JP2021518003A - Growth graph-based playlist recommendation method and system - Google Patents

Abstract

Playlist provision including a step of constructing a plurality of playlists based on the similarity between music contents and a step of recommending the playlist by providing a tree graph in which each of the playlists is a node (node). Provide a method.

Description

The following description relates to a technique for recommending playlists.

For services that efficiently disseminate content and recommend content that suits the user's taste as the number of users who use the content increases by downloading the content to electronic devices and computers via the communication network or streaming it in real time. The demand is increasing.

As an example of the technology for recommending content, Korean Publication No. 10-2013-0008696 (publication date: January 23, 2013) contains a playlist of content that can be used by anyone by interacting with other users. The technology that can generate is disclosed.

It is possible to provide a playlist in the form of a graph having a plurality of nodes, which is a new recommendation method.

By providing a playlist in the form of a graph, it is possible to provide more choices and support for more active and chained consumption.

A playlist providing method performed by a computer system, wherein the computer system includes at least one processor configured to execute a computer-readable instruction contained in a memory, and the playlist providing method is described as described above. The playlists are configured by at least one processor at the stage of constructing a plurality of playlists based on the similarity between music contents, and by providing a tree graph having each of the playlists as a node by the at least one processor. Provide a method of providing a playlist, including a stage of recommending.

Provided is a non-temporary computer-readable recording medium in which a program for causing a computer to execute the playlist providing method is recorded.

A playlist providing system implemented by a computer system, comprising a memory and at least one processor connected to the memory and configured to execute computer-readable instructions contained in the memory, said at least. One processor recommends the playlist by providing a playlist component that constitutes a plurality of playlists based on the similarity between music contents, and a tree graph having each of the playlists as a node. Provide a playlist providing system including a providing unit.

It is a figure which showed the example of the network environment in one Embodiment of this invention. It is a block diagram for demonstrating the internal structure of an electronic device and a server in one Embodiment of this invention. It is a block diagram which showed the example of the component which the processor of the server can include in one Embodiment of this invention. It is a flowchart which showed the example of the method which a server can execute in one Embodiment of this invention. It is a flowchart which showed the example of the process of constructing a playlist in one Embodiment of this invention. It is explanatory drawing which showed the process of recommending a playlist by the graph of the tree shape which grows gradually in one Embodiment of this invention. It is explanatory drawing which showed the process of recommending a playlist by the graph of the tree shape which grows gradually in one Embodiment of this invention. It is explanatory drawing which showed the process of recommending a playlist by the graph of the tree shape which grows gradually in one Embodiment of this invention. It is explanatory drawing which showed the process of recommending a playlist by the graph of the tree shape which grows gradually in one Embodiment of this invention.

<Outline of the invention>
A playlist providing method performed by a computer system, wherein the computer system includes at least one processor configured to execute a computer-readable instruction contained in a memory, and the playlist providing method is described as described above. The playlists are configured by at least one processor at the stage of constructing a plurality of playlists based on the similarity between music contents, and by providing a tree graph having each of the playlists as a node by the at least one processor. Provide a method of providing a playlist, including a stage of recommending.

According to one aspect, the recommendation step may include expanding the node while adding at least one depth relative to the node selected from the tree graph.

According to another aspect, the recommendation step may include placing an initial playlist that reflects the user's preference for music content at the root node of the tree graph.

In addition, according to another aspect, in the stage of recommendation, the nodes of the tree graph are gradually expanded by consuming the playlists arranged in each node of the tree graph, and other playlists are additionally arranged. Further steps may be included.

According to another aspect, the recommendation step may include a step of visualizing the nodes of the playlist consumed by the user on the tree graph.

According to another aspect, the recommendation step may include marking and concatenating the nodes of the playlist consumed by the user on the tree graph to visualize the content consumption path of the user.

According to another aspect, the playlist providing method may further include the step of managing the data related to the user's consumption history for the playlist provided by the tree graph by the at least one processor.

According to another aspect, the constituent steps include a step of extracting sound source features preferred by the user using data related to the user's consumption history, and a song corresponding to the extracted sound source features. It may include the steps of constructing a personalized playlist.

According to another aspect, at the stage of composing the personalized playlist, a plurality of playlists having the characteristics of the sound source preferred by the user in common, but having the characteristics of some sound sources different from each other between the playlists. It may include the steps of constructing a personalized playlist.

According to still another aspect, the constituent steps are a step of learning the sound source data of the music content for each of the music contents based on the deep learning learning model to generate a unique sound source feature, and the sound source feature. May include a step of calculating the similarity between the music contents using the above and constructing the playlist based on the similarity between the music contents.

Provided is a non-temporary computer-readable recording medium in which a program for causing a computer to execute the playlist providing method is recorded.

A playlist providing system implemented by a computer system, comprising a memory and at least one processor connected to the memory and configured to execute computer-readable instructions contained in the memory, said at least. One processor recommends the playlist by providing a playlist component that constitutes a plurality of playlists based on the similarity between music contents, and a tree graph having each of the playlists as a node. Provide a playlist providing system including a providing unit.

<Details of the invention>
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

An embodiment of the present invention relates to a technique for recommending playlists, and more particularly to a technique for providing playlists in the form of a graph having a plurality of nodes.

Embodiments, including the matters specifically disclosed herein, can provide playlists in the form of graphs with multiple nodes, thereby efficiency, diversity, entertainment elements, convenience, and cost savings. It is possible to achieve considerable advantages in such aspects.

FIG. 1 is a diagram showing an example of a network environment according to an embodiment of the present invention. The network environment of FIG. 1 shows an example including a plurality of electronic devices 110, 120, 130, 140, a plurality of servers 150, 160, and a network 170. Such FIG. 1 is merely an example for explaining the invention, and the number of electronic devices and the number of servers are not limited as in FIG.

The plurality of electronic devices 110, 120, 130, 140 may be fixed terminals or mobile terminals realized by a computer system. Examples of a plurality of electronic devices 110, 120, 130, 140 include smartphones, mobile phones, navigation systems, PCs (personal computers), notebook PCs, digital broadcasting terminals, PDAs (Personal Digital Assistants), and PMPs (Tablet Multimedia Players). ), Tablets, game consoles, wearable devices, IoT (internet of things) devices, VR (visual reality) devices, AR (agged reality) devices, and the like. As an example, FIG. 1 shows a smartphone as an example of the electronic device 110, but in the embodiment of the present invention, the electronic device 110 substantially uses a wireless or wired communication method, and another via the network 170. It may mean one of a variety of physical computer systems capable of communicating with electronic devices 120, 130, 140 and / or servers 150, 160.

The communication method is not limited, and not only a communication method using a communication network that can be included in the network 170 (for example, a mobile communication network, a wired Internet, a wireless Internet, a broadcasting network, a satellite network, etc.), but also a device. Short-range wireless communication between them may be included. For example, the network 170 includes a PAN (personal area network), a LAN (local area network), a CAN (campus area network), a MAN (metropolitan area network), a WAN (wide network), etc. It may include any one or more of the networks. Further, network 170 may include, but is limited to, any one or more of network topologies, including bus networks, star networks, ring networks, mesh networks, star-bus networks, tree or hierarchical networks, and the like. Will not be done.

Each of the servers 150, 160 is realized by one or more computer devices that communicate with a plurality of electronic devices 110, 120, 130, 140 via a network 170 to provide instructions, codes, files, contents, services, and the like. good. For example, the server 150 may be a system that provides the first service to a plurality of electronic devices 110, 120, 130, 140 connected via the network 170, and the server 160 may also be a plurality of systems connected via the network 170. It may be a system that provides a second service to electronic devices 110, 120, 130, 140. As a more specific example, the server 150 is a service (as an example, a music service) intended by the application through an application which is a computer program installed and executed in a plurality of electronic devices 110, 120, 130, 140. Etc.) may be provided to a plurality of electronic devices 110, 120, 130, 140 as a first service. As another example, the server 160 may provide a service as a second service that distributes files for installing and executing the above-mentioned application to a plurality of electronic devices 110, 120, 130, 140.

FIG. 2 is a block diagram for explaining the internal configurations of the electronic device and the server according to the embodiment of the present invention. FIG. 2 describes the internal configuration of the electronic device 110 and the internal configuration of the server 150 as examples for the electronic device. Further, the other electronic devices 120, 130, 140 and the server 160 may have the same or similar internal configuration as the electronic device 110 or the server 150 described above.

The electronics 110 and server 150 may include memory 211,221, processors 212,222, communication modules 213 and 223, and input / output interfaces 214 and 224. The memories 211 and 221 are non-temporary computer-readable recording media, and are a RAM (random access memory), a ROM (read only memory), a disk drive, an SSD (solid state drive), and a flash memory (flash memory). Permanent mass recording devices such as, etc. may be included. Here, a permanent large-capacity recording device such as a ROM, SSD, flash memory, or disk drive may be included in the electronic device 110 or the server 150 as another permanent recording device that is separated from the memories 211 and 221. good. Further, the memory 211 and 221 are installed in the operating system and at least one program code (for example, a browser installed and executed in the electronic device 110, or installed in the electronic device 110 to provide a specific service. The code for the application etc.) may be recorded. Such software components may be loaded from a computer-readable recording medium separate from the memories 211 and 221. Such other computer readable recording media may include computer readable recording media such as floppy® drives, discs, tapes, DVD / CD-ROM drives, memory cards and the like. In other embodiments, software components may be loaded into memory 211 and 221 through communication modules 213 and 223 that are not computer readable recording media. For example, at least one program is a computer program installed by a file provided via network 170 by a file distribution system (eg, server 160 described above) that distributes developer or application installation files (eg, described above). It may be loaded into the memory 211 or 221 based on the application.

Processors 212 and 222 may be configured to process instructions in a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to processors 212 and 222 by memory 211, 221 or communication modules 213 and 223. For example, processors 212 and 222 may be configured to execute instructions received according to program code recorded in a recording device such as memory 211 and 221.

The communication modules 213 and 223 may provide a function for the electronic device 110 and the server 150 to communicate with each other via the network 170, and the electronic device 110 and / or the server 150 may provide another electronic device (as an example). , Electronic device 120) or another server (as an example, server 160). As an example, a request generated by the processor 212 of the electronic device 110 according to a program code recorded in a recording device such as a memory 211 may be transmitted to the server 150 via the network 170 under the control of the communication module 213. On the contrary, control signals, instructions, contents, files, etc. provided under the control of the processor 222 of the server 150 are received by the electronic device 110 through the communication module 213 of the electronic device 110 via the communication module 223 and the network 170. May be done. For example, control signals, instructions, contents, files, etc. of the server 150 received through the communication module 213 may be transmitted to the processor 212 and the memory 211, and the contents, files, etc. may be further included in the electronic device 110. It may be recorded on a medium (permanent recording device described above).

The input / output interface 214 may be a means for an interface with the input / output device 215. For example, an input device may include a device such as a keyboard, mouse, microphone, camera, and an output device may include a device such as a display, speaker, haptic feedback device, and the like. As another example, the input / output interface 214 may be a means for an interface with a device such as a touch screen in which functions for input and output are integrated into one. The input / output device 215 may be composed of an electronic device 110 and one device. Also, the input / output interface 224 of the server 150 may be a means for connecting to the server 150 or for interfacing with an input or output device (not shown) that the server 150 can include. As a more specific example, when the processor 212 of the electronic device 110 processes an instruction of a computer program loaded in the memory 211, a service screen or content configured by using data provided by the server 150 or the electronic device 120. May be displayed on the display through the input / output interface 214.

Also, in other embodiments, the electronic device 110 and the server 150 may include more components than the components of FIG. However, it is not necessary to clearly illustrate most of the prior art components. For example, the electronic device 110 may be realized to include at least a part of the above-mentioned input / output device 215, such as a transceiver, a GPS (Global Positioning System) module, a camera, various sensors, a database, and the like. Other components may be further included. As a more specific example, when the electronic device 110 is a smartphone, an acceleration sensor or gyro sensor, a camera module, various physical buttons, buttons using a touch panel, an input / output port, which are generally included in the smartphone, Various components, such as a vibrating device for vibration, may be realized to be further included in the electronic device 110.

Hereinafter, a method of providing a playlist in the form of a graph having a plurality of nodes and a specific embodiment of the system will be described.

In the present specification, the playlist means music contents to be recommended, and may mean a track collection consisting of at least one music contents having common characteristics.

In the past, independent playlists were provided in the form of single-shot recommendations, so most of them were limited to single-shot consumption. The present invention allows users to have more choices for playlists by recommending playlists in a tree graph with multiple nodes, allowing for more active and chained consumption. Can be supported.

FIG. 3 is a block diagram showing an example of components that the processor of the server can include in one embodiment of the present invention, and FIG. 4 is a block diagram of what the server executes in one embodiment of the present invention. It is a flowchart which showed the example of the possible method.

The server 150 according to the present embodiment serves as a platform for providing music services to a plurality of electronic devices 110, 120, 130, 140 which are clients. The server 150 may provide music services in conjunction with applications installed on the electronic devices 110, 120, 130, 140.

As shown in FIG. 3, the processor 222 of the server 150 includes a playlist component 310, a playlist provider 320, and a consumption history management unit 330 as components for executing the playlist providing method according to FIG. May include. Depending on the embodiment, the components of processor 222 may be selectively included or excluded from processor 222. Also, depending on the embodiment, the components of processor 222 may be separated or merged to represent the functionality of processor 222.

Such processors 222 and components of the processor 222 may control the server 150 to perform steps 410-440 included in the playlist providing method of FIG. For example, the processor 222 and the components of the processor 222 may be implemented to execute instructions by the operating system code contained in the memory 221 and the code of at least one program.

Here, the components of the processor 222 may be representations of different functions of the processors 222 that are executed by the processor 222 according to the instructions provided by the program code recorded in the server 150. For example, the playlist configuration unit 310 may be used as a functional representation of the processor 222 that controls the server 150 according to the instructions described above so that the server 150 constitutes a playlist.

At step 410, processor 222 may read the required instructions from memory 221 loaded with instructions associated with control of server 150. In this case, the read instruction may include an instruction for controlling the processor 222 to execute steps 420 to 440 described below.

At step 420, the playlist component 310 may configure a plurality of playlists of similar music content based on the degree of similarity between the music content. In the present invention, the recommended playlist may be provided as each node of the tree graph by using the user interface in the form of a tree graph in order to provide more options in the process of recommending the playlist. At this time, the playlist component unit 310 may configure a playlist personalized to the user based on the data related to the user's consumption history for the music content (hereinafter referred to as "consumption history data"). The playlist component unit 310 may use the user's consumption history data to extract sound source features preferred by the user, and may configure a personalized playlist with songs corresponding to the extracted sound source features. At this time, the sound source feature may mean a parameter that determines the feature of the music content such as an album, an artist, a genre, a beat, etc., as well as a melody. The playlist component 310 will form a plurality of personalized playlists by songs having sound source characteristics preferred by the user based on the similarity between the music contents. The playlists may have some similarity and at the same time have appropriate discrimination. In other words, the playlist component unit 310 may configure a plurality of personalized playlists in which some sound source features are different from each other while having the sound source features that the user prefers in common. For example, the playlist component 310 may generate playlists with songs of the same genre as the user's preferred genre, but at this time, playlists with different beats may be generated.

As an example, the playlist component unit 310 may configure a playlist by using a learning model based on deep learning. FIG. 5 is a flowchart showing an example of a process of constructing a playlist in one embodiment of the present invention.

In step 501, the playlist configuration unit 310 may receive input of sound source data of music content for each music content, and process the input sound source data in the form of learning data. At this time, the music content may mean all digital data having an audio file format, and may include, for example, MP3 (MPEG AudioLayer-3), WAVE (Waveform AudioFormat), FLAC (Free Lossless AudioCodec), and the like. .. Further, the playlist component 310 may also receive input of text information related to the music content, but at this time, the text information may include lyrics or such as a singer, a genre, a song title, an album name, and the like. It may include meta information, or information such as hash tags and queries entered in connection with the classification and search of music content. Subsequently, the playlist component 310 may express the sound source data in time-frequency by preprocessing. For example, the playlist component 310 may convert the sound source data into time-frequency-size form data such as Mel-Spectrogram or MFCC (Mel Frequency Cepstrum). Further, the playlist component 310 may preprocess the text information when the text information is input to the music content together. As an example, the playlist component 310 may filter meaningless text from the input text information using a language preprocessing unit such as a morphological analyzer, an index term extractor, and the like. In other words, the playlist component 310 removes unnecessary part-speech words such as particles and auxiliary verbs contained in the text information and special symbols (for example,!,?, / Etc.), and corresponds to an uninflected word or a root. Words may be extracted.

In step 502, the playlist component 310 trains the training data preprocessed with respect to the sound source data based on the learning model to generate unique features, and then stores the generated unique features in a database (shown). You may record it in. The playlist component 310 may generate unique acoustic features of the sound source data itself based on deep learning. As an example, the playlist component 310 may utilize a learning model based on a CNN (Convolutional Neural Network). The playlist component 310 may express the sound source data as a multidimensional real number vector by using the CNN learning model. The CNN learning model may include a sound source data learning layer, and the following steps 1 to 3 may be examples of a process of generating a real number vector corresponding to the sound source data in the sound source data learning layer.

In step 1, the sound source data of the music content (for example, an mp3 file) may be converted into time-frequency-size form data such as a mel spectrogram or MFCC by preprocessing.

In step 2, a plurality of frequency frames in one or more short time intervals (1 to 10 seconds) are sampled from the converted sound source data and used as input data for the learning model of the sound source data. For example, the playlist component 310 may be used as an input of a CNN model presented as a sample of a music model in the sound source data learning layer by sampling a plurality of frames. As a result, the CNN model for learning the sound source data becomes a model having the same number of channels as the number of sampled frames. Alternatively, each generated frame is used as a single channel, and after each frame undergoes a unique convolution / pooling process, the generated frame-specific feature vectors are joined to serve as an input for the fully connected layer. It can also be used.

In process 3, a plurality of convolutions and pooling layers included in the sound source data learning layer may be repeatedly configured to generate abstract features from the music frame. The patch size may be varied in the convolution, and the pooling is also multiple pooling, such as the pooling technique using the maximum value, the pooling technique using the average value, and the hybrid pooling technique that combines the two pooling techniques. At least one of the techniques may be used.

On top of multiple convolution and pooling layers are fully connected layers for generating acoustic features, and the functions for each layer are the sigmoid function, the hyperbolic tangent (tanh) function, and the ReLU (Rectifier Liner Unit). ) Various functions such as functions may be used. Eventually, one multidimensional real number vector will be generated for the sound source data. For example, the given first sound source data m0 is one multidimensional real number vector in the output layer of the music learning model as in the form of x0 = {0.2, -0.1, 0.3, ...}. It may be expressed by.

Further, when the playlist component unit 310 receives both input of text information for the music content, the text information may also be expressed by a multidimensional real number vector. As an example, the playlist component 310 may generate text filtered by preprocessing on text information as a language vector using a pre-learned learning model. For example, a language vector may be represented in the form of a numeric multidimensional vector. A word occurrence frequency histogram, TF (term frequency) / IDF (inverse document fraction), language learning model (for example, word2vec, phase2vec, document2vec, etc.) may be used to generate the language vector. For example, a singer / genre / song title / year such as "Lee Seung Hwan Good Day Ballad 1992" is one n-dimensional real number vector v = {0.3, -1.2, 1.2, ...}. Can be expressed in. At this time, the order of the text information fields (singer, genre, song title, year, etc.) for the language learning model is not fixed, and can be changed to suit the purpose.

The playlist component 310 described above may record and maintain a feature vector for sound source data and a language vector for text information in a database for each music content. The feature vector for the sound source data and the language vector for the text information may be constructed in separate databases, or may be constructed in one database. Such a database may be realized as a component included in the server 150, or may exist as an external database built on a separate system that can be linked with the server 150.

In step 503, the playlist component 310 may calculate the similarity between sound sources for each music content using the unique characteristics of the sound source data recorded in the database, based on the similarity between the sound sources. A playlist for music content may be automatically configured. As an example, the playlist component 310 may calculate the similarity between sound sources by using the feature vector for the sound source data, and as another example, the feature vector for the sound source data and the language vector for the text information are combined. It may be used to calculate the similarity between sound sources. At this time, the playlist component 310 uses at least one of the songs recently consumed by the user or the songs currently consuming by the user as the seed song, and is similar to the seed song. The playlist may be configured indefinitely depending on the chain form with. Further, the playlist composition unit 310 may compose a playlist with songs preferred by the user based on the user's consumption history data for the music content.

Therefore, the present invention can automatically compose a playlist with similar songs based on the similarity between music contents using a model in which sound source data of music contents and text information are learned.

Again, in FIG. 4, at stage 430, the playlist provider 320 may recommend playlists by providing a tree graph with each of the playlists configured in stage 420 as a node. The playlist provider 320 may recommend a playlist by a tree graph in which the depth and the number of nodes are fixed in advance, and as another example, at least one based on the nodes of the playlist selected from the tree graph. Playlists may be recommended by gradually expanding the nodes by adding one or more depths. At this time, the playlists of the nodes connected to each other have similarities with each other and at the same time have a certain degree of discrimination. For example, the playlist provider 320 arranges playlists of songs of the same genre as the user's preference on each node, but at this time, the playlists of each node are composed of songs having different beats. good.

Referring to FIG. 6, the initial playlist S is arranged as the root node of the tree graph 600, and the initial playlist S may be a playlist that reflects the user preference. As an example, the playlist S of the root node may be composed of sound source features extracted from the user's consumption history data accumulated within a certain period of time in recent years, that is, songs corresponding to the sound source features preferred by the user. ..

The playlist providing unit 320 may recommend a playlist in the form of starting from the root node and expanding the nodes of the tree graph 600. Referring to FIG. 7, the playlist configuration unit 310 uses the playlist S of the root node as a reference when the user is consuming the playlist S of the root node or when the consumption is completed. IV may be configured. At this time, the playlist providing unit 320 extends the child node from the root node of the tree graph 600 when a certain time (for example, one day) elapses after the user completes the consumption of the playlist S of the root node. Then, playlists I to IV newly configured as extended nodes may be additionally arranged.

Further, referring to FIG. 8, the playlist configuration unit 310 is newly added in the tree graph 600 while the user is consuming any one of the playlists I to IV or when the consumption is completed. Playlists V to XI are configured, and the playlist provider 320 expands the nodes of the tree graph 600 after a certain period of time (for example, one day) has passed since the consumption of the previous playlist was completed. , Playlists V to XI newly configured as extended nodes may be additionally placed.

For example, referring to FIGS. 6 to 8, the node of the tree graph 600 may be expanded and new playlists I to IV may be additionally arranged on the day after the initial playlist S is consumed. If playlist II is consumed in the tree graph 600 in which playlists I to IV are additionally arranged, the child node for new playlist recommendation is expanded from the playlist II node the next day, and the play is performed. Once Listing III is consumed, the next day, child nodes for new playlist recommendations may be extended from the Playlist III node. In this way, in addition to expanding the nodes in the order in which the playlists are consumed, if any one of the playlists I to IV is consumed, the corresponding node on the next day. Child nodes may be extended from adjacent nodes of the same depth as, or child nodes may be extended from all nodes of the same depth at once. The rules and order of node expansion of the tree graph 600 can be changed as much as possible.

Therefore, it is possible to provide more choices by recommending playlists using a gradually growing tree-shaped graph, and to provide an entertainment element by gradually growing the tree graph.

Playlists of nodes connected to each other have similarities to each other and at the same time have some degree of discrimination, but child nodes derived from one parent node also have some degree of similarity and discrimination. ..

The user consumes the recommended playlist while freely moving the nodes in the tree graph 600. At this time, the playlist provider 320 visually displays the history for the playlist consumed by the user on the tree graph 600. It may be transformed into. At this time, the playlist providing unit 320 may visualize the content consumption route by marking and concatenating the playlist nodes consumed by the user in the tree graph 600. As shown in FIG. 9, the playlist providing unit 320 sets the nodes of the playlist (for example, S, II, III, VI, IX) consumed by the user on the tree graph 600 with other nodes that are not consumed. It may be displayed separately.

Again in FIG. 4, at step 440, the consumption history management unit 330 may manage data related to the user's consumption history for the playlist provided in the tree graph. The consumption history management unit 330 may record and manage the music playback log of each user who uses the music service as consumption history data. The consumption history data includes information about playlists consumed by the user, and for each playlist, the identifier of the corresponding playlist (for example, ID), the number of times the corresponding playlist has been played, and the corresponding Percentage of playback that indicates how much of the total playback time of a playlist has been played, user feedback on the playlist (for example, user reaction such as "like" or "favorite" registration), Whether or not the playlist can be played continuously, the time when the playlist was consumed, the user position, and the like may be included. At this time, in the case of a user who has consented to the collection of position information in advance, the position may be automatically collected from the electronic device 110 of the user. In addition, the consumption history management unit 330 records and manages metadata information of songs included in playlists consumed by the user, for example, metadata including song identifiers, album information, artist information, and genre information as consumption history data. It's okay. In addition, the consumption history management unit 330 records and manages external information related to the playlist consumed by the user, for example, the weather at the time when the playlist was consumed, social issues, etc. as consumption history data. good. The above-mentioned consumption history data may be utilized for analyzing the consumption pattern of the user with respect to the playlist, and in particular, may be utilized for personalizing and composing the playlist in the playlist configuration unit 310. To further refine playlist recommendations by collecting consumption history data for playlists consumed by users using a tree graph and using this for the composition of playlists in the next recommendation process. Can be done.

Even if the user does not give direct feedback to the recommended playlist, detailed and elaborate feedback data can be collected by an indirect method using a tree graph, which can be used to show the user's consumption history and behavior. Since it can be easily grasped, it can be used to compose a playlist personalized to the user.

The devices described above may be implemented by hardware components, software components, and / or combinations of hardware components and software components. For example, the devices and components described in the embodiments include a processor, a controller, an ALU (arithmetic logic unit), a digital signal processor, a microcomputer, an FPGA (field programgate array), a PLU (programmable log unit), a microprocessor, and the like. Alternatively, it may be implemented using one or more general purpose computers or special purpose computers, such as various devices capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the OS. The processing device may also respond to the execution of the software, access the data, and record, manipulate, process, and generate the data. For convenience of understanding, one processor may be described as being used, but one of ordinary skill in the art may appreciate that the processor may include multiple processing elements and / or multiple types of processing elements. You can understand. For example, the processing device may include multiple processors or one processor and one controller. Other processing configurations, such as parallel processors, are also possible.

The software may include computer programs, code, instructions, or a combination of one or more of these, configuring the processing equipment to operate at will, or instructing the processing equipment independently or collectively. You may do it. The software and / or data is embodied in any type of machine, component, physical device, computer recording medium or device to be interpreted based on the processing device or to provide instructions or data to the processing device. good. The software is distributed on a networked computer system and may be recorded or executed in a distributed state. The software and data may be recorded on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed by various computer means and recorded on a computer-readable medium. Here, the medium may be a continuous recording of a computer-executable program or a temporary recording for execution or download. Further, the medium may be various recording means or storage means in the form of a combination of a single piece of hardware or a plurality of pieces of hardware, and is not limited to a medium directly connected to a certain computer system, and is distributed on a network. It may exist. Examples of media include hard disks, floppy (registered trademark) disks, and magnetic media such as magnetic tape, optical media such as CD-ROMs and DVDs, opto-magnetic media such as floppy disks, and ROMs, RAMs. It may be configured to record program instructions, including a flash memory and the like. Other examples of media include recording media or storage media managed by application stores that distribute applications, sites that supply or distribute various other software, servers, and the like.

As described above, the embodiments have been described based on the limited embodiments and drawings, but those skilled in the art will be able to make various modifications and modifications from the above description. For example, the techniques described may be performed in a different order than the methods described, and / or components such as the systems, structures, devices, circuits described may be in a form different from the methods described. Appropriate results can be achieved even if they are combined or combined, or confronted or replaced by other components or equivalents.

Therefore, even if the embodiments are different, they belong to the attached claims as long as they are equal to the claims.

The embodiment of the present invention further solves the following problems.

By providing playlists in a gradually growing tree-shaped graph, game-like elements can provide ancillary enjoyment.

It supports consuming playlists while freely moving the nodes of the growth graph, and can effectively visualize the user's consumption history on the growth graph.

It is possible to easily grasp the form of consuming the playlist while moving the nodes of the growth graph, and it is possible to further refine the recommendation of the playlist based on the form of consumption by the growth graph.

Claims (20)

It is a playlist providing method executed by a computer system.
The computer system includes at least one processor configured to execute computer-readable instructions contained in memory.
The playlist providing method is
The play by providing a stage of constructing a plurality of playlists based on the similarity between music contents by the at least one processor, and providing a tree graph having each of the playlists as a node by the at least one processor. How to serve playlists, including the stage of recommending lists. The recommended stage is
The playlist providing method according to claim 1, further comprising a step of expanding a node while adding at least one depth based on a node selected from the tree graph. The recommended stage is
The playlist providing method according to claim 1, further comprising a step of arranging an initial playlist reflecting a user's preference for music content at the root node of the tree graph. The recommended stage is
The third aspect of claim 3, further comprising a step of gradually expanding the nodes of the tree graph by consuming the playlists arranged in each node of the tree graph and additionally arranging other playlists. How to provide playlists. The recommended stage is
The playlist providing method according to claim 1, further comprising a step of visualizing a playlist node consumed by a user on the tree graph. The recommended stage is
The playlist providing method according to claim 1, further comprising a step of marking and concatenating the nodes of the playlist consumed by the user on the tree graph to visualize the content consumption route of the user. The playlist providing method is
The playlist providing method according to claim 1, further comprising a step of managing data related to a user's consumption history for the playlist provided in the tree graph by the at least one processor. The constituent steps are
This includes a step of extracting sound source features preferred by the user using data related to the user's consumption history, and a step of constructing a personalized playlist with songs corresponding to the extracted sound source features. The playlist providing method according to claim 7. The steps to compose the personalized playlist are:
The playlist provided according to claim 8, which includes a step of forming a plurality of personalized playlists in which some sound source characteristics are different from each other while having the sound source characteristics preferred by the user in common. Method. The constituent steps are
For each of the music contents, a step of learning the sound source data of the music contents based on the deep learning learning model to generate unique sound source features, and calculating the similarity between the music contents by using the sound source features. The method for providing a playlist according to claim 1, wherein the playlist is formed based on the degree of similarity between the music contents. A non-temporary computer-readable recording medium, wherein a program for causing a computer to execute the playlist providing method according to any one of claims 1 to 10 is recorded. A playlist providing system realized by a computer system
Includes memory and at least one processor connected to said memory and configured to execute computer-readable instructions contained in said memory.
The at least one processor
Includes a playlist component that composes a plurality of playlists based on the similarity between music contents, and a playlist provider that recommends the playlist by providing a tree graph having each of the playlists as a node. Playlist providing system. The playlist provider
The playlist providing system according to claim 12, further comprising expanding a node while adding at least one depth based on a node selected from the tree graph. The playlist provider
The playlist providing system according to claim 12, wherein an initial playlist reflecting a user's preference for music content is arranged at the root node of the tree graph. The playlist provider
14. The fourth aspect of claim 14, wherein the playlists arranged in each node of the tree graph are gradually expanded by consuming the playlists arranged in each node of the tree graph, and other playlists are additionally arranged. Playlist providing system. The playlist provider
The playlist providing system according to claim 12, wherein the playlist node consumed by the user is visualized on the tree graph. The playlist provider
The playlist providing system according to claim 12, wherein the playlist nodes consumed by the user are marked and concatenated on the tree graph to visualize the content consumption route of the user. The at least one processor
The playlist providing system according to claim 12, further comprising a consumption history management unit that manages data related to the user's consumption history for the playlist provided by the tree graph. The playlist component
Using the data related to the user's consumption history, the sound source features preferred by the user are extracted.
The playlist providing system according to claim 18, wherein a personalized playlist is composed of songs corresponding to the extracted sound source characteristics. The playlist component
The play according to claim 19, wherein a plurality of personalized playlists having some sound source characteristics different from each other are formed between playlists while having the sound source characteristics preferred by the user in common. List providing system.

Images