, or the time when it ends playing. The historical playback time can be included in the sorting basis in the historical playback records. The earliest playback time is at the start position of the playback record, and the latest playback time is at the end position of the playback record, and then arranged in forward or reverse order to obtain the playback record sequence. It is worth noting that when a song is repeatedly played, it can be kept at different positions in the historical playback record sequence at the same time. The advantage of this setting is that it increases the proportion of the music type of the song being played repeatedly, which can make the music playback record more able to reflect the music type preferred by the user.

S303. Configure a first weight sequence for the historical playback record according to the historical playback time.

Among them, the weight value in the first weight sequence can change linearly with the playback order. For example, if the historical playback records take 100 pieces of music, then from the earliest time to the latest time, configure the weight sequence for it as 100 from 0.01 to 1.00. weight values, and then combine the weight values together to form a weight sequence. It can also be changed non-linearly. For example, the configuration with the latest time is 1.00, and it will not change after each decrement of 0.01 until 0.50. The result is that the weight value of the first 50 songs from early to late is all 0.50 , the last 50 songs are currently incremented until 1.00. It can also be configured according to the difference of the historical playback time in the historical playback records. The advantage of this setting is that as time progresses, if the type of music preferred by the user changes, it can be reflected through the corresponding weight value. Avoid the problem that because the user prefers one type of music recently, but because of its small number of historical playback records, it is covered up by other types of music.

S304. Input the information of each type of leisure habit into the mapping model, and input the historical play records configured with the first weight sequence into the mapping model for training.

After the first weight sequence is configured, the historical playback record input mapping model can fully reflect the type of music that the user prefers in the most recent time period, and it will be reflected in the training results. However, the benefits of such settings in the embodiment of the present application can also be based on users with the same leisure habit information. If their favorite music types are all developing towards a certain music type as time progresses, then it can be used in the music recommendation process for users. When recommending this type of music, it can not only provide the user with fresh music, but also determine that the user will also like this type of music based on certain data. Such music recommendation can achieve a very ideal effect.

S305. After training, obtain a mapping relationship between leisure habit information and music genre label weights as the mapping model.

S306. Obtain the leisure habit information of the current user, input the mapping model, and determine the type of preferred music to be recommended.

S307. Perform music recommendation according to the type of preferred music to be recommended.

On the basis of the above technical solution, this technical solution provides the implicit information based on historical playback records, and configures weights for the music in it, which can provide users with fresh music on the basis of the original technical solution. Music, and based on certain data, it can be determined that users will also like this type of music. Such music recommendation can achieve very ideal results.

Fig. 4 is a schematic flow chart of another music recommendation method provided in the embodiment of the present application. As shown in Fig. 4, the method includes:

S401. Collect leisure habit information of a preset number of users, and obtain music playing records of the users to form a sample training set.

S402. Obtain the historical playback completeness of the music in the corresponding user's historical playback records.

Among them, the playback completeness can be the ratio of the playing time to the total duration of the music if it is switched by the user during the playback of the music. For example, the total duration of a certain music is 4 minutes, but the user only plays it for 2 minutes before switching If the user selects the next song or exits the music playing program, it can be determined that the playing completion of the music is 50%. It is worth noting that the playing integrity of the current music can also be changed by dragging the progress bar during the music playing process. In this embodiment, switching is only used as an example rather than a specific limiting manner.

S403. According to the historical playback completeness, configure a second weight sequence for the historical playback record.

After obtaining the playback completeness of each piece of music in the music playback record, you can configure its weight according to its playback completeness, where the configured weight value can be proportional to the playback completeness, that is, if the playback completeness If it is 50%, the weight value configured for the music is 0.50, or it may be positively correlated, that is, the lower the playback integrity, the lower the weight value configured for the music. Arranging the weight values configured for each song in a play order or in accordance with the change order of the weight values to form a second weight sequence.

S404. Input each type of leisure habit information into the mapping model, and input the historical play records configuring the second weight sequence into the mapping model for training.

After the second weight sequence is configured, the historical playback record input mapping model can fully reflect the type of music that the user prefers or dislikes during playback, and will be reflected in the training results.

S405. After training, obtain a mapping relationship between leisure habit information and music genre tag weights as the mapping model.

S406. Obtain the leisure habit information of the current user, input the mapping model, and determine the type of preferred music to be recommended.

S407. Perform music recommendation according to the type of preferred music to be recommended.

On the basis of the above technical solution, this technical solution provides the implicit information based on the playback integrity of historical playback records, and configures weights for the music in it, which can be based on the original technical solution. The user provides the favorite music type with the same leisure habit information, so that the music recommendation can meet the user's preference for the music type.

Fig. 5 is a schematic flow chart of another music recommendation method provided in the embodiment of the present application. As shown in Fig. 5, the method includes:

S501. Collect leisure habit information of a preset number of users, and obtain music playing records of the users to form a sample training set.

S502. Perform training on the sample training set to obtain a mapping model between leisure habit information and preferred music types.

S503. Obtain the leisure habit information of the current user, input the mapping model, and determine the type of preferred music to be recommended.

S504. Determine the genre label of the music to be recommended.

Wherein, the music to be recommended may be originally recommended music in the music recommendation interface when the user enters the music recommendation interface through the terminal device. It may be to obtain some music information on the original music recommendation page, and determine the genre tags of the music to be recommended according to the music information. For example, after the audio data is obtained, the type tags of the music to be recommended can be determined by obtaining the characteristic information of the music, such as music accompaniment, music rhythm, etc. After analysis, the obtained results are treated as recommended music annotation type labels.

S505. According to the type of preferred music to be recommended, determine the arrangement order of the music to be recommended with tags of corresponding types, and perform music recommendation.

Wherein, according to the output result of the mapping model, the type of favorite music to be recommended corresponding to the leisure habit information of the current user can be determined, and then combined with the type label of each piece of music in the music recommendation interface, the music in the music recommendation interface Sorting and recommending, wherein, the music that conforms to the music type output by the model is sorted according to the user's possible preference, such as song A and song B, the label of song A is jazz type, while song B is Chinese style, the user's leisure The habit information is the leisure habit of loving reading, and the mapping model determines the type of music the user likes and its coefficients are: pastoral 0.75, Chinese style 0.7, jazz 0.6, rock 0.3 and sad 0.1, then song B can be ranked before song A as Users make recommendations.

On the basis of the above technical solution, this technical solution provides a specific method for sorting and recommending music to be recommended. By adopting this solution, it is possible to quickly reorder and recommend music to be recommended, and can provide users with Favorite music types, improve the reception of recommended music and the conversion rate of audition and download.

Fig. 6 is a structural block diagram of an apparatus for music recommendation provided by an embodiment of the present application. This apparatus can be implemented by software and/or hardware, and is generally integrated in a terminal device. The volume of the terminal device can be adjusted by performing a music recommendation method. adjust. As shown in Figure 6, the device includes:

The sample training set determination module 601 is used to collect the leisure habit information of a preset number of users, and obtain the music playing records of the users to form a sample training set;

A mapping model determination module 602, configured to train the sample training set to obtain a mapping model between leisure habit information and preferred music types;

Favorite music type determination module 603, for obtaining the leisure habit information of current user, input described mapping model, determine the favorite music type to be recommended;

The music recommendation module 604 is configured to perform music recommendation according to the type of preferred music to be recommended.

In the technical solution provided by the embodiment of the present application, a sample training set is formed by collecting the leisure habit information of a preset number of users and obtaining the music playing records of the users; training the sample training set to obtain the leisure habit information and A mapping model of music preferences; obtaining the leisure habit information of the current user, inputting the mapping model, and determining the music preferences to be recommended; performing music recommendation according to the music preferences to be recommended. By adopting the technical solution provided by this application, the effect of optimizing the way of music recommendation of the terminal device can be achieved.

On the basis of the above technical solution, optionally, the sample training set determining module 601 includes:

A position information acquisition unit, configured to acquire the position information of the user during the preset leisure time period;

A preferred leisure place category determining unit, configured to determine the user's preferred leisure place category according to the location information;

The leisure habit information determining unit is configured to determine the user's leisure habit information according to the category of the preferred leisure place.

On the basis of the above technical solutions, optionally,

The categories of preferred leisure places include: reading leisure places, sports leisure places, communication leisure places and joyful leisure places;

The user's leisure habits information includes: leisure habits of loving reading, loving sports and leisure habits, loving leisure habits of making friends, and loving leisure habits of singing and dancing.

On the basis of the above technical solutions, optionally, the leisure habit information determining unit is specifically used for:

The leisure habit information of the user is determined according to the preferred leisure place category, and the occurrence frequency and time of all preferred leisure place categories in the leisure period of the preset cycle.

On the basis of the above technical solutions, optionally, the mapping model determining module 602 includes:

The mapping model training unit is used to input each kind of leisure habit information into the mapping model, and input the corresponding user's historical play records into the mapping model for training;

The mapping model determination unit is configured to obtain the mapping relationship between the leisure habit information and the weight of the music genre label after training as the mapping model.

On the basis of the above technical solutions, optionally, the mapping model training unit is specifically used for:

Obtain the historical playing time of music in the historical playing record of the corresponding user;

According to the historical playback time, configure a first weight sequence for the historical playback record;

Inputting information of each type of leisure habit into the mapping model, and inputting the historical play records configuring the first weight sequence into the mapping model for training.

On the basis of the above technical solutions, optionally, the mapping model training unit is specifically used for:

Obtain the historical playback integrity of the music in the corresponding user's historical playback records;

According to the completeness of the historical playback, configure a second weight sequence for the historical playback record;

Inputting information of each type of leisure habit into the mapping model, and inputting the historical play records configuring the second weight sequence into the mapping model for training.

On the basis of the above technical solutions, optionally, the device also includes:

A genre tag determining module of music to be recommended is used to determine a genre tag of music to be recommended;

Correspondingly, the music recommendation module 604 is specifically used for:

According to the type of favorite music to be recommended, determine the arrangement order of the music to be recommended with corresponding type tags, and perform music recommendation.

The above-mentioned device can execute the method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

The embodiment of the present application also provides a storage medium containing computer-executable instructions, and the computer-executable instructions are used to perform a music recommendation method when executed by a computer processor, the method comprising:

Collect leisure habit information of a preset number of users, and obtain music playing records of the users to form a sample training set;

Carry out training to described sample training set, obtain the mapping model of leisure habit information and preferred music type;

Obtain the leisure habit information of the current user, input the mapping model, and determine the type of favorite music to be recommended;

Perform music recommendation according to the type of preferred music to be recommended.

storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media such as CD-ROMs, floppy disks or tape drives; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc. ; non-volatile memory, such as flash memory, magnetic media (eg hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. Also, the storage medium may be located in a computer system in which the program is executed, or may be located in a different second computer system connected to the computer system through a network such as the Internet. The second computer system may provide program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations, such as in different computer systems connected by a network. The storage medium may store program instructions (eg embodied as computer programs) executable by one or more processors.

Certainly, a storage medium containing computer-executable instructions provided in the embodiments of the present application, the computer-executable instructions are not limited to the operation of music recommendation as described above, and may also perform the operation of music recommendation provided in any embodiment of the present application. Related operations in the method.

An embodiment of the present application provides a terminal device, in which the music recommendation apparatus provided in the embodiment of the present application can be integrated. FIG. 7 is a schematic structural diagram of a terminal device provided in an embodiment of the present application. As shown in FIG. 7, the terminal device may include: a memory 701, a central processing unit (Central Processing Unit, CPU) 702 (also known as a processor, hereinafter referred to as CPU), a circuit board (not shown in the figure) and a power circuit ( not shown in the figure). The circuit board is placed inside the space surrounded by the housing; the CPU 702 and the memory 701 are arranged on the circuit board; the power supply circuit is used to supply power to each circuit or device of the terminal device The memory 701 is used to store executable program codes; the CPU702 executes a computer program corresponding to the executable program codes by reading the executable program codes stored in the memory 701, to achieve the following steps:

Collect leisure habit information of a preset number of users, and obtain music playing records of the users to form a sample training set;

Carry out training to described sample training set, obtain the mapping model of leisure habit information and preferred music type;

Obtain the leisure habit information of the current user, input the mapping model, and determine the type of favorite music to be recommended;

Perform music recommendation according to the type of preferred music to be recommended.

The terminal device also includes: peripheral interface 703, RF (Radio Frequency, radio frequency) circuit 705, audio circuit 706, speaker 711, power management chip 708, input/output (I/O) subsystem 709, touch screen 712, other Input/control devices 710 and external ports 704 , these components communicate via one or more communication buses or signal lines 707 .

It should be understood that the illustrated terminal device 700 is only an example of a terminal device, and the terminal device 700 may have more or fewer components than those shown in the figure, and two or more components may be combined, Or can have a different component configuration. The various components shown in the figures may be implemented in hardware, software, or a combination of hardware and software including one or more signal processing and/or application specific integrated circuits.

The terminal device for music recommendation provided by this embodiment will be described in detail below, and the terminal device is a mobile phone as an example.

Memory 701, the memory 701 can be accessed by the CPU 702, the peripheral interface 703, etc., the memory 701 can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more disk storage devices, flash memory devices , or other volatile solid-state storage devices.

Peripheral interface 703 , which can connect the input and output peripherals of the device to CPU 702 and memory 701 .

The I/O subsystem 709 , the I/O subsystem 709 can connect input and output peripherals on the device, such as a touch screen 712 and other input/control devices 710 , to the peripheral interface 703 . I/O subsystem 709 may include a display controller 7091 and one or more input controllers 7092 for controlling other input/control devices 710 . Among them, one or more input controllers 7092 receive electrical signals from or send electrical signals to other input/control devices 710, which may include physical buttons (push buttons, rocker buttons, etc.) ), dials, slide switches, joysticks, click wheels. It is worth noting that the input controller 7092 can be connected to any of the following: a keyboard, an infrared port, a USB interface, and a pointing device such as a mouse.

A touch screen 712. The touch screen 712 is an input interface and an output interface between the user terminal device and the user, and displays visual output to the user. The visual output may include graphics, text, icons, videos, and the like.

The display controller 7091 in the I/O subsystem 709 receives electrical signals from the touch screen 712 or sends electrical signals to the touch screen 712 . The touch screen 712 detects the contact on the touch screen, and the display controller 7091 converts the detected contact into an interaction with the user interface object displayed on the touch screen 712, that is, realizes human-computer interaction, and the user interface object displayed on the touch screen 712 can be a running Icons for games, icons for networking to appropriate networks, etc. It is worth noting that the device may also include an optical mouse, which is a touch-sensitive surface that does not display visual output, or that is an extension of a touch-sensitive surface formed by a touch screen.

The RF circuit 705 is mainly used to establish communication between the mobile phone and the wireless network (that is, the network side), and realize data reception and transmission between the mobile phone and the wireless network. Such as sending and receiving short messages, e-mails, etc. Specifically, the RF circuit 705 receives and sends RF signals, which are also called electromagnetic signals, and the RF circuit 705 converts electrical signals into electromagnetic signals or converts electromagnetic signals into electrical signals, and communicates with communication networks and other devices through the electromagnetic signals to communicate. RF circuitry 705 may include known circuitry for performing these functions including, but not limited to, an antenna system, an RF transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a CODEC ( COder-DECoder, Codec) Chipset, Subscriber Identity Module (Subscriber Identity Module, SIM) and so on.

The audio circuit 706 is mainly used to receive audio data from the peripheral interface 703 , convert the audio data into electrical signals, and send the electrical signals to the speaker 711 .

The speaker 711 is used to restore the voice signal received by the mobile phone from the wireless network through the RF circuit 705 into sound and play the sound to the user.

The power management chip 708 is used for power supply and power management for the hardware connected to the CPU 702 , the I/O subsystem and the peripheral interface.

The terminal device provided in the embodiment of the present application can realize the effect of optimizing the manner of music recommendation.

The music recommendation device, storage medium, and terminal device provided in the above embodiments can execute the music recommendation method provided in any embodiment of the present application, and have corresponding functional modules and beneficial effects for executing the method. For technical details not exhaustively described in the above embodiments, refer to the music recommendation method provided in any embodiment of the present application.

Note that the above are only preferred embodiments and technical principles used in this application. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present application. Therefore, although the present application has been described in detail through the above embodiments, the present application is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present application, and the present application The scope is determined by the scope of the appended claims.

Claims (11)

1. A method for music recommendation, comprising: Collect leisure habit information of a preset number of users, and obtain music playing records of the users to form a sample training set; Carry out training to described sample training set, obtain the mapping model of leisure habit information and preferred music type; Obtain the leisure habit information of the current user, input the mapping model, and determine the type of favorite music to be recommended; Perform music recommendation according to the type of preferred music to be recommended. 2. The method for music recommendation according to claim 1, wherein the collection of leisure habit information of a preset number of users includes: Obtain the location information of the user during the preset leisure time; According to the location information, determine the user's preferred leisure place category; According to the preferred leisure place category, the user's leisure habit information is determined. 3. The method for music recommendation according to claim 2, characterized in that, The categories of preferred leisure places include: reading leisure places, sports leisure places, communication leisure places and joyful leisure places; The user's leisure habits information includes: leisure habits of loving reading, loving sports and leisure habits, loving leisure habits of making friends, and loving leisure habits of singing and dancing. 4. The method for music recommendation according to claim 2 or 3, characterized in that, according to the category of preferred leisure places, determining the user's leisure habit information includes: The leisure habit information of the user is determined according to the preferred leisure place category, and the occurrence frequency and time of all preferred leisure place categories in the leisure period of the preset cycle. 5. The method for music recommendation according to claim 1, wherein the sample training set is trained to obtain a mapping model of leisure habit information and favorite music type, including: Input each kind of leisure habit information into the mapping model, and input the corresponding user's historical play records into the mapping model for training; After training, the mapping relationship between leisure habit information and music genre tag weight is obtained as the mapping model. 6. The method for music recommendation according to claim 5, characterized in that, each kind of leisure habit information is input into the mapping model, and the corresponding user's historical play records are input into the mapping model for training, including: Obtain the historical playing time of music in the historical playing record of the corresponding user; According to the historical playback time, configure a first weight sequence for the historical playback record; Inputting information of each type of leisure habit into the mapping model, and inputting the historical play records configuring the first weight sequence into the mapping model for training. 7. The method for music recommendation according to claim 5, characterized in that, each kind of leisure habit information is input into the mapping model, and the corresponding user's historical play records are input into the mapping model for training, including: Obtain the historical playback integrity of the music in the corresponding user's historical playback records; According to the completeness of the historical playback, configure a second weight sequence for the historical playback record; Inputting information of each type of leisure habit into the mapping model, and inputting the historical play records configuring the second weight sequence into the mapping model for training. 8. The method for music recommendation according to claim 5, further comprising: Determine the type label of the music to be recommended; Correspondingly, perform music recommendation according to the type of preferred music to be recommended, including: According to the type of favorite music to be recommended, determine the arrangement order of the music to be recommended with corresponding type tags, and perform music recommendation. 9. A device for music recommendation, characterized by comprising: The sample training set determination module is used to collect the leisure habit information of a preset number of users, and obtain the music playing records of the users to form a sample training set; The mapping model determination module is used to train the sample training set to obtain the mapping model of leisure habit information and preferred music type; The preferred music type determination module is used to obtain the leisure habit information of the current user, input the mapping model, and determine the preferred music type to be recommended; The music recommendation module is used for performing music recommendation according to the type of preferred music to be recommended. 10. A computer-readable storage medium, on which a computer program is stored, wherein when the program is executed by a processor, the method for recommending music according to any one of claims 1-8 is implemented. 11. A terminal device, comprising a memory, a processor, and a computer program stored on the memory and operable by the processor, characterized in that, when the processor executes the computer program, it realizes any of claims 1-8. A method for music recommendation.