Information processing device and information processing method

Abstract

To generate music content that matches a user's tastes. [Solution] An information processing device is provided that includes a first extraction unit that extracts the number of times the main content has been viewed for each piece of content based on the content viewing history of each user, for at least one or more pieces of content each of which includes a combination of the main content and a used song; a second extraction unit that extracts the number of times the used song has been viewed or the number of times the used song has been skipped for each piece of content based on the content viewing history of each user; a score calculation unit that calculates a score for each used song based on the extracted number of times the main content has been viewed and the number of times the used song has been viewed or the number of times the used song has been skipped; and a generation unit that generates combined favorite song data using data for at least two used songs with the highest scores.

Description

[Technical Field]

[0001] The present invention relates to an information processing device and an information processing method. [Background technology]

[0002] In the above technical fields, Patent Document 1 discloses a technology for selecting some sound sources from a sound source pool based on the number of times short-form content has been generated using the sound sources to create a popularity pool, and recommending at least some of the sound sources included in the popularity pool as popular sound sources. Patent Document 2 discloses a technology for calculating viewing recommendation information using a preference value obtained by normalizing the number of times content has been viewed for each content attribute by the number of opportunities to view the content. Patent Document 3 discloses a technology for selecting songs according to song evaluation points (history, etc.) and automatically playing videos and songs that suit the user's preferences. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-157004 [Patent Document 2] Japanese Patent Application Laid-Open No. 2009-118189 [Patent Document 3] Japanese Patent Application Laid-Open No. 2003-259318 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology described in the above document does not generate music content that matches the user's preferences with respect to content that includes a combination of the main content and the music used.

[0005] An object of the present invention is to provide a technique for solving the above-mentioned problems. [Means for solving the problem]

[0006] In order to achieve the above object, the device according to the present invention comprises: a first extraction unit that extracts the number of times each of at least one content item has been viewed based on the content viewing history of each user, the number of times each of the content items has been viewed based on the content viewing history of each user, the first extraction unit extracting ... a second extraction unit that extracts the number of times a song used for each content has been listened to or the number of times a song used for each content has been skipped based on the content viewing history of each user; a score calculation unit that calculates a score for each used song based on the extracted number of times the main program has been played and the extracted number of times the used song has been played or the extracted number of times the used song has been skipped; a generating unit that generates combined favorite song data using data of at least two used songs with the highest scores; The information processing device is provided with: In order to achieve the above object, the method according to the present invention comprises: a first extraction step in which a first extraction unit extracts the number of times each content has been viewed based on the content viewing history of each user, for at least one content including a combination of a main content and a used song; a second extraction step in which a second extraction unit extracts the number of times a song used for each content has been listened to or the number of times a song used for each content has been skipped based on the content viewing history of each user; a score calculation step in which a score calculation unit calculates a score for each used song based on the extracted number of times the main program has been played and the extracted number of times the used song has been played or the extracted number of times the used song has been skipped; a generating step in which a generating unit generates combined favorite song data using data of at least two used songs with the highest scores; The information processing method includes: [Effects of the Invention]

[0007] According to the present invention, it is possible to generate music content that matches the preferences of a user. [Brief explanation of the drawings]

[0008] [Figure 1]1 is a block diagram showing a configuration of an information processing device according to a first embodiment. [Figure 2] FIG. 10 is a block diagram showing the configuration of an information processing device according to a second embodiment. [Figure 3] FIG. 10 is a block diagram showing the hardware configuration of an information processing device according to a second embodiment. [Figure 4] 10 is a flowchart showing the flow of processing by an information processing device according to a second embodiment. [Figure 5] FIG. 10 is a block diagram showing the configuration of an information processing device according to another example of the second embodiment. [Figure 6] FIG. 10 is a block diagram showing the configuration of an information processing device according to a third embodiment. [Figure 7] FIG. 10 is a block diagram showing the configuration of an information processing device according to a fourth embodiment. [Figure 8] FIG. 10 is a block diagram showing the configuration of an information processing device according to a fifth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. However, the components described in the following embodiments are merely examples and are not intended to limit the technical scope of the present invention.

[0010] [First embodiment] An information processing device 100 according to a first embodiment of the present invention will be described with reference to FIG. 1. The information processing device 100 is a device that generates combined favorite music data tailored to a user's preferences from at least one piece of content, each of which includes a combination of a main story and a used song. Typical examples of content that includes a combination of a main story and a used song include, but are not limited to, a drama series or an animated series. The combined favorite music data may be data in which the user's favorite used songs are simply arranged sequentially, or data in which multiple used songs are connected together to form a single song, such as a medley. As shown in FIG. 1, information processing device 100 includes main content viewing count extraction unit 101, used song viewing count extraction unit 102, score calculation unit 103, and combined data generation unit 104.

[0011] The main content viewing count extraction unit 101 extracts the main content viewing count 151 for each content based on the content viewing history for each user. The content viewing history for each user is data that can be read from, for example, the viewing history database 140, and for example, the viewing start time, viewing end time, viewing start position within the content, viewing end position within the content, etc. are linked to the identifier of the content viewed by the user and stored in chronological order. The main content viewing count 151 is the number of times the user has viewed the main part of the content in particular.

[0012] The used song viewing count extraction unit 102 extracts the used song viewing count 152 for each piece of content based on the content viewing history for each user. The used song viewing count 152 is the number of times that the used song portion of the content has been listened to in particular. The used song skip count may be extracted instead of the used song viewing count 152. The used songs include opening songs and ending songs. The number of times that only the opening song has been viewed may be extracted as the used song viewing count, or the opening song and ending song may be distinguished and the viewing count for each may be extracted. If the skip history is stored in the anime viewing history database as described above, the used song skip count may be extracted instead of the used song viewing count, or the value obtained by subtracting the number of skips from the main program viewing count 151 may be used as the used song viewing count.

[0013] The score calculation unit 103 calculates a score 153 for each used song based on the extracted main program viewing count 151 and used song viewing count 152. The score may be calculated based on the used song skip count instead of the used song viewing count 152.

[0014] The combined data generator 104 generates combined favorite song data 154 using data on at least two used songs with high scores 153. In the example of FIG. 1, since "DDD" and "AAA" have high scores for user A, the data on these two used songs is read from the content database 160 and combined to generate combined favorite song data 154. The combined favorite song data 154 may be video data or audio data, and is stored in association with the user, allowing the user to play it back at any time they like.

[0015] With the above configuration, it is possible to generate combined favorite music data tailored to the user's preferences from at least one content, each of which includes a combination of a main feature and a used song, and provide the data to the user. In particular, since the used songs that make up the combined favorite music data are selected taking into consideration not only the number of times each song has been listened to but also the number of times the main feature has been listened to, it is possible to provide combined favorite music data that is very close to the user's preferences.

[0016] [Second embodiment] Next, the configuration of an information processing device 200 according to a second embodiment of the present invention will be described with reference to FIG. 2 and subsequent figures. The information processing device is a device that generates a combined video of an opening song tailored to a user's preferences from at least two pieces of anime content data, including a combination of a main story and an opening song. While this embodiment focuses on the opening song, the present invention is not limited to this, and the technical scope of the present invention also includes cases where "opening song" below is read as "used song" or "opening song or ending song."

[0017] (Functional configuration) 2 is a block diagram showing the functional configuration of an information processing device 200. As shown in FIG. 2, the information processing device 200 includes a main feature viewing count extraction unit 201, an opening song viewing count extraction unit 202, a score calculation unit 203, a favorite song combination data generation unit 204, and a favorite song database 205.

[0018] The main program viewing count extraction unit 201 extracts the main program viewing count 251 for each anime based on the anime viewing history 241 for each user, and stores the extracted count as the favorite music database 205. Here, the main program viewing count extraction unit 201 extracts the main program viewing count for each episode in which an opening song was used. That is, for example, even if an anime called "Hero Academia" itself has been broadcast for a total of 160 episodes from season 1 to season 7, the number of times the main program was viewed out of the 12 episodes in which the opening song "THE D" was used is stored in the favorite music database 205 as the main program viewing count 251. That is, the main program viewing count 251 here is the count linked to the opening song 255. However, the present invention is not limited to this, and the total number of times the anime was viewed regardless of the season may be used as the main program viewing count 251.

[0019] The opening song viewing count extraction unit 202 extracts the opening song viewing count 252 for each anime based on the anime viewing history 241 for each user.

[0020] The anime viewing history 241 for each user is data that can be read from the anime viewing history database 240, and includes, for example, the viewing start time, viewing end time, and anime viewing start / end positions, linked to an identifier such as the name of the anime viewed by the user. The anime viewing start / end positions indicate which part of which anime video data viewing started and ended. Note that, for ease of understanding, the anime name is listed in the anime viewing history 241 here, but an identifier (e.g., a 10-digit ID) corresponding to the anime data stored in the anime database 260 may be stored instead.

[0021] It can be determined whether the viewer watched the entire anime series from the opening song through the main story to the ending song, whether the viewer skipped the opening song and watched the main story and the ending song, or whether the viewer skipped both the opening song and the ending song and watched only the main story. Of course, it can also be determined whether the viewer watched only the opening song or only the ending song. In other words, by analyzing the anime viewing history 241, it is possible to extract the number of times the viewer has watched the main story 251 and the number of times the viewer has watched the opening song 252.

[0022] The score calculation unit 203 calculates a score 253 for each opening song based on the extracted main feature viewing count 251 and opening song viewing count 252. In other words, the score 253 is a numerical representation of the user's attachment to the opening song.

[0023] The score calculation unit 203 can derive the score 253 using, for example, the following calculation formula. Score = (Number of times opening song is played / Number of times anime is played) x {Number of times anime is played / (α + Number of times anime is played)} Here, α is generally the number of times that one can say that one has become addicted to the anime, and may be a constant such as 100, or the total number of times that the theme song of the anime has been played (usually 12 times per season). That is, the extraction unit 201 extracts the number of times 251 the main story is viewed for each episode in which the opening song is used, and the score calculation unit 203 calculates the score using the opening song viewing rate obtained by dividing the number of times 252 the opening song is viewed by the number of times 251 the main story is viewed for each episode in which the opening song is used. This makes it possible to calculate a score that closely matches the user's preferences.

[0024] For example, if α is 12, like the opening song "THE D" of the first season of the anime "My Hero Academia," and you watch the anime five times and listen to the opening song once during that time, then (1 / 5) × (5 / 17) = 0.059 This becomes:

[0025] For example, if α is 12, like the opening song "Peace" from the second season of the anime "My Hero Academia," and you watch the anime twice and listen to the opening song twice during that time, then (2 / 2) × (2 / 14) = 0.143 This becomes:

[0026] For example, if α is 12, like the opening song of the 11th season of the anime "Two Piece," "Share the W," and you watch the anime 10 times and listen to the opening song 10 times during that time, then (10 / 10) × (10 / 22) = 0.455. This becomes:

[0027] For example, if α is 12, like the opening song "Ah Y" from the second season of the anime "High View," and you watch the anime 10 times and listen to the opening song 5 times during that time, then (5 / 10) × (10 / 22) = 0.227 This becomes:

[0028] Even if the number of views of the main feature is low, if the viewer rating of the opening song is high, the score will be high. On the other hand, even if the viewer rating of the opening song is low, if the number of views of the main feature is high, the score will be high. If the number of views of the main feature is low in the first place, the score will not be high.

[0029] For example, if a user has watched the anime five times but only listened to the opening song twice, and the user has only watched the anime twice but listened to the opening song both times, the user's preference level for both songs is considered to be roughly the same (scores of 0.118 and 0.143). Since neither user has watched the opening song more than three times, it cannot be said that they like it very much, and since the number of times the anime has been watched is small, it is unclear whether they like it very much.

[0030] The combined favorite song data generator 204 generates combined favorite song data 254 (for example, an anime song medley) using data for at least two opening songs with high scores 253. In the example of FIG. 2, since "Peace" and "Share the W" have high scores for user A, the data for these two opening songs is read from the content database 160 and combined to generate the combined favorite song data 254. The combined favorite song data 254 may be video data or audio data, and is stored in association with the user, so that the user can play it back at any time they like.

[0031] The combined favorite song data 254 may be generated by inserting a short song (a so-called eye-catcher) that is played before or after the commercials of the anime between favorite songs with high scores 253 .

[0032] (Hardware configuration) 3 is a diagram showing the hardware configuration of the information processing device 200. The information processing device 200 may be a server provided on the Internet, or may be a portable information terminal carried by a user, such as a smartphone.

[0033] The information processing device 200 is configured as a computer including hardware such as a processor 301, a ROM 302, a communication control unit 303, a RAM 304, a storage 305, and a bus connecting these. Each of these pieces of hardware operates using power supplied from a power source (not shown). In the following description, the term "device" can be interpreted as a circuit, a device, a unit, a module, or the like. The hardware configuration of the information processing device 200 is not limited to these, and the information processing device 200 may also include input devices (e.g., keys, microphones, switches, buttons, sensors, etc.) and output devices (e.g., displays, speakers, LED lamps, etc.). Of course, the information processing device 200 may also include hardware such as a touch screen that combines an input device and an output device.

[0034] The information processing device 200 may be configured to include one or more of each piece of hardware shown in Fig. 3, or may be configured to exclude some of the devices. Furthermore, the information processing device 200 may be realized as an overall system by connecting a plurality of devices that are provided separately for communication.

[0035] The processor 301 executes, for example, an operating system and various program modules to control the entire information processing device 200. The processor 301 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. Furthermore, for example, a baseband signal processing unit, a call processing unit, etc. may be realized by the processor 301. The processor 301 may be implemented by one or more chips.

[0036] In addition to a CPU (Central Processing Unit), a DSP (Digital Signal Processor) or a GPU (Graphics Processing Unit) may be used as the processor 301. Alternatively, instead of the processor 301, an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), an FPGA (Field Programmable Gate Array), or the like may be used.

[0037] The ROM 302, RAM 304, and storage 305 are all computer-readable recording media that can store executable programs (program codes), software modules, and the like for implementing the method according to this embodiment.

[0038] ROM 302 is a read-only memory that stores various parameters and the like, as well as a boot program that should be executed first by processor 301, and examples of such memory include EPROM (Erasable Programmable ROM) and EEPROM (Electrically Erasable Programmable ROM). RAM 304 is a random access memory that has execution areas for various applications and is also called a register, cache, main memory (primary storage device), etc.

[0039] The storage 305 may be configured by at least one of, for example, a flash memory, a solid state drive (SSD), a hard disk, an optical disk, a magneto-optical disk, a magnetic strip, etc. The storage 305 may also be called an auxiliary storage device. In the case of a smartphone, the storage 305 may be a storage medium called an embedded multi-media card (eMMC) or universal flash storage (UFS).

[0040] Generally, the processor 301 loads program code, software modules, data, etc. from the ROM 302, storage 305, communication control unit 303, etc. into the RAM 304 and executes various processes, but the present invention is not limited to this.

[0041] The communication control unit 303 is hardware (transmission / reception device) for performing communication between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0042] The above hardware components are connected by a bus for communicating information. The bus may be configured using a single bus or different buses may be used between the devices.

[0043] Each functional block 201 to 204 of the information processing device 200 is realized by the corresponding program module being read into RAM 304, executed by the processor 301, and controlling communication by the communication control unit 303 and / or controlling the reading and writing of data in the storage 305. The various program modules may be executed sequentially by one processor 301 or in parallel by two or more processors 301.

[0044] Here, the storage 305 stores the favorite song database 205 in addition to the favorite song combination application 351 .

[0045] The favorite song combination application 351 is read out from the storage 305 in response to a user instruction, and is developed in the RAM 304 as the favorite song combination application 340 .

[0046] The favorite song combination application 340 has a main song play count extraction module 341, an opening song play count extraction module 342, a score calculation module 343, and a favorite song combination data generation module 344, which correspond to the respective function blocks 201 to 204 in Fig. 2. Each module is executed by the processor 301 to read / write data stored in the storage 305 and to communicate with an external database via the communication control unit 303, thereby realizing the respective function blocks 201 to 204 in Fig. 2.

[0047] In FIG. 2, the anime viewing history database 240 and the anime database 260 are provided outside the information processing device 200, but they may be included in the storage 305 as indicated by the dotted line in FIG.

[0048] (Processing flow) 4 is a flowchart outlining the processing flow of this embodiment. Each process is performed by the processor 301 executing the favorite song combination application 340. First, when the favorite song combination application 340 is launched, in step S401 the main program viewing count extraction unit 201 extracts the main program viewing count 251 based on the anime viewing history 241 for each user and stores it in the favorite song database 205. Next, in step S403, the opening song viewing count extraction unit 202 extracts the opening song viewing count 252 based on the anime viewing history 241 for each user and stores it in the favorite song database 205.

[0049] Furthermore, in step S405, the score calculation unit 203 calculates a score 253 for each opening song based on the main feature viewing count 251 and the opening song viewing count 252.

[0050] Next, in step S407, the favorite song combined data generating unit 204 extracts and combines data of at least two opening songs with the highest scores 253 to generate favorite song combined data 254.

[0051] With the above configuration, combined favorite music data tailored to the user's preferences can be generated and provided to the user. If an anime song medley is to be generated from ending music as well as opening music, the configuration shown in FIG. 5 is used. That is, an OP / ED music viewing count extraction unit 502 is provided. In this way, in the favorite music database 205, all songs 555 used, whether they are opening or ending music (or even movie theme songs), are scored based on the number of times they have been viewed in the main story and the songs used, and combined favorite music data 254 is generated.

[0052] [Third embodiment] Next, an information processing device 600 according to a third embodiment of the present invention will be described with reference to FIG. 6. FIG. 6 is a diagram illustrating the overall configuration of the information processing device 600 according to this embodiment. The information processing device 600 according to this embodiment differs from the second embodiment in that it calculates a score based on the number of times the opening song has been skipped. Other configurations and operations are the same as those of the second embodiment, so the same configurations and operations are denoted by the same reference numerals and detailed descriptions thereof will be omitted.

[0053] The information processing device 600 includes an opening song skip count extraction unit 602 that analyzes the anime viewing history 241 and stores the skip count 652 for each opening song in a favorite song database 605 .

[0054] Furthermore, the skip history may be included in the anime viewing history 241. For example, in the case of a content playback browser that has a function (skip button) that allows the user to skip the opening song part, it is possible to store the number of skip instructions received from the user as the anime viewing history.

[0055] The score calculation unit 603 calculates the score using the following formula. Score = (1-skip views / anime views) x {anime views / (α+anime views)} According to the above configuration, it is possible to more easily generate combined favorite songs data that matches the user's preferences using the number of skips and provide it to the user.

[0056] [Fourth embodiment] Next, an information processing device 700 according to a fourth embodiment of the present invention will be described with reference to FIG. 7. FIG. 7 is a diagram illustrating the overall configuration of the information processing device 700 according to this embodiment. The information processing device 700 according to this embodiment differs from the second embodiment in that the anime viewing period is used to calculate the score. Other configurations and operations are the same as those of the second embodiment, so the same configurations and operations are denoted by the same reference numerals and detailed description thereof will be omitted.

[0057] The information processing device 700 extracts the number of times each anime has been viewed, the number of times each song has been viewed, and the duration of each anime viewing for each user, and calculates a score representing the degree to which each work is liked from these. The songs with the highest scores are extracted from the anime data as a set list, and the video is connected to it.

[0058] An anime that has been watched for many years is considered to be a particularly favorite anime, so by using the viewing period of that anime to calculate the score of the songs used, it is possible to provide the favorite song combination data 254 that is more in line with the user's feelings.

[0059] The information processing device 700 includes a main program viewing period extraction unit 706, which extracts the viewing period for each piece of content and stores it as a favorite song database 705. The score calculation unit 703 calculates a score by taking into consideration the viewing period in addition to the number of times the main program has been viewed and the number of times the opening song has been viewed. Favorite song combination data is generated based on three feature quantities: the number of times an anime has been viewed (the more often you watch an anime you like, the more you like its songs), the number of times a song has been viewed (among your favorite anime, you particularly like its songs), and the viewing period (an anime you have rewatched for years is a particularly favorite anime).

[0060] The score calculation unit 703 calculates the score based on the following patterns 1 to 4.

[0061] Pattern 1: Score when watching the anime 5 times and listening to the song only once < Score when watching the anime 2 times and listening to the song 2 times Reason: The former may not like the song, but the latter can be said to like the song.

[0062] Pattern 2: Score if you watch the anime 5 times and listen to the song only 2 times ≒ Score if you watch the anime 2 times and listen to the song 2 times Reason: I can't say I like the former very much because I haven't seen the song more than three times, but I haven't watched the latter anime much, so I don't know if I like it very much yet.

[0063] Pattern 3: Score if you watch the anime 5 times and listen to the song 4 times, and have been watching that anime once a year for the past 5 years > Score if you watch the anime 5 times and listen to the song 4 times, and have been watching that anime 5 times in a row since last month Reason: I like both the former and latter songs, but I feel more attached to the former.

[0064] Pattern 4: If you watched the anime 5 times and listened to the song once, and have been watching that anime once a year for the past 5 years, your score will be ≒ if you watched the anime 5 times, listened to the song once, and have been watching that anime 5 times in a row since last month. Reason: I don't particularly like either the former or latter songs.

[0065] The following can be said from the above patterns 1 to 4. The more the number of anime views = the number of song views, the higher the score. The fewer times an anime is watched, the lower its score will be. The longer the viewing period, the higher the score. The number of views has a greater impact on the score than the viewing period.

[0066] Based on the above, the score calculation unit 703 calculates the score using the following formula. Score = (number of song views / number of anime views) x {number of anime views / (α + number of anime views)} x (0.1 x number of years of viewing) The reason we multiplied the number of years of viewing by 0.1 here is to give more weight to the impact of the number of views on the score; any other number less than 1, such as 0.2, could also be used.

[0067] The score may be calculated using the following formula, where the number of years of viewing is an integer.

[0068] Score = (number of song views / number of anime views) x {number of anime views / (α + number of anime views)} x (0.1 x number of years watching + 1) The reason why 1 is added to 0.1 x number of years of viewing is because when the number of years of viewing is less than one year, the number of years of viewing is 0.

[0069] For example, if α is 12, like the opening song of the first season of the anime "My Hero Academia," and you watch the anime five times over a 2.5-year period and listen to the opening song once during that time, then (1 / 5) x (5 / 17) x 2.5 = 0.147 This becomes:

[0070] For example, if α is 12, like the opening song "Peace" from the second season of the anime "My Hero Academia," and you watch the anime twice in 0.8 years and listen to the opening song twice during that time, then (2 / 2) x (2 / 14) x 0.8 = 0.114 This becomes:

[0071] For example, if α is 12, like the opening song for the 11th season of the anime "Two Piece," "Share the W," and you watch the anime 10 times over a 2.1 year period and listen to the opening song 10 times during that time, then (10 / 10) x (10 / 22) x 2.1 = 0.955. This becomes:

[0072] For example, if α is 12, like the opening song for the second season of the anime "High View," and you watch the anime 10 times in 0.3 years and listen to the opening song 5 times during that time, then (5 / 10) x (10 / 22) x 0.3 = 0.068 This becomes:

[0073] If the favorite song combination data 254 is generated using the score calculated as described above, it is possible to provide favorite song combination data that takes into account the listening period.

[0074] [Fifth embodiment] Next, an information processing device 800 according to a fifth embodiment of the present invention will be described with reference to FIG. 8. FIG. 8 is a diagram illustrating the overall configuration of the information processing device 800 according to this embodiment. The information processing device 800 according to this embodiment differs from the fourth embodiment in that the time of viewing of the anime is further used to calculate the score. Since the other configurations and operations are the same as those of the fourth embodiment, the same reference numerals are used for the same configurations and operations, and detailed description thereof will be omitted.

[0075] The information processing device 800 extracts the number of times an anime has been viewed, the number of times a song has been viewed, the anime viewing period, and the viewing time for each user, and calculates a score representing the degree to which each work is liked from these. The songs with the highest scores are extracted from the anime data as a set list, and the video is connected.

[0076] Since the anime that was recently watched is considered to be a particularly favorite anime, by using the time when the anime was watched to calculate the score of the song used, it is possible to provide the favorite song combination data 254 that is more in line with the user's feelings.

[0077] The information processing device 800 includes a main content viewing period extraction unit 807, which extracts the viewing period for each content. The score calculation unit 803 calculates a score by taking into consideration the viewing period in addition to the number of times the main content has been viewed, the number of times the opening song has been viewed, and the viewing period.

[0078] In other words, the combined data of favorite songs is generated based on four features: the number of times an anime has been watched (the more favorite anime you are, the more times you watch it), the number of times a song has been watched (among your favorite anime, you particularly like the song), the duration of viewing (anime you have watched over and over for years is your favorite anime), and the time of viewing (anime you have watched recently is your favorite anime).

[0079] The score calculation unit 803 further calculates the score based on the following pattern 5.

[0080] Pattern 5: Score if you watch an anime 5 times and listen to the song 4 times, and have been watching that anime for 2 years, starting from 5 years ago > Score if you watch an anime 5 times and listen to the song 4 times, and have been watching that anime for 2 years, but also watched it 1 month ago Reason: I like both the former and latter songs, but I feel more attached to the latter.

[0081] The following can be said from pattern 5 above. The closer to when you last watched the anime, the higher the score.

[0082] Based on the above, the score calculation unit 803 calculates the score using the following formula. Score = (number of song views / number of anime views) x {number of anime views / (α + number of anime views)} x (0.1 x number of years of viewing) / (time since last viewing) For example, if α is 12, like the opening song "THE D" of the first season of the anime "My Hero Academia," and you watched the anime five times in the 2.5 years up until one year ago and listened to the opening song once during that time, then the α is (1 / 5) x (5 / 17) x 2.5 / 1 = 0.147 This becomes:

[0083] For example, if α is 12, like the opening song "Peace" from the second season of the anime "My Hero Academia," and you watched the anime twice in the 0.8 years up until 0.5 years ago and listened to the opening song twice during that time, then (2 / 2) x (2 / 14) x 0.8 / 0.5 = 0.228 This becomes:

[0084] For example, if α is 12, like the opening song of the 11th season of the anime "Two Piece," "Share the W," and you watched the anime 10 times in the 2.1 years up until three years ago and listened to the opening song 10 times during that time, then (10 / 10) x (10 / 22) x 2.1 / 3 = 0.318 This becomes:

[0085] For example, if α is 12, like the opening song "Ah Y" from the second season of the anime "High View," and you watched the anime 10 times in the 0.3 years up to 0.1 years ago and listened to the opening song 5 times during that time, then (5 / 10) x (10 / 22) x 0.3 / 0.1 = 0.682 This becomes:

[0086] By using the scores calculated as described above to generate the combined favorite music data 254 by combining opening songs with high scores, it is possible to provide combined favorite music data that also takes into account the time of listening.

[0087] In this case, the favorite song combination data generating unit 204 may generate the favorite song combination data by dividing the data by viewing period. In the preference database 205, opening songs can be classified by viewing period 757, and it is possible to generate, for example, an anime song medley for 2022 (a special collection of opening songs of anime that the user often watched in 2022). This makes it possible to generate an anime song medley based on personal memories, rather than an anime song medley of anime generally watched in 2022.

[0088] [Other embodiments] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various modifications can be made to the configuration and details of the present invention that are understandable to those skilled in the art within the technical scope of the present invention. Furthermore, systems or devices that combine the separate features included in each embodiment in any manner are also included in the technical scope of the present invention.

[0089] The present invention may also be applied to a system consisting of multiple devices or to a single device. Furthermore, the present invention may also be applied when an information processing program that realizes the functions of the embodiments is supplied to a system or device and executed by a built-in processor. The technical scope of the present invention also includes a program installed on a computer to realize the functions of the present invention, a medium storing the program, a server from which the program is downloaded, and a processor that executes the program. In particular, the technical scope of the present invention includes at least a non-transitory computer-readable medium storing a program that causes a computer to execute the processing steps included in the above-described embodiments.

[0090] [Other expressions of embodiments] Some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes. (Appendix 1) a first extraction unit that extracts the number of times each of at least one content item has been viewed based on the content viewing history of each user, the number of times each of the content items has been viewed based on the content viewing history of each user, the first extraction unit extracting ... a second extraction unit that extracts the number of times a song used for each content has been listened to or the number of times a song used for each content has been skipped based on the content viewing history of each user; a score calculation unit that calculates a score for each used song based on the extracted number of times the main program has been played and the extracted number of times the used song has been played or the extracted number of times the used song has been skipped; a generating unit that generates combined favorite song data using data of at least two used songs with the highest scores; An information processing device comprising: (Appendix 2) Further, a third extraction unit is provided to extract a viewing period for each of the contents, 2. The information processing device according to claim 1, wherein the score calculation unit calculates the score based on the extracted viewing period. (Appendix 3) Further, a fourth extraction unit is provided to extract a viewing period for each of the content items, 2. The information processing device according to claim 1, wherein the score calculation unit further calculates the score based on the extracted viewing period. (Appendix 4) Further, a fourth extraction unit is provided to extract a viewing period for each of the content items, The information processing device according to claim 1, wherein the generating unit further generates the favorite song combination data for each of the extracted listening periods. (Appendix 5) The content includes at least an anime, The information processing device according to claim 1, wherein the first extraction unit extracts, for each episode in which the song is used, the number of times the main story is viewed for that episode. (Appendix 6) The content includes at least an anime, The first extraction unit extracts, for each episode in which the song is used, the number of times the main program has been viewed in that episode; The information processing device described in Appendix 1, wherein the score calculation unit calculates the score using a song viewing rate or song skip rate obtained by dividing the number of times the song was listened to or skipped by the number of times the song was listened to for each episode in which the song was used. (Appendix 7) a first extraction step in which a first extraction unit extracts the number of times each content has been viewed based on the content viewing history of each user, for at least one content including a combination of a main content and a used song; a second extraction step in which a second extraction unit extracts the number of times a song used for each content has been listened to or the number of times a song used for each content has been skipped based on the content viewing history of each user; a score calculation step in which a score calculation unit calculates a score for each used song based on the extracted number of times the main program has been played and the extracted number of times the used song has been played or the extracted number of times the used song has been skipped; a generating step in which a generating unit generates combined favorite song data using data of at least two used songs with the highest scores; An information processing method including:

Claims

1. a first extraction unit that extracts the number of times each of at least one content item has been viewed based on the content viewing history of each user, the number of times each of the content items has been viewed based on the content viewing history of each user, for each of at least one content item that includes a combination of a main content item and a used song; a second extraction unit that extracts the number of times a song used for each content has been listened to or the number of times a song used for each content has been skipped based on the content viewing history of each user; a score calculation unit that calculates a score for each of the used songs based on the extracted number of times the main program has been played and the extracted number of times the used songs have been played or the extracted number of times the used songs have been skipped; a generating unit that generates combined favorite song data using data of at least two used songs with the highest scores; An information processing device comprising:

2. Further, a third extraction unit is provided to extract a viewing period for each of the contents, The information processing device according to claim 1 , wherein the score calculation unit calculates the score based on the extracted viewing period.

3. Further, a fourth extraction unit is provided to extract a viewing period for each of the content items, The information processing device according to claim 1 , wherein the score calculation unit further calculates the score based on the extracted viewing period.

4. Further, a fourth extraction unit is provided to extract a viewing period for each of the content items, The information processing device according to claim 1 , wherein the generating unit further generates the favorite song combination data for each of the extracted listening periods.

5. The content includes at least an anime, The information processing device according to claim 1 , wherein the first extraction unit extracts, for each episode in which the song is used, the number of times the main story is viewed for that episode.

6. The content includes at least an anime, the first extraction unit extracts, for each episode in which the song is used, the number of times the main program is viewed for that episode; The information processing device according to claim 1, wherein the score calculation unit calculates the score using a used song viewing rate or used song skip rate obtained by dividing the number of times the used song was listened to or the number of times the used song was skipped by the number of times the main story was listened to for each episode in which the used song was used.

7. a first extraction step in which a first extraction unit extracts the number of times each content has been viewed based on the content viewing history of each user, for at least one content including a combination of a main feature and a used song; a second extraction step in which a second extraction unit extracts the number of times a used song has been listened to or the number of times a used song has been skipped for each piece of content based on the content viewing history of each user; a score calculation step in which a score calculation unit calculates a score for each used song based on the extracted number of times the main program is played and the extracted number of times the used song is played or the extracted number of times the used song is skipped; a generating step in which a generating unit generates combined favorite song data using data of at least two used songs with the highest scores; An information processing method including:

Images