Music playing device, music provision device, and music playing program
The artwork search function in music management systems addresses the challenge of song retrieval by using machine learning to extract and link artwork features, enabling effective song retrieval without knowing the title or artist name.
Patent Information
- Application Number
- PCT/JP2024/028679
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2026-02-12
AI Technical Summary
Existing song search functions in music management systems are inadequate when users cannot remember the song title or artist name, making it difficult to find desired songs.
Implementing an artwork search function that utilizes object and color features of music artwork, using machine learning for image recognition to extract object tags and color tags, and linking these features to a database for searching and retrieving matching songs.
Enables users to search for songs based on remembered artwork characteristics, even if they cannot recall the song title or artist name, thereby improving song retrieval efficiency.
Smart Images

Figure JP2024028679_12022026_PF_FP_ABST
Abstract
Description
Music playback device, music providing device, and music playback program
[0001] The present invention relates to a music playback device, a music providing device, and a music playback program.
[0002] Music management software, streaming services, music sales services, and other services offer song search functions that allow users to search for songs that match search keywords such as song titles and artist names, in order to help users find the songs they are looking for.
[0003] Patent No. 6421130
[0004] However, the above-described song search function leaves room for improvement in that if the user does not remember the song title or artist name, the user cannot search for the desired song.
[0005] In one aspect, an object is to provide a music playback device, a music providing device, and a music playback program that are capable of realizing artwork search.
[0006] One aspect of the music playback device includes a reception unit that receives artwork features as a search query, a search unit that searches a database in which music artwork and the features of the artwork are linked and registered to search for artwork corresponding to the features received as the search query, and an output control unit that outputs the search results by the search unit.
[0007] According to one embodiment, artwork searching may be provided.
[0008] FIG. 1 is a diagram showing an example of the functional configuration of a music playback device. FIG. 2 is a diagram (1) showing one aspect of a problem-solving approach. FIG. 3 is a diagram (2) showing one aspect of the problem-solving approach. FIG. 4 is a schematic diagram showing an example of object tag extraction. FIG. 5 is a schematic diagram showing an example of color tag extraction. FIG. 6 is a diagram showing an example of a search palette. FIG. 7 is a diagram showing an example of an artwork search screen. FIG. 8 is a diagram showing an example of the results of generating major classification tags. FIG. 9 is a diagram (1) showing an example of a display of search results. FIG. 10 is a diagram (2) showing an example of a display of search results. FIG. 11 is a flowchart showing the procedure for registration processing. FIG. 12 is a flowchart showing the procedure for search processing. FIG. 13 is a diagram showing an example of the functional configuration of a music providing device. FIG. 14 is a diagram showing an example of a hardware configuration.
[0009] Hereinafter, a description will be given of a music playback device, a music providing device, and a music playback program (hereinafter referred to as "embodiments") according to the present disclosure with reference to the accompanying drawings. Note that the embodiments merely illustrate one example or one aspect, and the following description does not limit the structure, operation, function, properties, characteristics, methods, uses, etc. according to the present disclosure.
[0010] <First Embodiment> <Overall Configuration> Fig. 1 is a diagram showing an example of the functional configuration of a music playback device 10. Fig. 1 shows an example of a music playback device 10 that provides a music playback function for DJing music managed in a library by DJ (Disc Jockey) software and music distributed by a streaming service such as music distribution.
[0011] In one aspect, the music playback device 10 may be realized by an audio device having a music playback function or a playback control function for DJs, such as a DJ player or a DJ mixer, or a DJ controller such as a DJ system that integrates these. In another aspect, the music playback device 10 may be realized by a user terminal, such as a personal computer or a mobile terminal, on which DJ software is installed.
[0012] <Library> As part of the music management function provided by the DJ software, a library listing the collection of songs imported into the DJ software may be created in the music playback device 10 or in cloud storage, independent of the music content data files. Note that the library may include not only individual songs but also albums, playlists, etc.
[0013] <One aspect of the problem> As explained in the background art section above, the above song search function has room for improvement in that if the user does not remember the song title or artist name, the user cannot search for the desired song.
[0014] For example, some DJ software users may have libraries with tens of thousands of songs, and it is unrealistic to require users to remember the names of individual songs and artists for such a large number of songs.
[0015] <One Aspect of the Problem-Solving Approach> Therefore, in this embodiment, a problem-solving approach is adopted that realizes an artwork search function that uses feature quantities of artwork of music pieces, such as objects and colors.
[0016] When users try to search for music in their library, they often find it difficult to remember the song title or artist name. However, even if they cannot remember the song title or artist name, they can still remember the artwork, such as the composition and colors of the artwork on the jacket image. This is because the impact of artwork on users is so strong that there is a phenomenon known as "cover buying."
[0017] Figure 2 is a diagram (1) showing one aspect of the problem-solving approach. For example, in the example shown in Figure 2, there are many situations where user U1 can only remember that the jacket is red and has a dog-like animal in the middle. However, even if the above-mentioned song search function is used, user U1 cannot remember the song title or artist name, so the above-mentioned song search function is unable to help.
[0018] From this perspective, the artwork search function allows users to search for the desired artwork by entering the objects and colors depicted in the artwork as a search query.
[0019] Fig. 3 is a diagram (2) showing one aspect of the problem-solving approach. For example, in the example shown in Fig. 3, by inputting an object included in artwork AW1, such as "animal," "dog," "star," or "ribbon," or a color pattern corresponding to color c1, color c2, color c3, or color c4, or a combination thereof, as a search query, artwork AW1 is found.
[0020] By realizing such an artwork search function, it becomes possible for a user who does not remember the song title or artist name to search for the desired song.
[0021] <Configuration of music playback device 10> Next, the functional configuration of the music playback device 10 according to this embodiment will be described. For example, Fig. 1 shows a block diagram of functions related to the music playback function of the music playback device 10. As shown in Fig. 1, the music playback device 10 has an input unit 11, an output unit 12, a storage unit 13, and a control unit 15. Note that Fig. 1 only shows an excerpt of the functional units related to the music playback function, and the music playback device 10 may also be provided with functional units other than those shown.
[0022] The input unit 11 is a functional unit that accepts various instruction inputs. In one embodiment, when the music playback device 10 is realized by a personal computer, the input unit 11 may be realized by general-purpose peripheral devices such as a keyboard and a mouse.
[0023] The output unit 12 is a functional unit that outputs various types of information. In one embodiment, the output unit 12 may be realized as a display unit using a liquid crystal display, an organic EL (Electro Luminescence) display, or the like. In another embodiment, the output unit 12 may be realized as an audio output unit using a speaker or a speaker unit having multiple speakers.
[0024] The input unit 11 and the output unit 12 may be integrated into a display input unit realized by a touch panel or the like.
[0025] The storage unit 13 is a functional unit that stores various types of data. In one embodiment, the storage unit 13 may be realized by internal, external, or auxiliary storage of the music playback device 10. For example, the storage unit 13 stores a library 13A and a tag DB (DataBase) 13B. The data in the library 13A and the tag DB 13B will be described later together with the scenes in which each data is referenced or registered.
[0026] The control unit 15 is a functional unit that performs overall control of the music playback device 10. For example, the control unit 15 can be realized by a hardware processor. As shown in Fig. 1, the control unit 15 has a feature extraction unit 15A, a registration unit 15B, a reception unit 15C, a search unit 15D, and an output control unit 15E. Note that the control unit 15 may also be realized by hardwired logic or the like.
[0027] The feature extraction unit 15A is a processing unit that extracts features of artwork. In one aspect, the feature extraction unit 15A can start processing when a new song is imported into the collection of the library 13A managed by the song management function of the DJ software.
[0028] In one aspect, the feature extraction unit 15A can extract an object drawn in the artwork as one of the feature quantities of the artwork. In this case, the feature extraction unit 15A can recognize the object drawn in the artwork using a machine learning model that performs an image recognition task. An example of such a machine learning model is a Recognize Anything Model (RAM), which takes an image as input and outputs a bounding box indicating the location of an object in the image, an object tag, and a tag confidence level. Hereinafter, an object tag may be referred to as an "object tag."
[0029] 4 is a schematic diagram showing an example of object tag extraction. As shown in FIG. 4, the feature extraction unit 15A inputs artwork AW1 into the RAM 20, thereby obtaining object tags such as "animal," "art," "bobcat," "dog," "star," "mouth," and "poster" output by the RAM 20. In this way, object tags output by the RAM 20 can be narrowed down to those with a certainty factor of a threshold value, for example, 0.7, and used for artwork search.
[0030] In another aspect, the feature extraction unit 15A can extract the color contained in the artwork as one of the feature quantities of the artwork.
[0031] 5 is a schematic diagram showing an example of color tag extraction. As shown in FIG. 5, the feature extraction unit 15A extracts pixel values of colors c1, c2, c3, and c4 contained in artwork AW1. It goes without saying that the extracted pixel values can be expressed in any color space, such as the RGB color system, which expresses values using a combination of red, green, and blue, or the HSV color system, which expresses values using a combination of hue, saturation, and brightness.
[0032] 6 is a diagram showing an example of the search palette 31. As shown in FIG. 6, the search palette 31 is provided with color tags corresponding to 16 palette colors identified by a total of 16 color numbers: colors C11 to C14, colors C21 to C24, colors C31 to C34, and colors C41 to C44. One reason for using the color tags of the search palette 31 to specify a search query is that it allows the user to specify a color that is closer to their memory than by verbalizing the color of the artwork they remember.
[0033] In this way, the colors c1, c2, c3, and c4 extracted from the artwork AW1 shown in Figure 5 are clustered into the palette color that is the shortest distance in color space among the multiple palette colors included in the search palette 31 shown in Figure 6.
[0034] For example, color c1 extracted from artwork AW1 is clustered into color tag C44 of the search palette 31. Colors c2 and c3 extracted from artwork AW1 are clustered into color tag C41 of the search palette 31. Color c4 extracted from artwork AW1 is clustered into color tag C43 of the search palette 31.
[0035] Returning to the explanation of FIG. 1, the registration unit 15B is a processing unit that links the artwork and the feature amount extracted by the feature extraction unit 15A to each other and registers them in the tag DB 13B stored in the storage unit 13.
[0036] In one aspect, the registration unit 15B registers a song for which an import request has been received by adding it to the collection in the library 13A. In this library 13A, attribute information such as the song, the artwork assigned to the song, the album on which the song is recorded, and the artist who performs the song, as well as associations of DJ editing operations such as playlists, cues, and loops, can be stored as collection information.
[0037] In another aspect, the registration unit 15B links the identification information of the artwork assigned to the imported music piece, the object tag extracted by the feature extraction unit 15A, and the color tag extracted by the feature extraction unit 15A, and registers them in the tag DB 13B. When registering the color tag in this way, the registration unit 15B can also register the proportion of the artwork that the color tag occupies, for example, its occupancy rate.
[0038] The receiving unit 15C is a processing unit that receives various requests. In one embodiment, the receiving unit 15C can receive a search query via an artwork search screen 30 illustrated in FIG.
[0039] Fig. 7 is a diagram showing an example of an artwork search screen 30. As shown in Fig. 7, the artwork search screen 30 may include a search palette 31 and an object tag specification screen 32. Of these, the search palette 31, as described using Fig. 6, has color tags arranged therein corresponding to 16 types of palette colors identified by a total of 16 color numbers: colors C11 to C14, colors C21 to C24, colors C31 to C34, and colors C41 to C44.
[0040] For example, a color tag can be specified from the search palette 31. By specifying such a search query, the search unit 15D (described later) can perform filtering to extract artworks containing a color corresponding to the specified color tag while excluding artworks that do not contain a color corresponding to the specified color tag. Furthermore, the artworks obtained as a result of filtering can be sorted in descending order of the occupancy rate of the color corresponding to the specified color tag.
[0041] For example, in the case where artwork AW1 shown in FIG. 3 is the target of the search, specifying color tag C43 makes it easier to narrow down the search to artwork AW1 with a high occupancy rate of the color corresponding to color tag C43.
[0042] Furthermore, GUI (Graphical User Interface) components, such as check boxes, are arranged in association with each category tag that classifies the object groups stored in the tag DB 13B on the object tag specification screen 32. Hereinafter, the category tags that classify the object groups may be referred to as "major category tags."
[0043] Such "major category tags" can be generated by a large-scale language model such as an LLM (Large Language Model), as an example. For example, by inputting the vocabulary contained in tag DB 13B, i.e., all object tags, into the LLM, major category tags that classify all object tags can be output. When generating major category tags in the LLM, a prompt including an instruction element instructing the LLM to group the input data into 10 or fewer items can be input. The accuracy of generating major category tags can be improved by further including in the prompt example sentences that classify the object tags as context elements.
[0044] FIG. 8 is a diagram showing an example of the results of generating major category tags. FIG. 8 excerpts a portion of the output results of major category tags output by the LLM to which the vocabulary stored in the tag DB 13B is input. For example, the example shown in FIG. 8 includes three major category tags, such as "Urban Elements," "Clothing and Accessories," and "Shapes and Patterns." For example, "Urban Elements" means that object tags such as "city skyline," "road," "city," ..., "street art" belong to it. Furthermore, "Clothing and Accessories" means that object tags such as "shoe," "underclothes," ..., "sunglasses" belong to it. Furthermore, "Shapes and Patterns" means that object tags such as "square," "circle," ..., "triangle" belong to it.
[0045] The major category tags obtained in this manner are placed on the object tag specification screen 32. For example, a check mark may be specified in a check box associated with the major category tag. By specifying such a search query, the search unit 15D (described later) can perform filtering to extract artworks that include corresponding object tags that belong to the specified major category tag, while excluding artworks that do not include object tags that do not belong to the specified major category tag.
[0046] For example, in the case where the artwork AW1 shown in Figure 3 is the search target, by checking the checkbox for the major classification tag "animal," it becomes easier to narrow down the search to artwork AW1 depicting a dog that corresponds to the major classification tag "animal."
[0047] Returning to the explanation of FIG. 1, the search unit 15D is a processing unit that searches the tag DB 13B for artwork corresponding to the feature amount received as a search query.
[0048] 7, the search unit 15D performs the following search. That is, the search unit 15D extracts artworks that include a color corresponding to the specified color tag from the tag DB 13B, while filtering out artworks that do not include a color corresponding to the specified color tag. Furthermore, the search unit 15D can sort the artworks obtained as a result of the filtering in descending order of the occupancy rate of the color corresponding to the specified color tag.
[0049] In another aspect, when the designation of a major classification tag is accepted on the object tag designation screen 32 shown in Fig. 7, the search unit 15D executes the following search: That is, the search unit 15D extracts artworks including a corresponding object tag that belongs to the designated major classification tag from the tag DB 13B, while executing filtering to exclude artworks that do not include an object tag that does not belong to the designated major classification tag.
[0050] While the example described above accepts the specification of either a color tag or a major category tag, it is also possible to accept the specification of both a color tag and a major category tag. In this case, the search unit 15D can, as an example, search the tag DB 13B using an AND condition of a color tag and a major category tag. For example, artworks that include a color corresponding to the specified color tag and a corresponding object tag belonging to the specified major category tag can be extracted from the tag DB 13B. It goes without saying that the search is not limited to such an AND condition, and an OR condition search can also be performed to extract artworks from the tag DB 13B that include a color corresponding to the specified color tag or a corresponding object tag belonging to the specified major category tag.
[0051] The output control unit 15E is a processing unit that executes output control for the output unit 12. In one aspect, the output control unit 15E can cause the output unit 12 to output the search results of the search unit 15D.
[0052] As one aspect, the output control unit 15E can display on the output unit 12 a list of songs to which artwork obtained as a search result by the search unit 15D is assigned. FIG. 9 is a diagram (1) showing an example of a display of search results. FIG. 9 shows an example of a collection screen 200 that lists a collection of songs imported by the DJ software as part of the song management function provided by the DJ software. As shown in FIG. 9, the collection screen 200 includes a tree view 210, a track list 220A, and an artwork search screen 30. For example, the tree view 210 displays a hierarchical structure of folders that classify the songs included in the collection. Furthermore, the track list 220A displays a list of tracks included in a folder selected in the tree view 210. When displaying the search results on such a collection screen 200, the output control unit 15E can display on the track list 220A a list of songs to which artwork obtained as a search result by the search unit 15D is assigned.
[0053] As another aspect, the output control unit 15E can also display on the output unit 12 a list of artwork obtained as a search result by the search unit 15D. FIG. 10 is a diagram (2) showing an example of a display of search results. FIG. 10 shows an example of a collection screen 200 that lists a collection of artwork imported by the DJ software as part of the music management function provided by the DJ software. As shown in FIG. 10, the collection screen 200 includes a tree view 210, a jacket list 220B, and an artwork search screen 30. For example, the tree view 210 displays a hierarchical structure of folders that classify the music included in the collection. Furthermore, the track list 220A displays a list of tracks included in a folder selected in the tree view 210. When displaying the search results on such a collection screen 200, the output control unit 15E can display a list of artwork obtained as a search result by the search unit 15D, such as a list of jacket images, in the jacket list 220B. At this time, the output control unit 15E can refer to the collection information stored in the library 13A and display attribute information such as track name and artist name, and analysis information such as BPM (Beats Per Minute) and Key for each artwork.
[0054] <Processing Flow> Next, a processing flow of the music playback device 10 according to this embodiment will be described. Here, (1) registration processing executed by the music playback device 10 will be described, followed by (2) search processing.
[0055] (1) Registration Processing Fig. 11 is a flowchart showing the procedure of the registration processing. This processing is merely an example and can be started when a new song is imported into the collection of the library 13A managed by the song management function of the DJ software.
[0056] 11 , when a request to import new music pieces into the collection of the library 13A is received (step S101), the feature extraction unit 15A executes loop process 1, which repeats the processes from step S102 to step S105 described below a number of times corresponding to the number M of artworks to be imported into the library 13A. Note that the processes from step S102 to step S105 described below do not necessarily have to be executed serially, and may be executed in parallel.
[0057] That is, the feature extraction unit 15A extracts tags of objects drawn in the m-th artwork (step S102). Furthermore, the feature extraction unit 15A extracts colors contained in the m-th artwork (step S103). Next, the feature extraction unit 15A clusters the colors extracted from the m-th artwork into palette colors that are the shortest distance apart in color space from among the palette colors contained in the search palette 31 (step S104).
[0058] Then, the registration unit 15B links the identification information of the mth artwork, the object tag extracted in step S102, and the color tag corresponding to the palette color clustered in step S104, and registers them in the tag DB 13B (step S105).
[0059] By repeating this loop process 1, object tags and color tags are extracted and registered for each of the M artworks to be imported.
[0060] Thereafter, the registration unit 15B generates category tags, that is, large classification tags, for classifying the vocabulary included in the tag DB 13B, that is, all object tag groups (step S106), and ends the process.
[0061] (2) Search Processing Fig. 12 is a flowchart showing the procedure of the search processing. This processing can be started when an operation to specify a search query is accepted on the artwork search screen 30 shown in Fig. 7, for example.
[0062] As shown in FIG. 12, when an operation to specify a search query is accepted on the artwork search screen 30 (step S301), the search unit 15D determines whether a color tag has been specified on the search palette 31 (step S302).
[0063] At this time, if the search palette 31 accepts the designation of a color tag (Yes in step S302), the search unit 15D executes the following process. That is, the search unit 15D extracts artworks containing the color corresponding to the designated color tag from the tag DB 13B and sorts them in descending order of the occupancy rate of the color corresponding to the designated color tag (step S303). Note that if the search palette 31 does not accept the designation of a color tag (No in step S302), the above step S303 is skipped.
[0064] The search unit 15D then determines whether or not the designation of a major category tag has been accepted on the object tag designation screen 32 (step S304). At this time, if the designation of a major category tag has been accepted on the object tag designation screen 32 (step S304 Yes), the search unit 15D extracts artwork including a corresponding object tag belonging to the designated major category tag from the tag DB 13B (step S305). Note that if the designation of a major category tag has not been accepted on the object tag designation screen 32 (step S304 No), the above step S305 is skipped.
[0065] Thereafter, the output control unit 15E causes the output unit 12 to output the result of either step S303 or step S305, or both steps S303 and S305, i.e., the search result of the AND condition (step S306), and ends the process.
[0066] Although Figure 12 also shows an example in which the specification of either a color tag or a major classification tag is accepted, as described above, it is possible to accept the specification of both a color tag and a major classification tag and search the tag DB 13B using an AND condition.
[0067] <Summary> As described above, the music playback device 10 according to this embodiment accepts artwork features as a search query, searches a database in which music artwork and artwork features are linked and registered for artwork corresponding to the features accepted as the search query, and outputs the search results. Therefore, the music playback device 10 according to this embodiment can realize an artwork search. By realizing such an artwork search, it is possible for a user who does not remember the song title or artist name to search for a desired song.
[0068] <Embodiment 2> Although embodiment 1 of the present disclosure has been described so far, various applications are possible, and further, the present disclosure may be implemented in various different forms other than embodiment 1 described above.
[0069] <Exercising Creative Ability> The matters described in the first embodiment, such as the types and numbers of artwork features and specific examples of machine learning models such as RAM and LLM, are merely examples and can be changed. Furthermore, the order of processing in the flowchart described in the first embodiment can also be changed within a consistent range.
[0070] <Application Example 1 of Object Tag Designation> In the above-described first embodiment, an example in which the designation of one object tag is accepted has been given, but the designation of multiple object tags can also be accepted. In this case, multiple color tags can also be searched for from the tag DB 13B using either an AND condition or an OR condition.
[0071] <Application Example 1 of Color Tag Designation> In the above-described first embodiment, the designation of one color tag is accepted. However, the designation of multiple color tags can also be accepted. Even in this case, multiple color tags can be searched for in the tag DB 13B using either an AND condition or an OR condition. For example, the designation of a color pattern included in artwork can also be accepted. In the example where the artwork AW1 shown in FIG. 3 is the search target, the designation of a combination of color tags C41, C43, and C44 can be accepted. When such a designation is accepted, the search unit 15D can search the tag DB 13B for artworks including the combination of color tags C41, C43, and C44, thereby narrowing down the search to only artworks similar to the color pattern of the artwork AW1 shown in FIG. 3.
[0072] <Application to other usage scenarios> In the above-mentioned embodiment 1, the music playback device 10 realized by an audio device or the like is given as an example, but the processing of Figures 11 and 12 can also be executed in usage scenarios where a streaming service that distributes music and videos or a music sales service is provided.
[0073] Fig. 13 is a block diagram showing an example of the functional configuration of the music providing apparatus 100. For example, Fig. 13 shows the music providing apparatus 100 that provides a streaming service or a music sales service.
[0074] The music providing apparatus 100 may be realized by a server apparatus. For example, the music providing apparatus 100 can provide the above-mentioned streaming service or the above-mentioned music sales service as a cloud service by executing PaaS (Platform as a Service) type middleware or SaaS (Software as a Service) type application.
[0075] 13, the music providing device 100 can be communicably connected to an administrator terminal 200 and a user terminal 300 via a network NW. For example, the network NW may be any type of communication network, whether wired or wireless, such as the Internet or a LAN (Local Area Network).
[0076] The administrator terminal 200 is a terminal device used by a person related to the service provider that provides the streaming service or the music sales service, such as an administrator, etc. The user terminal 300 is a terminal device used by a user who receives the streaming service or the music sales service.
[0077] The administrator terminal 200 and the user terminal 300 may be realized by any computer, such as a personal computer, a smartphone, a tablet terminal, or a wearable terminal.
[0078] Under this overall configuration, the music providing device 100 shown in Figure 13 differs from the music playback device 10 shown in Figure 1 in that various requests are accepted via the network NW and the results of processing execution are output via the network NW.
[0079] For example, instead of the music playback device 10 accepting a request to import a song as a user operation via the input unit 11, the music providing device 100 accepts a request from the administrator terminal 200 via the communication control unit 110 to register a song that is to be newly distributed or sold, such as a new song, through the streaming service or the music sales service in the music DB 131. Furthermore, instead of the music playback device 10 accepting a search query specification as a user operation via the input unit 11, the music providing device 100 accepts a search query specification from the user terminal 300 via the communication control unit 110 and outputs the search results to the user terminal 300 as a response.
[0080] 1 and the music providing device 100 shown in Fig. 13 may have similar functions, except that the music providing device 100 is realized as a server device in a client-server system. For example, the feature extraction unit 151, registration unit 152, reception unit 153, search unit 154, and output control unit 155 of the control unit 150 of the music providing device 100 may have similar functions to the feature extraction unit 15A, registration unit 15B, reception unit 15C, search unit 15D, and output control unit 15E of the control unit 15 of the music playing device 10. Furthermore, the tag DB 132 of the storage unit 130 of the music providing device 100 may have similar functions to the tag DB 13B of the storage unit 13 of the music playing device 10.
[0081] Artwork search can also be realized in the above-described music providing device 100. By realizing such artwork search, it becomes possible for a user who does not remember the song title or artist name to search for a desired song.
[0082] <System> The information including the processing procedures, control procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, any one or more of the functional units of the music playback device 10, including the feature extraction unit 15A, registration unit 15B, reception unit 15C, search unit 15D, and output control unit 15E, may be configured as separate devices.
[0083] Furthermore, the components of each device shown in the figure are functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown. In other words, all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc. Note that each configuration may also be a physical configuration.
[0084] Furthermore, all or any part of the processing performed by the illustrated device may be realized by a program executed by a hardware processor such as an MPU (Micro-Processing Unit) or a CPU (Central Processing Unit), or may be realized as hardware using wired logic.
[0085] <Hardware> Next, an example of the hardware configuration of the information processing device described in the above embodiment will be described. Fig. 14 is a diagram showing an example of the hardware configuration. As shown in Fig. 14, the music playback device 10 has a communication device 10a, a storage device 10b, a memory 10c, and a processor 10d. Note that the components shown in Fig. 14 may be connected to each other via a bus or the like.
[0086] The communication device 10a is a network interface card, etc. The storage device 10b is a storage device such as a hard disk drive (HDD) or a solid state drive (SSD). For example, the storage device 10b stores programs and databases that operate the functions shown in FIG.
[0087] The processor 10d reads out a program that executes the same processing as the processing unit shown in FIG. 1 from the storage device 10b or the like and loads it into the memory 10c, thereby operating a process that executes the functions described in FIG.
[0088] Such a process realizes the same functions as the processing units of the music playback device 10. For example, the processor 10d reads out a program having the same functions as the feature extraction unit 15A, the registration unit 15B, the reception unit 15C, the search unit 15D, the output control unit 15E, etc. from the storage device 10b, etc. Then, the processor 10d executes a process that executes the same processing as the feature extraction unit 15A, the registration unit 15B, the reception unit 15C, the search unit 15D, the output control unit 15E, etc.
[0089] In this way, the music playback device 10 operates as an information processing device that executes a music playback method by reading and executing a program. The music playback device 10 can also realize functions similar to those of the above-described embodiment by reading the program from a recording medium using a medium reading device and executing the read program. Note that the program in these other embodiments is not limited to being executed by the music playback device 10. For example, the functions of the present disclosure can be similarly applied when another computer or server executes the program, or when these execute the program in cooperation with each other.
[0090] The above program can be distributed via a network such as the Internet. The above program can also be recorded on any recording medium and executed by a computer by reading it from the recording medium. For example, the recording medium can be a hard disk, a flexible disk (FD), a CD-ROM, a magneto-optical disk (MO), a digital versatile disk (DVD), or the like.
[0091] REFERENCE SIGNS LIST 10 Music playback device 11 Input unit 12 Output unit 13 Storage unit 13A Library 13B Tag DB 15 Control unit 15A Feature extraction unit 15B Registration unit 15C Reception unit 15D Search unit 15E Output control unit
Claims
1. A music playback device comprising: a reception unit that receives artwork features as a search query; a search unit that searches a database in which music artwork and the features of the artwork are linked and registered to search for artwork corresponding to the features received as the search query; and an output control unit that outputs the search results by the search unit.
2. The music playback device according to claim 1, further comprising: an extraction unit that extracts features from the artwork; and a registration unit that links the artwork with the features extracted by the extraction unit and registers them in the database.
3. The music playback device described in claim 2, characterized in that the extraction unit extracts colors contained in the artwork, and the registration unit links the artwork with a palette color to which the color extracted from the artwork by the extraction unit belongs, from among multiple palette colors contained in a search palette used to specify the search query, and registers the artwork in the database.
4. The music playback device described in claim 3, characterized in that the reception unit receives a palette color specification from a search palette containing a plurality of palette colors, and the search unit searches for artwork contained in the database that corresponds to the palette color for which the specification has been accepted.
5. A music playback device according to any one of claims 2 to 4, wherein the extraction unit extracts an object drawn in the artwork, and the registration unit links the artwork with the object extracted by the extraction unit and registers them in the database.
6. The music playback device described in claim 5, characterized in that the reception unit receives the search query specification from among category tags that classify the group of objects stored in the database, and the search unit searches for artwork corresponding to objects included in the category tag for which the specification was received among the objects stored in the database.
7. A music playback device according to any one of claims 1 to 6, characterized in that the output control unit outputs artwork obtained as a search result by the search unit, or music to which the artwork is assigned.
8. A music providing device comprising: a reception unit that receives artwork features as a search query; a search unit that searches a database in which music artwork and the features of the artwork are linked and registered to search for artwork corresponding to the features received as the search query; and an output control unit that outputs the search results by the search unit.
9. The music providing device according to claim 8, further comprising: an extraction unit that extracts features from the artwork; and a registration unit that links the artwork with the features extracted by the extraction unit and registers them in the database.
10. The music providing device of claim 9, wherein the extraction unit extracts the colors contained in the artwork, and the registration unit associates the artwork with a palette color to which the color extracted from the artwork by the extraction unit belongs, from among multiple palette colors contained in a search palette used to specify the search query, and registers the artwork in the database.
11. The music providing device described in claim 10, characterized in that the reception unit receives a designation of a palette color from a search palette containing a plurality of palette colors, and the search unit searches for artwork contained in the database that corresponds to the palette color for which the designation has been accepted.
12. A music providing device according to any one of claims 9 to 11, wherein the extraction unit extracts an object drawn in the artwork, and the registration unit links the artwork with the object extracted by the extraction unit and registers them in the database.
13. The music providing device described in claim 12, characterized in that the reception unit receives the search query from among category tags that classify the group of objects stored in the database, and the search unit searches for artwork corresponding to objects included in the category tag for which the specification has been received among the objects stored in the database.
14. A music providing device according to any one of claims 8 to 13, characterized in that the output control unit outputs artwork obtained as a search result by the search unit, or music to which the artwork is assigned.
15. A music playback program that causes a computer to perform the following process: accept artwork features as a search query; search for artwork corresponding to the features accepted as the search query from a database in which music artwork and the features of the artwork are linked and registered; and output the search results.
Citation Information
Patent Citations
Image search apparatus and image search system
JP2016103084A
Image extraction method, image extraction device, image extraction system, server, user terminal, communication system and program
WO2013005262A1