KR102516212B1 - Method and Apparatus for Generating Recommended Playlists - Google Patents

Abstract

A method for generating a recommended playlist and an apparatus therefor are disclosed.
A method for generating a recommended playlist according to an embodiment of the present invention includes a signal acquiring step of obtaining a search request signal for a recommended playlist for a previously provided reference playlist from the user terminal; an analysis step of analyzing reference sound source information for the reference playlist based on the search request signal; a creation step of generating at least one recommended playlist based on at least one attribute information included in the analysis result of the reference sound source information; and providing the generated recommendation playlist to the user terminal.

Description

Method and Apparatus for Generating Recommended Playlists {Method and Apparatus for Generating Recommended Playlists}

The present invention relates to a method and apparatus for generating a recommended playlist based on a reference playlist.

The contents described in this section simply provide background information on the embodiments of the present invention and do not constitute prior art.

Recently, with the development of mobile communication networks and the spread of smart phones, a lot of digital media has become commonplace for users, and the need for effective information search and recommendation methods using them is increasing. In particular, in recommending music, there is an increasing demand for a method of recommending music suitable for a user without the user having prior knowledge about music.

In current music services, a large number of playlists are created and managed to respond to various tastes and situations.

However, from the user's point of view, it is very difficult to create a playlist desired by the user among thousands to tens of thousands of sound sources. In particular, when there is a reference playlist previously created by a user, it is very difficult to create and provide a playlist similar to the reference playlist as the concept of 'similar' can be interpreted differently for each person and for each situation.

Accordingly, a technique for generating and providing a recommended playlist similar to a reference playlist previously created by a user is required.

The present invention analyzes information on a pre-provided reference playlist, generates a recommended playlist using a matched sound source from a pre-stored entire sound source list based on the analysis result, and provides the generated recommended playlist to a user terminal. The main purpose is to provide a method for generating a recommended playlist and an apparatus therefor.

According to one aspect of the present invention, a method for generating a recommended playlist to achieve the above object includes a signal acquisition step of acquiring a search request signal for a recommended playlist for a pre-provided reference playlist from the user terminal; an analysis step of analyzing reference sound source information for the reference playlist based on the search request signal; a creation step of generating at least one recommended playlist based on at least one attribute information included in the analysis result of the reference sound source information; and providing the generated recommendation playlist to the user terminal.

In addition, according to another aspect of the present invention, a music service providing apparatus for achieving the above object includes one or more processors and a memory for storing one or more programs executed by the one or more processors, wherein the processor is configured to include the user a signal acquisition step of obtaining a search request signal for a recommended playlist for a previously provided reference playlist from a terminal; an analysis step of analyzing reference sound source information for the reference playlist based on the search request signal; a creation step of generating at least one recommended playlist based on at least one attribute information included in the analysis result of the reference sound source information; and providing the created recommendation playlist to the user terminal.

As described above, the present invention has an effect of providing a recommended playlist having a high degree of similarity by generating a recommended playlist by analyzing a reference playlist.

In addition, the present invention has an effect of providing a playlist desired by a user with high similarity accuracy by generating a similar recommended playlist using all or part of individual sound sources included in the reference playlist.

1 is a schematic block diagram of a music service providing system according to an embodiment of the present invention.
2 is a schematic block diagram of a music service providing apparatus for generating a recommended playlist according to an embodiment of the present invention.
3A and 3B are exemplary diagrams for explaining a screen and operation of a user terminal for generating and providing a recommended playlist according to an embodiment of the present invention.
4 is a flowchart illustrating a method of generating a recommended playlist in a music service providing apparatus according to an embodiment of the present invention.
5 is an exemplary diagram for explaining an operation of generating a recommended playlist based on a reference playlist according to an embodiment of the present invention.
6 is a schematic block diagram of a music service providing device implemented as a computing device according to an embodiment of the present invention.
7 is a diagram for explaining an operation of a playlist generating unit of a music service providing apparatus according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In describing the present invention, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description will be omitted. In addition, although preferred embodiments of the present invention will be described below, the technical idea of the present invention is not limited or limited thereto and can be modified and implemented in various ways by those skilled in the art. Hereinafter, a method for generating a recommended playlist proposed in the present invention and an apparatus therefor will be described in detail with reference to drawings.

1 is a schematic block diagram of a music service providing system according to an embodiment of the present invention.

A music service providing system according to this embodiment includes a music service providing apparatus 10 , a music service database 12 and a user terminal 20 . The music service providing system of FIG. 1 is according to an embodiment, and all blocks shown in FIG. 1 are not essential components, and some blocks included in the music service providing system may be added, changed, or deleted in another embodiment. there is.

The music service providing device 10 refers to a device that provides a music service by interworking with the user terminal 10 .

The music service providing apparatus 10 may basically provide a reference playlist according to a user's request and generate a recommended playlist similar to the reference playlist according to the user's request.

The music service providing device 10 retrieves data from all playlists stored in the music service database 12, provides a reference playlist to the user terminal 20, and generates a recommended playlist similar to the reference playlist to the user terminal. (20) can be provided.

The music service providing device 10 is described as providing a music service in conjunction with the music service database 12, but is not necessarily limited thereto, and provides a music service using a playlist stored in the music service providing device 10. may also provide. A detailed description of an operation of generating a recommended playlist in the music service providing apparatus 10 and providing a music service will be described in FIG. 2 .

The music service database 12 refers to a general data structure implemented in the storage space (hard disk or memory) of a computer system using a database management program (DBMS), and searches (extracts), deletes, edits, and adds data. It refers to a data storage format that can freely perform, such as Oracle, Informix, Sybase, and relational database management systems (RDBMS) such as DB2, Gemston, Orion One implementation of the present invention using object-oriented database management systems (OODBMS) such as (Orion) and O2 and XML Native Databases such as Excelon, Tamino, and Sekaiju. It can be implemented for the purpose of the example, and has appropriate fields or elements to achieve its function.

The music service database 12 according to the present embodiment may store data or information (eg, playlist, sound source, etc.) for providing music service, and provide the stored data and information to the music service providing apparatus 10. . Although the music service database 12 is described as a data storage device separate from the music service providing device 10, it is not necessarily limited thereto, such as a sound source service storage unit (not shown) in the music service providing device 10. It can also be implemented in a form.

The user terminal 20 includes a processor 21, a display 24 and a communication unit 26, and the music service application 22 may be driven by the processor 21.

The processor 210 may generate an action history by a user's action of listening to a sound source or selecting a menu through a display, and may generate preference input information input by the user.

The processor 210 works with a memory (not shown) that stores programs executed by the processor. The memory includes at least one instruction or program executable by the processor 210 . The memory may include instructions or programs for requirements for providing a music service. Also, the memory may include a command or program for generating a script for providing a music service.

The display 24 displays playback information (eg, name of a sound source, playing time of a sound source, etc.) for a reference playlist selected by the user, and a button for requesting creation of a recommended playlist similar to the reference playlist by the user. (touch area) may be provided.

The communication unit 26 may perform communication with the music service providing device 10 in order to select a standard playlist or request generation of a recommended playlist by a user's manipulation or input.

2 is a schematic block diagram of a music service providing apparatus for generating a recommended playlist according to an embodiment of the present invention.

The music service providing apparatus 10 according to the present embodiment includes a signal acquiring unit 210, a standard playlist providing unit 220, a playlist generating unit 230, and a recommended playlist providing unit 240. The music service providing device 10 of FIG. 2 is according to an embodiment, and all blocks shown in FIG. 2 are not essential components, and in another embodiment, some blocks included in the music service providing device 10 are added. , may be changed or deleted.

The signal acquisition unit 210 interworks with the user terminal 20 and performs an operation of obtaining various signals and information.

The signal acquisition unit 210 acquires a selection signal for providing a reference playlist from the user terminal 20 . Here, the selection signal means a signal requesting a playlist selected by the user among all previously stored playlists, and the selected playlist (reference playlist) is a playlist that can be provided through a music providing service, a predetermined recommendation method, or recommendation logic. It may be a playlist recommended to the user through , a playlist directly created by the user, and the like.

The signal acquisition unit 210 transmits a selection signal to the reference playlist providing unit 220 so that the reference playlist corresponding to the selection signal is provided to the user terminal 20 .

Meanwhile, the signal acquisition unit 210 may obtain a search request signal for a recommended playlist for a previously provided reference playlist from the user terminal 20 . Here, the search request signal means a signal for requesting a search for a playlist in order to receive a recommendation for a new playlist (recommended playlist) that is similar to or has something in common with the reference playlist.

The signal acquisition unit 210 transmits a search request signal to the playlist generator 230 so that a recommended playlist similar to the reference playlist is created.

The reference playlist providing unit 220 performs an operation of providing a reference playlist to the user terminal 20 .

The reference playlist providing unit 220 provides the user terminal 20 with a reference playlist corresponding to the selection signal received from the user terminal 20 . The standard playlist providing unit 220 extracts a standard playlist corresponding to a selection signal from among all playlists pre-stored in the music service database 12 and provides the extracted standard playlist to the user terminal 20 .

When a search request signal for a recommended playlist is received, the playlist generator 230 analyzes the reference playlist and creates a recommendation playlist similar to the reference playlist based on the analysis result. The playlist generating unit 230 according to the present embodiment includes a reference playlist analyzing unit 232 , a recommended playlist generating unit 234 and a recommended playlist sorting unit 236 .

The standard playlist analyzer 232 analyzes the standard playlist provided to the user terminal 20 in order to generate a recommended playlist.

The reference playlist analyzer 232 checks playlist information on the reference playlist. Here, the playlist information may include list attribute information such as title information, tag information, category information, popularity information, and recency information of the playlist.

Also, the reference playlist analyzer 232 checks reference sound source information for each individual sound source included in the reference playlist. Here, the reference sound source information may include song attribute information such as song title information, artist information, tag information, genre information, style information, popularity information, latest information, release year information, etc. for each individual sound source.

The recommended playlist generator 234 selects at least one sound source similar to the reference playlist from the entire list of pre-stored sound sources based on playlist information, reference sound source information, etc., and creates a recommended playlist.

The recommended playlist generating unit 234 creates at least one recommended playlist based on at least one attribute information included in the analysis result of reference sound source information.

The recommended playlist generator 234 checks at least one attribute information included in the reference sound source information and performs an operation of combining the at least one attribute information.

The recommended playlist generating unit 234 selects at least one sound source matching the combined attribute information from the entire list of sound sources and creates a recommended playlist. Here, the recommendation playlist generation unit 234 creates a plurality of different recommendation playlists for each combination of attribute information.

Specifically, the recommended playlist generator 234 includes at least one of song name information, artist information, tag information, genre information, style information, popularity information, recency information, and release year information for each individual sound source included in the reference sound source information. Combined attribute information may be generated by combining one piece of attribute information with each other.

The recommended playlist generating unit 234 recommends play using the combination attribute information generated by combining attribute information with a user preference score equal to or higher than a preset reference score based on the user preference score set for each of the at least one attribute information. create a list

The recommended playlist generating unit 234 may generate a plurality of candidate recommended playlists using the combination attribute information, and finally generate a recommended playlist according to a similarity with a reference playlist among the plurality of candidate recommended playlists. .

The recommendation playlist generator 234 compares individual sound sources of the reference playlist with individual sound sources of the candidate recommendation playlist, and calculates a degree of similarity for each of the candidate recommendation playlists.

The recommended playlist generator 234 according to the first embodiment compares each individual sound source included in the reference playlist with all individual sound sources included in each candidate recommendation playlist to calculate a similarity of at least one sound source, and calculates a similarity of at least one sound source. Calculate the similarity for each candidate recommendation playlist using the sound source similarity of .

The recommended playlist generator 234 according to the second embodiment matches each individual sound source included in the reference playlist with each individual sound source included in the arranged candidate recommendation playlist according to the arrangement order, and then generates the matched individual sound sources. The comparison is performed to calculate the similarity of at least one sound source, and the similarity for each candidate recommended playlist is calculated using the similarity of the at least one sound source.

The recommended playlist generator 234 compares the similarity of each candidate recommended playlist with a preset similarity criterion threshold, and selects the candidate recommended playlist as the final recommended playlist when the similarity is greater than or equal to the similarity criterion threshold.

Hereinafter, operations of the reference playlist analyzer 232 and the recommendation playlist generator 234 according to an embodiment of the present invention will be described in detail with reference to FIG. 7 . The playlist generator 230 of FIG. 7 is illustrated as including a reference playlist analyzer 232, a recommendation playlist generator 234, and a data storage unit 235, but is not necessarily limited thereto. A playlist sorting unit 236 may be additionally included.

In FIG. 7 , the original song list 700 , the property selection module 710 , and the original song list property 720 may be components for the operation of the standard playlist analyzer 232 . Also, the song candidate selection module 730 , the attribute filter module 740 , and the song similar list creation module 740 may be components for the operation of the recommendation playlist generator 234 . Also, a database for storing the meta data 760 , the model data 770 , and the aggregated data 780 may be a component for the operation of the data storage unit 235 .

The original song list 700 means an original song list (individual sound source list) of a reference playlist input to generate a recommended playlist.

The attribute selection module 710 performs an operation of specifying attribute information for the song original list 700 .

The attribute selection module 710 may use one or more attributes selected based on a request by a user's manipulation or input, or the attribute selection module 710 may automatically select one or more attributes according to a specific criterion.

The original song list attribute 720 is reference sound source information of the reference playlist selected by the attribute selection module 710, and refers to attribute information for generating a recommended playlist. One or more attribute values may be included in the song original list attribute 720, and one or more recommended playlists may be generated for one attribute.

The original song list attribute 720 may include song attribute information including meta data and sound source attribute information, song characteristic information defined through machine learning, data aggregated from listening logs, and the like.

For example, the original song list properties 720 include metadata such as song title information, artist information, tag information, and genre information for each individual sound source, sound source properties such as piano performance songs, other performance songs, music tempo, style information, It may include a plurality of attributes connected to sound source attribute information such as popularity information, recency information, release year information, and the like.

Also, the original song list attribute 720 may include combination attribute information in which two or more attributes are combined. For example, the original song list property 720 may include an acoustic sound source property combining a piano performance song and other performance song properties. In addition, the user directly selects the hip-hop genre so that a recommended playlist corresponding to the hip-hop genre is created, or the properties corresponding to the largest number of sound sources among various properties for each individual sound source included in the reference playlist are selected from the original list of songs. A recommended playlist may be created by including it in the attribute 720 or randomly including the attribute.

The song candidate selection module 730 performs an operation of selecting a candidate recommended playlist for generating a final recommended playlist. Candidate music sources of the candidate recommendation playlist may be selected from various sources. For example, the song candidate selection module 730 selects music charts, similar songs, similar artists, songs that are frequently listened to as derived based on machine learning, user's favorite songs, songs that the user has listened to a lot, and recommendations to the user. A candidate recommendation playlist can be created using all sound source lists that can be obtained by using a specific sound source, such as a song, as an original.

The attribute filter module 740 performs an operation of filtering sound sources included in the candidate recommendation playlist resulting from the song candidate selection module 730 .

The attribute filter module 740 may use the song original list attribute 700 as a basic filtering criterion, and add data 760, 770, 780 such as metadata, model, and aggregate acquired from the data storage unit 235. It can also be used to perform additional filtering. For example, the attribute filter module 740 excludes music sources that are in a service-unavailable state from the candidate recommendation playlist, excludes songs with too low a score of a model for recommendation to a specific user, or songs that the user has listened to less than a specific number of times. You can perform additional filtering, such as excluding.

The song similar list generation module 750 classifies the sound sources resulting from the attribute filter module 740 according to the original song list 700 and generates a final recommended playlist selected according to a specific criterion from each classified list. can

The song candidate selection module 730, the attribute filter module 740, and the song similar list generation module 740 shown in FIG. 7 are described as being implemented in stages, but are not necessarily limited thereto. It may be implemented as a single module or device that is integrated and performed.

The recommended playlist arranging unit 236 performs an operation of arranging at least one generated recommended playlist. Specifically, the recommendation playlist arranging unit 236 calculates a first comprehensive preference score for each of the generated at least one recommended playlist, and sorts the at least one recommended playlist based on the first comprehensive preference score. .

The recommended playlist sorting unit 236 transfers the sorted recommended playlists to the recommended playlist providing unit 240 so that at least one recommended playlist is provided according to the sorted order.

The recommended playlist arranging unit 236 generates a preferred action score by analyzing the behavior history collected for the reference playlist, generates a preferred input score using the preference input information input for the reference playlist, and generates a preferred action score. The score is used to generate a preferred prediction score.

The recommendation playlist arranging unit 236 calculates a second comprehensive preference score using at least one of a preference action score, a preference input score, and a preference prediction score.

The recommended playlist sorting unit 236 compares the first comprehensive preference score and the second comprehensive preference score for each of the at least one recommended playlist and sorts the at least one recommended playlist according to the determined priority.

3A and 3B are exemplary diagrams for explaining a screen and operation of a user terminal for generating and providing a recommended playlist according to an embodiment of the present invention.

Referring to FIGS. 3A and 3B , the user terminal 10 may output the music service provided from the music service providing device 10 through a user interface (UI) screen (hereinafter referred to as a terminal screen). there is.

Hereinafter, a manipulation operation for generating a recommended playlist will be described.

A previously provided reference playlist 320 is displayed on the screen of the terminal, and a touch area 310 for requesting creation of a recommended playlist based on the reference playlist 320 is provided.

When the user performs an input (eg, touch) on the touch area 310, the music service providing device 10 obtains a creation request signal from the user terminal 20, and recommends plays similar to the reference playlist 320. Create list 330. Here, the generation request signal may include information about the reference playlist 320 being output on the screen of the terminal.

The music service providing apparatus 10 checks at least one attribute information included in the analysis result of reference sound source information, performs an operation of combining at least one attribute information, and then matches the combined attribute information from the entire sound source list. A recommended playlist is created by selecting at least one sound source. Here, the music service providing apparatus 10 generates a plurality of different recommendation playlists 340 for each combination of attribute information.

The music service providing apparatus 10 sorts the plurality of recommended playlists 340 and provides the sorted plurality of recommended playlists 340 to the user terminal 20 .

A plurality of recommended playlists 340 generated for each combination of attribute information in which at least one attribute information for a reference sound source is combined may be displayed on the terminal screen of the user terminal 20 .

4 is a flowchart illustrating a method of generating a recommended playlist in a music service providing apparatus according to an embodiment of the present invention.

The music service providing apparatus 10 obtains a selection signal for a reference playlist from the user terminal 20 (S410).

The music service providing apparatus 10 provides a reference playlist corresponding to the selection signal to the user terminal (S420). A reference playlist corresponding to a selection signal may be extracted from among all playlists pre-stored in the music service database 12 and provided to the user terminal 20 .

The music service providing apparatus 10 obtains a request signal for generating a recommended playlist for the reference playlist from the user terminal 20 (S430). Here, the creation request signal means a signal requesting the creation of a playlist in order to receive a recommendation for a new playlist (recommended playlist) that is similar to or has something in common with the reference playlist.

The music service providing apparatus 10 analyzes the reference playlist based on the search request signal (S440). The music service providing apparatus 10 checks playlist information for a reference playlist and reference sound source information for each individual sound source included in the reference playlist. Here, the playlist information may include list attribute information such as title information, tag information, category information, popularity information, and recency information of the playlist, and the reference sound source information may include song title information for each sound source, artist information, Song property information such as tag information, genre information, style information, popularity information, latest information, and release year information may be included.

The music service providing apparatus 10 selects at least one sound source similar to the reference playlist from the entire previously stored sound source list based on the playlist information, reference sound source information, etc., and creates a recommended playlist (S450).

Specifically, the music service providing apparatus 10 checks at least one attribute information included in the analysis result of the reference sound source information, performs an operation of combining the at least one attribute information, and then combines attributes from the entire list of sound sources. A recommended playlist is created by selecting at least one sound source that matches the information. Here, the music service providing apparatus 10 generates a plurality of different recommendation playlists for each combination of attribute information.

Meanwhile, the music service providing apparatus 10 may further perform a step of arranging a plurality of recommended playlists in a random order or arranging a predetermined order by using a similarity to each recommended playlist.

The music service providing apparatus 10 provides the recommended playlist generated based on the reference playlist to the user terminal 20 (S460).

In FIG. 4, each step is described as sequentially executed, but is not necessarily limited thereto. In other words, since it will be applicable to changing and executing the steps described in FIG. 4 or executing one or more steps in parallel, FIG. 4 is not limited to a time-series sequence.

The method for generating a recommended playlist according to the present embodiment described in FIG. 4 may be implemented as an application (or program) and recorded on a recording medium readable by a terminal device (or computer). All types of recording media in which an application (or program) for implementing the method for generating a recommended playlist according to the present embodiment is recorded and which is readable by a terminal device (or a computer) stores data that can be read by a computing system. Including devices or media.

5 is an exemplary diagram for explaining an operation of generating a recommended playlist based on a reference playlist according to an embodiment of the present invention.

5 is a diagram for explaining an operation of generating a recommended playlist.

Referring to FIG. 5 , the music service providing device 10 checks at least one attribute information 510 included in the reference sound source information of the reference playlist 510, and combines the at least one attribute information to form a combined combination. Attribute information 520 is generated.

The music service providing apparatus 10 selects at least one sound source matching the combination attribute information 520 and generates a plurality of recommended playlists 530 . Here, the music service providing apparatus 10 generates a plurality of different recommendation playlists 530 for each combination of attribute information.

The music service providing device 10 calculates a total preference score for each of the plurality of recommended playlists 530, rearranges the plurality of recommended playlists 530 based on the calculated total preference score, and rearranges the recommended playlists. 540.

Thereafter, the music service providing apparatus 10 transfers the rearranged recommended playlist 540 to the user terminal 20 and provides a recommended playlist 550 similar to the reference playlist to the user.

6 is a schematic block diagram of a music service providing device implemented as a computing device according to an embodiment of the present invention.

6 is a block diagram illustrating and illustrating a music service providing apparatus 10 implemented as a computing device suitable for use in exemplary embodiments. In the illustrated embodiment, each component may have different functions and capabilities other than those described below, and may include additional components other than those described below. In one embodiment, the music service providing device 10 may be any type of computing device that transmits and receives signals with other terminals.

The music service providing apparatus 10 includes at least one processor 610, a computer readable storage medium 620, and a communication bus 660. The processor 610 may cause the music service providing apparatus 10 to operate according to the above-mentioned exemplary embodiment. For example, the processor 610 may execute one or more programs stored in the computer readable storage medium 620 . The one or more programs may include one or more computer executable instructions, which, when executed by the processor 610, cause the music service providing device 10 to perform operations according to an exemplary embodiment. can be configured to

Computer-readable storage medium 620 is configured to store computer-executable instructions or program code, program data, and/or other suitable form of information. The program 1030 stored in the computer readable storage medium 620 includes a set of instructions executable by the processor 610 . In one embodiment, computer readable storage medium 620 may include memory (volatile memory such as random access memory, non-volatile memory, or a suitable combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash It may be memory devices, other types of storage media accessible by the music service providing apparatus 10 and capable of storing desired information, or a suitable combination thereof.

The communication bus 660 interconnects various other components of the music service providing device 10, including the processor 610 and the computer readable storage medium 620.

The music service providing apparatus 10 may also include one or more input/output interfaces 640 and one or more communication interfaces 650 providing interfaces for one or more input/output devices (not shown). Input/output interface 640 and communication interface 650 are connected to communication bus 660 . An input/output device (not shown) may be connected to other components of the music service providing device 10 through an input/output interface 640 . Exemplary input/output devices include a pointing device (such as a mouse or trackpad), a keyboard, a touch input device (such as a touchpad or touchscreen), an input device such as a voice or sound input device, various types of sensor devices, and/or a photographing device; and/or output devices such as display devices, printers, speakers, and/or network cards. An exemplary input/output device (not shown) may be included inside the music service providing device 10 as a component constituting the music service providing device 10, or as a separate device distinct from the music service providing device 10. It may also be connected to a computing device.

The above description is only illustrative of the technical idea of the embodiment of the present invention, and those skilled in the art to which the embodiment of the present invention pertains may make various modifications and modifications within the scope not departing from the essential characteristics of the embodiment of the present invention. transformation will be possible. Therefore, the embodiments of the present invention are not intended to limit the technical idea of the embodiment of the present invention, but to explain, and the scope of the technical idea of the embodiment of the present invention is not limited by these examples. The protection scope of the embodiments of the present invention should be construed according to the claims below, and all technical ideas within the equivalent range should be construed as being included in the scope of the embodiments of the present invention.

10: music service provider 12: music service database
20: user terminal
210: signal acquisition unit 220: reference playlist providing unit
230: playlist generation unit 240: recommended playlist providing unit

Claims (10)

A method for generating a recommended playlist in a music service providing device interworking with a user terminal,
a signal acquisition step of acquiring a search request signal of a recommended playlist for a previously provided reference playlist from the user terminal;
an analysis step of analyzing reference sound source information for the reference playlist based on the search request signal;
a creation step of generating at least one recommended playlist based on at least one attribute information included in the analysis result of the reference sound source information; and
A providing step of providing the generated recommended playlist to the user terminal,
The analyzing step includes checking playlist information for the reference playlist and reference sound source information for each individual sound source included in the reference playlist;
In the generating step, based on the user preference score set for each of the at least one piece of attribution information, combined attribute information is generated by combining attribute information for which a user preference score equal to or higher than a preset reference score is set, and the generated combination attribute information is generated. A method of generating a recommended playlist, characterized in that a plurality of candidate recommended playlists are generated using a plurality of candidate recommended playlists, and the recommended playlist is generated according to a similarity between the plurality of candidate recommended playlists and the reference playlist. delete According to claim 1,
The generating step is
checking at least one attribute information included in the reference sound source information;
combining the at least one piece of attribute information;
selecting at least one sound source matching the combined attribute information from the entire list of sound sources; and
generating the recommended playlist for each combination of attribute information;
A method for generating a recommended playlist comprising a. According to claim 3,
The generating step is
At least one attribute information among song name information, artist information, tag information, genre information, style information, popularity information, recency information, and release year information for each individual sound source included in the reference sound source information is combined with each other, and the combined attribute A method for generating a recommended playlist, characterized in that generating information. According to claim 1,
a sorting step of calculating a first comprehensive preference score for each of the at least one recommended playlist and arranging the at least one recommended playlist based on the first comprehensive preference score;
Wherein the providing step provides the at least one recommended playlist according to a sorted order. According to claim 5,
The sorting step is
Preferred action scores are generated by analyzing collected action histories for the reference playlist, preferred input scores are generated using preference input information input for the reference playlist, and preferred prediction is made using the preferred action scores. generating a score, and calculating a second comprehensive preference score using at least one of the preference action score, the preference input score, and the preference prediction score;
and arranging the at least one recommended playlist according to a priority determined by comparing the first comprehensive preference score and the second comprehensive preference score for each of the at least one recommended playlist. . A music service providing apparatus including one or more processors and a memory storing one or more programs executed by the one or more processors, wherein the processor comprises:
a signal acquisition step of obtaining a search request signal for a recommended playlist for a previously provided reference playlist from a user terminal;
an analysis step of analyzing reference sound source information for the reference playlist based on the search request signal;
a creation step of generating at least one recommended playlist based on at least one attribute information included in the analysis result of the reference sound source information; and
Performing a providing step of providing the generated recommended playlist to the user terminal;
The analyzing step includes checking playlist information for the reference playlist and reference sound source information for each individual sound source included in the reference playlist;
In the generating step, based on the user preference score set for each of the at least one piece of attribution information, combined attribute information is generated by combining attribute information for which a user preference score equal to or higher than a preset reference score is set, and the generated combination attribute information is generated. A music service providing apparatus characterized in that a plurality of candidate recommended playlists are generated by using a playlist, and the recommended playlist is generated according to a similarity between the plurality of candidate recommended playlists and the reference playlist. According to claim 7,
The generating step may include checking at least one attribute information included in the reference sound source information; combining the at least one piece of attribute information; selecting at least one sound source matching the combined attribute information from the entire list of sound sources; and generating the recommended playlist for each of the combination attribute information. According to claim 7,
a sorting step of calculating a first comprehensive preference score for each of the at least one recommended playlist and arranging the at least one recommended playlist based on the first comprehensive preference score;
Wherein the providing step provides the at least one recommended playlist according to a sorted order. According to claim 9,
The sorting step is
Preferred action scores are generated by analyzing collected action histories for the reference playlist, preferred input scores are generated using preference input information input for the reference playlist, and preferred prediction is made using the preferred action scores. generating a score, and calculating a second comprehensive preference score using at least one of the preference action score, the preference input score, and the preference prediction score;
and arranging the at least one recommended playlist according to a priority determined by comparing the first comprehensive preference score and the second comprehensive preference score for each of the at least one recommended playlist.

Images