Recommendation device
The recommendation device addresses the limited range of video suggestions by identifying and matching musical emotional structures, using a content map to recommend videos that align with user emotional preferences, enhancing the emotional connection and diversity of content recommendations.
Patent Information
- Application Number
- PCT/JP2024/017991
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-18
- Filing Date
- 2024-05-15
- Publication Date
- 2024-11-21
AI Technical Summary
Conventional video recommendation systems in video distribution services often recommend content that is similar in genre, leading to a limited range of suggestions, failing to capture user interest through diverse emotional connections.
A recommendation device that identifies the musical emotional structure of video content viewed by a user and recommends videos with matching or similar emotional compositions, using a content map that associates video content with emotional values like Valence and Arousal, derived from mel spectrograms and CNNs, to suggest content that resonates emotionally.
Expands the range of recommended video content by suggesting videos that align with the user's emotional preferences, even if they have different genres or meta information, thereby providing a deeper resonance with user tastes.
Smart Images

Figure JP2024017991_21112024_PF_FP_ABST
Abstract
Description
Recommendation device
[0001] One aspect of the present invention relates to a recommendation device.
[0002] Patent Documents 1 and 2 describe recommendation systems that recommend video content to users in consideration of the user's tastes and preferences.
[0003] JP 2008-117222 A JP 2011-128981 A
[0004] In a typical recommendation system for video distribution services, for example, video content similar to video content that a user has previously viewed (similar genres, etc.) is recommended. In this case, there is a risk that the recommended video content will be similar to each other.
[0005] One aspect of the present invention has been made in consideration of the above-described circumstances, and aims to broaden the range of video content that can be recommended.
[0006] A recommendation device according to one aspect of the present invention includes an acquisition unit that acquires information related to video content associated with a user, an identification unit that identifies the musical composition desired by the user based on the information related to the video content acquired by the acquisition unit, and a recommendation unit that recommends video content corresponding to the musical composition identified by the identification unit.
[0007] A recommendation device according to one aspect of the present invention identifies the musical composition desired by a user based on information related to video content associated with the user, and recommends video content corresponding to the musical composition. Typical recommendation systems for video streaming services, for example, recommend video content similar to video content previously viewed by the user (similar genres, etc.). In this case, there is a risk that the recommended video content will be similar to each other. The present applicants hypothesized that video content with different genres or meta information may be of interest to the user (resonate deeply with the user) if it has a similar musical composition, and came up with the idea of recommending video content that focuses on musical composition. As described above, a recommendation device according to one aspect of the present invention identifies the musical composition from video content associated with the user, and recommends video content corresponding to (e.g., similar to) the musical composition. This configuration makes it possible to recommend video content that may interest the user from a new perspective, namely, musical composition, rather than relying on similarities in genre, etc., as in conventional methods. This will allow us to expand the range of video content that we recommend.
[0008] According to the present invention, it is possible to widen the range of video content to be recommended.
[0009] FIG. 1 is a diagram showing an image of video content recommended by a recommendation device. FIG. 2 is a functional block diagram of a recommendation device included in a recommendation system. FIG. 3 is a diagram illustrating deriving a music vector using a mel spectrogram and a CNN. FIG. 4 is a diagram illustrating creating a content map according to a music vector. FIG. 5 is a diagram illustrating an example of acquiring an emotion a user wants to have. FIG. 6 is a diagram illustrating another example of acquiring an emotion a user wants to have. FIG. 7 is a diagram illustrating an example of a UI. FIG. 8 is a diagram illustrating another example of a UI. FIG. 9 is a diagram illustrating yet another example of a UI. FIG. 10 is a diagram illustrating yet another example of a UI. FIG. 11 is a flowchart showing recommendation processing. FIG. 12 is a diagram illustrating the hardware configuration of a recommendation device according to an embodiment.
[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements are designated by the same reference numerals, and redundant description will be omitted.
[0011] First, the recommendation of video content by the recommendation device according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an image of video content recommended by the recommendation device.
[0012] As shown in FIG. 1 , assume that a user is currently watching a video content titled "TEL101." The theme song for "TEL101" is the song "Discharge" by singer Taro Yoneyama. The recommendation device according to this embodiment, for example, identifies the musical emotional composition (details will be described later) of "Discharge," the theme song for the video content "TEL101," and recommends video content corresponding to the identified musical emotional composition. Specifically, the recommendation device identifies music (e.g., a song) with a musical emotional composition identical to or similar to the musical emotional composition of "Discharge," and recommends video content for which the identified song is the theme song. This recommendation is based on the hypothesis that "the atmosphere of a work (video content) can be grasped by its musical emotional composition."
[0013] Such recommendation targets are determined, for example, using a content map (described in detail later) shown in the right diagram of FIG. 1. The content map is an emotion map in which emotions are mapped with valence (emotional valence) on the horizontal axis and arousal (arousal level) on the vertical axis, and each video content is associated with the emotion map based on the musical composition. Emotions such as astonished, excited, happy, good, hopeful, peaceful, sleepy, bored, anxious, sad, disappointed, frustrated, annoyed, and afraid are mapped to the emotion map. Then, each video content (or music associated with each video content) is mapped to the emotion map based on the musical emotion composition indicating the emotion of the music associated with each video content (e.g., theme song).
[0014] In the content map shown on the right side of FIG. 1 , the aforementioned "Discharge" is mapped as music mapped near the musical emotional composition "excited." Furthermore, as music mapped near the same musical emotional composition "excited," for example, the song "New York" by singer "Nowgli's," the song "Knock Out" by singer "Taro Yoneyama," and the song "Door of Time" by singer "BANDS" are mapped. In this case, the recommendation device recommends video content whose theme song is "New York," "Knock Out," or "Door of Time," which are mapped near "excited" like "Discharge." The recommendation device may, for example, identify a song whose position (i.e., musical emotional composition) on the content map is closest to "Discharge" and recommend video content whose theme song is that song. Now, suppose that the song closest to "Discharge" in the content map is "KNOCK OUT." In this case, the recommendation device recommends video content "Nokogiri Man," which uses "KNOCK OUT" as its theme song. Note that, although an example of a recommendation triggered by obtaining information indicating video content viewed by a user has been described here, a recommendation may also be triggered by obtaining other information (details will be described later).
[0015] 2 is a functional block diagram of a recommendation device 10 included in the recommendation system 1. As shown in FIG. 2, the recommendation system 1 is configured to include the recommendation device 10 and a user terminal 20 held by a user. Note that the recommendation system 1 includes multiple user terminals 20 associated with multiple users, but for ease of explanation, only one user terminal 20 will be explained here. The user terminal 20 may be any terminal capable of wireless communication, such as a smartphone, tablet terminal, or PC terminal.
[0016] The recommendation device 10 is a device that recommends to a user (user terminal 20) video content that is likely to be desired by the user (that is in line with the user's preferences). In detail, the recommendation device 10 identifies a musical emotional composition desired by the user from video content associated with the user (e.g., video content viewed by the user), and recommends video content corresponding to the musical emotional composition. The musical emotional composition is information indicating the emotion expressed by music (the emotion evoked by music), and is represented by a vector (music vector) of multiple perspectives including, for example, valence (emotional valence) and arousal (arousal level).
[0017] The recommendation device 10 includes an acquisition unit 11 , an identification unit 12 , a recommendation unit 13 , a display unit 14 , and a storage unit 15 .
[0018] The storage unit 15 stores a content map in which each emotion is mapped and each video content is associated with a music emotional structure. Creation of the content map will be described with reference to FIGS. 3 and 4. When creating the content map, first, a music vector indicating the music emotional structure of the music associated with each video content (e.g., theme song) is derived (FIG. 3). Then, a content map is created in which each video content is mapped onto the emotion map based on the music vector (FIG. 4).
[0019] 3 is a diagram illustrating the derivation of a music vector using a mel spectrogram and a convolutional neural network (CNN). As shown in FIG. 3, music associated with each video content is converted into a mel spectrogram, for example. A mel spectrogram is an acoustic feature whose vertical axis represents time, horizontal axis represents frequency, and value represents power. The portion converted into a mel spectrogram may be a characteristic portion that represents the music.
[0020] Such characteristic portions are extracted, for example, using the following method. First, k-medoids clustering is performed on song segments (divided portions). A d-dimensional acoustic feature vector is used to represent each segment. The medoids of each cluster are selected for annotation as representative segments. The number of clusters, k, is set proportional to the number of segments in the track. To ensure the quality and diversity of the k-medoids results, the algorithm is repeated multiple times, and the results based on the cumulative distance between the segments and their medoids are selected. Finally, an average of m representative segments are obtained for each track. The melspectrogram images are then input into a CNN to derive music vectors that represent the emotional composition of each piece of music. The music vectors here are vectors that represent, for example, the features of valence and arousal.
[0021] FIG. 4 is a diagram illustrating the creation of a content map according to music vectors. Assume that the music vector of "Discharge," the theme song of the video content "TEL101," is derived as [Valance: 0.40, Arousal: 0.10, ...], and the music vector of "Knock Out," the theme song of the video content "Nokogiri Man," is derived as [Valance: 0.42, Arousal: 0.13, ...]. For the video content with music whose music vectors have been derived in this way, each is mapped to a pre-prepared emotion map based on the music vector of the music. The emotion map has Valence on the horizontal axis and Arousal on the vertical axis, and is a map onto which emotions such as astonished, excited, happy, good, hopeful, peaceful, sleepy, bored, anxious, sad, disappointed, frustrated, annoyed, and afraid are mapped. Since music vectors are also represented by the feature quantities of valence and arousal, they can be mapped to an emotion map of video content. A content map is created by mapping each video content to the emotion map. The storage unit 15 stores the content map created in this way.
[0022] The acquisition unit 11 acquires information related to video content associated with a user (user terminal 20). The acquisition unit 11 acquires, for example, information indicating video content viewed by the user as the information related to the video content associated with the user. The acquisition unit 11 acquires, for example, information indicating the video content viewed by the user from the user terminal 20 when the user has finished viewing the video content.
[0023] The acquisition unit 11 may acquire, as information related to video content associated with the user (user terminal 20), information indicating, for example, emotions the user wants to derive from the video content. FIG. 5 is a diagram illustrating an example of acquiring emotions the user wants to derive. As shown in FIG. 5 , the emotion map defines the relationships between emotions (whether emotions are similar to each other). Therefore, the acquisition unit 11 may acquire information indicating emotions the user wants to derive compared to the emotions the user derives from the video content the user has viewed. Specifically, for example, after the user has finished viewing the video content, a question such as "What do you want to watch next?" is sent to the user terminal 20, and the user selects an answer from answer candidates such as "A. Keep it like this," "B. More intense than before," and "C. Quieter than before." This allows the acquisition unit 11 to acquire information indicating emotions the user wants to derive compared to the emotions the user derives from the video content the user has viewed.
[0024] In the example shown in Fig. 5, for example, if the musical emotional composition of the video content viewed by the user is "excited," and the user responds with "A. Keep it like this," information indicating the emotion the user desires to experience is "excited," as shown in the left diagram of Fig. 5. Furthermore, if the user responds with "B. More intense than before," information indicating an emotion even more intense than "excited" is acquired, as shown in the center diagram of Fig. 5. Furthermore, if the user responds with "C. Quieter than before," information indicating an emotion quieter than "excited" (e.g., peaceful) is acquired, as shown in the right diagram of Fig. 5.
[0025] FIG. 6 is a diagram illustrating another example of acquiring the emotion the user wants to derive from the video content. The acquisition unit 11 may acquire information indicating the emotion the user wants to derive from the video content, without comparing the emotion with the video content that the user has viewed, as described above. In the example shown in FIG. 6 , a question such as "What kind of work do you want to watch now?" is sent to the user terminal 20, and the user selects an answer from answer candidates such as "A. excited," "B. happy," and "C. calm." Based on the emotion map, the user's emotion corresponding to the user's answer is identified (acquired).
[0026] The acquisition unit 11 may also acquire information indicating the emotion the user wants to derive from the video content based on a selection operation by the user viewing the emotion map displayed on the user terminal 20 (see FIG. 8; details will be described later).
[0027] The identification unit 12 identifies the musical emotion configuration desired by the user based on the information related to the video content acquired by the acquisition unit 11. As described above, the information related to the video content acquired by the acquisition unit 11 may be information indicating the video content viewed by the user, or information indicating the emotion the user wants to derive from the video content.
[0028] The identification unit 12 identifies the musical emotional configuration desired by the user based on the information related to the video content acquired by the acquisition unit 11 and the content map. Assume now that information indicating the video content viewed by the user is acquired by the acquisition unit 11. In this case, the identification unit 12 refers to the content map and identifies the musical emotional configuration (e.g., excited) of the video content viewed by the user as the musical emotional configuration desired by the user.
[0029] Also, assume that information indicating the emotion the user wants to get from video content is acquired by the acquisition unit 11. In this case, the identification unit 12 refers to the content map and identifies a musical emotion configuration corresponding to the emotion the user wants to get as the musical emotion configuration the user is looking for.
[0030] The recommendation unit 13 recommends video content corresponding to the musical emotional configuration identified by the identification unit 12. By referring to the content map, the recommendation unit 13 identifies video content with a musical emotional configuration that matches or is similar to the musical emotional configuration identified by the identification unit 12, and recommends the video content. Matching musical emotional configurations means, for example, that the closest emotions in the emotional map match (for example, matching excited). Similar musical emotional configurations means, for example, that the closest emotions in the emotional map do not match but are close in the emotional map (for example, excited and happy are close in the emotional map).
[0031] For example, when there are multiple pieces of video content with matching musical emotional compositions, the recommendation unit 13 may recommend video content with a musical emotional composition that is closest to the musical emotional composition of the video content that the user has previously viewed.
[0032] The display unit 14 displays information on the user terminal 20. The display unit 14 displays video content recommended by the recommendation unit 13 on the user terminal 20. The display unit 14 also displays a UI (User Interface) on the user terminal 20 to enable the acquisition unit 11 to acquire information.
[0033] 7 is a diagram showing an example of a UI displayed on the user terminal 20 by the display unit 14. For example, assume that the screen shown in FIG. 7( a) is an initial screen. From this state, a screen is displayed asking the user about their preferred atmosphere in video content, as shown in FIG. 7( b). If, for example, the user answers Y (YES) to the question "Do you like works with a calm atmosphere?" in FIG. 7( b), a list of works (video content) with a calm musical emotional composition is displayed, as shown in FIG. 7( c).
[0034] FIG. 8 illustrates another example of a UI. In the example illustrated in FIG. 8( a), the emotion map is roughly divided into four regions, and facial expression icons corresponding to each region are displayed, along with the question, "Which piece of work do you want to watch with which emotion?" In this state, for example, when the smiling icon in the upper right corner is clicked, details of the musical emotion configuration in the upper right corner are displayed, as illustrated in FIG. 8( b), and facial expression icons for the detailed emotional configuration (e.g., excited) are displayed. Then, as illustrated in FIG. 8( c), for example, when "excited" is clicked, a list of works (video content) with a musical emotion configuration of "excited" is displayed. In this case, video content may be suggested in descending order of the degree of "excited." In this manner, the display unit 14 may display the emotion map on the user terminal 20. Furthermore, the acquisition unit 11 may acquire information indicating the emotion the user desires to derive from video content based on a selection operation by the user viewing the emotion map displayed on the user terminal 20.
[0035] 9A and 9B are diagrams showing other examples of UIs. In the example shown in Fig. 9A, when displaying an emotion map, as described above, the map is divided into four major regions, and icons with facial expressions appropriate to each region are displayed. In the example shown in Fig. 9B, the emotion map is displayed as is, without dividing it into regions as described above. In either case, the emotion map can be displayed together with a message such as "Which emotion piece would you like to see?" to obtain the emotion the user desires.
[0036] 10A and 10B are diagrams showing other examples of UIs. In the example shown in Fig. 10A, information indicating a plurality of emotions associated with a video content viewed by a user (e.g., icons for each emotion) is displayed. When one emotion is selected from the information indicating the plurality of emotions, a list of video content corresponding to the selected emotion is displayed, as shown in Fig. 10B.
[0037] Next, the recommendation process will be described with reference to Fig. 11. Fig. 11 is a flowchart showing the recommendation process.
[0038] As shown in FIG. 11, the recommendation device 10 first acquires information related to video content associated with a user (step S1).
[0039] Next, based on the information related to the acquired video content, the musical emotional composition desired by the user is identified (step S2).
[0040] Finally, video content having a music emotional composition corresponding to (the same as or similar to) the identified music emotional composition is recommended (step S3). This completes the recommendation process.
[0041] Next, the effects of the recommendation device 10 according to this embodiment will be described.
[0042] The recommendation device 10 includes an acquisition unit 11 that acquires information related to video content associated with a user, an identification unit 12 that identifies the musical emotional composition desired by the user based on the information related to the video content acquired by the acquisition unit 11, and a recommendation unit 13 that recommends video content corresponding to the musical emotional composition identified by the identification unit.
[0043] The recommendation device 10 according to the present embodiment identifies the musical emotional composition desired by the user based on information related to video content associated with the user, and recommends video content corresponding to the musical emotional composition. Typical recommendation systems for video streaming services, for example, recommend video content similar to video content previously viewed by the user (similar genres, etc.). In this case, there is a risk that the recommended video content will be similar to each other. The present applicants hypothesized that video content with different genres or meta information may be of interest to the user (resonate deeply with the user) if it has a similar musical emotional composition, and came up with the idea of recommending video content that focuses on musical emotional composition. As described above, the recommendation device 10 according to the present embodiment identifies the musical emotional composition from video content associated with the user, and recommends video content corresponding to (e.g., similar to) the musical emotional composition. This configuration makes it possible to recommend video content that may interest the user from a new perspective, namely, musical emotional composition, rather than relying on similarities in genre, etc., as in the past. This will allow us to broaden the range of video content we recommend. Specifically, it will be possible to recommend long-tail works that may resonate deeply with users, as well as recommend video content with different genres and meta information.
[0044] The recommendation device further includes a storage unit 15 that stores a content map in which each emotion is mapped to a corresponding emotion map and each video content is associated with a musical emotional composition. The identification unit 12 identifies the musical emotional composition desired by the user based on the information related to the video content acquired by the acquisition unit 11 and the content map. The recommendation unit 13 may refer to the content map to identify video content with a musical emotional composition that matches or is similar to the musical emotional composition identified by the identification unit 12 and recommend the video content. In this way, by using the emotion map in which each emotion is mapped, the musical emotional composition desired by the user can be easily identified and video content that matches or is similar to the musical emotional composition can be easily recommended. In other words, this configuration makes it easy to expand the range of recommended video content.
[0045] The acquiring unit 11 may acquire information indicating video content viewed by the user as the information related to the video content associated with the user. With this configuration, it is possible to identify the musical emotion composition desired by the user from the video content that the user actually selected and viewed, and to appropriately recommend video content that is likely to match the user's preferences.
[0046] The acquisition unit 11 may acquire information indicating the emotion the user wants to derive from the video content as the information related to the video content associated with the user. By acquiring information indicating the emotion the user wants to derive from the video content in this way, it is possible to appropriately recommend video content with a musical emotion composition that matches the emotion of the user, i.e., video content that is likely to match the user's preferences.
[0047] The acquisition unit 11 may acquire information indicating an emotion that the user wants to feel compared to an emotion that the user felt from the video content that the user has viewed. In this way, by acquiring information indicating what emotion the user wants to feel compared to an emotion that the user felt from the video content that the user has viewed, it is possible to identify with high accuracy the emotion that the user wants to feel based on the video content that the user has viewed, and to appropriately recommend video content with a musical emotion composition that matches the user's emotion, i.e., video content that is likely to match the user's preferences.
[0048] The recommendation device 10 may further include a display unit 14 that displays information on a user terminal 20 held by the user, the display unit 14 displays an emotion map on the user terminal 20, and the acquisition unit 11 may acquire information indicating the emotion the user wants to get from the video content based on a selection operation from the user who views the emotion map displayed on the user terminal 20. In this way, by displaying the emotion map and acquiring information indicating the emotion the user wants to get from the user, the emotion that the user is looking for can be acquired easily and with high accuracy.
[0049] Next, the hardware configuration of the recommendation device 10 described above will be described with reference to Fig. 12. The recommendation device 10 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.
[0050] In the following description, the term "device" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the recommendation device 10 may be configured to include one or more of the devices shown in the figure, or may be configured to exclude some of the devices.
[0051] Each function of the recommendation device 10 is realized by loading specific software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations and control communication via the communication device 1004 and the reading and / or writing of data in the memory 1002 and storage 1003.
[0052] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control unit, an arithmetic unit, a register, etc. For example, the control functions of the acquisition unit 11 and the like may be realized by the processor 1001.
[0053] The processor 1001 also reads programs (program codes), software modules, and data from the storage 1003 and / or the communication device 1004 into the memory 1002, and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above embodiments.
[0054] For example, the control functions of the acquisition unit 11 and the like may be realized by a control program stored in the memory 1002 and running on the processor 1001, and similar functions may be realized for other functional blocks. Although the above-described various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented on one or more chips. The program may be transmitted from a network via a telecommunications line.
[0055] The memory 1002 is a computer-readable recording medium and may be composed of at least one of, for example, a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to one embodiment of the present invention.
[0056] Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including memory 1002 and / or storage 1003.
[0057] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via a wired and / or wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.
[0058] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).
[0059] Furthermore, each device such as the processor 1001 and the memory 1002 is connected to a bus 1007 for communicating information. The bus 1007 may be configured as a single bus, or may be configured as different buses between the devices.
[0060] The recommendation device 10 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented by at least one of these pieces of hardware.
[0061] Although the present embodiment has been described in detail above, it is clear to those skilled in the art that the present embodiment is not limited to the embodiment described in this specification. The present embodiment can be implemented in modified and altered forms without departing from the spirit and scope of the present invention as defined by the claims. Therefore, the description in this specification is intended to be illustrative and does not have any limiting meaning on the present embodiment.
[0062] Each aspect / embodiment described herein may be applied to systems utilizing LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA, GSM, CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB (Ultra-Wide Band), Bluetooth, or other suitable systems and / or next generation systems enhanced thereon.
[0063] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described herein may be rearranged unless it is consistent. For example, the methods described herein present elements of various steps in an example order and are not limited to the particular order presented.
[0064] Input and output information may be stored in a specific location (for example, memory) or managed in a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.
[0065] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).
[0066] The aspects / embodiments described herein may be used alone or in combination, or may be switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).
[0067] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.
[0068] Software, instructions, etc. may also be transmitted or received over a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired technologies such as coaxial cable, fiber optic cable, twisted pair, and Digital Subscriber Line (DSL), and / or wireless technologies such as infrared, radio, and microwave, these wired and / or wireless technologies are included within the definition of transmission media.
[0069] The information, signals, etc. described herein may be represented using any one of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.
[0070] It should be noted that terms explained in this specification and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meanings.
[0071] Furthermore, the information, parameters, etc. described in this specification may be expressed as absolute values, as relative values from a predetermined value, or as corresponding other information.
[0072] A communications terminal may also be referred to by those skilled in the art as a mobile communications terminal, subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communications device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.
[0073] As used herein, the phrase "based on" does not mean "based only on," unless expressly specified otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."
[0074] When designations such as "first," "second," etc. are used herein, any reference to such elements does not generally limit the quantity or order of those elements. These designations may be used herein as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed therein or that the first element must precede the second element in some way.
[0075] To the extent that the terms "include," "including," and variations thereof are used herein or in the claims, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, the term "or," as used herein or in the claims, is not intended to be an exclusive or.
[0076] In this specification, a plurality of devices is also included unless the context or the technology clearly indicates that only one device exists.
[0077] Throughout this disclosure, the plural is intended to be included unless the singular is clearly indicated by the context.
[0078] 10...recommendation device, 11...acquisition unit, 12...identification unit, 13...recommendation unit, 14...display unit, 15...storage unit, 20...user terminal.
Claims
1. A recommendation device comprising: an acquisition unit that acquires information related to video content associated with a user; an identification unit that identifies a musical composition desired by the user based on the information related to the video content acquired by the acquisition unit; and a recommendation unit that recommends video content corresponding to the musical composition identified by the identification unit.
2. A recommendation device as described in claim 1, further comprising a memory unit that stores a content map in which each emotion is mapped to an emotion map and each video content is associated with a musical composition, wherein the identification unit identifies the musical composition desired by the user based on information related to the video content acquired by the acquisition unit and the content map, and the recommendation unit identifies video content with a musical composition that matches or is similar to the musical composition identified by the identification unit by referring to the content map, and recommends the video content.
3. A recommendation device as claimed in claim 1 or 2, wherein the acquisition unit acquires information indicating video content viewed by the user as information relating to the video content associated with the user.
4. The recommendation device according to claim 2, wherein the acquisition unit acquires information indicating an emotion that the user desires to derive from the video content as information related to the video content associated with the user.
5. The recommendation device according to claim 4, wherein the acquisition unit acquires information indicating an emotion that the user wants to obtain compared with an emotion that the user obtains from video content viewed by the user.
6. A recommendation device as described in claim 4 or 5, further comprising a display unit that displays information on a user terminal held by a user, wherein the display unit displays the emotion map on the user terminal, and the acquisition unit acquires information indicating the emotion that the user wants to derive from video content based on a selection operation by the user viewing the emotion map displayed on the user terminal.
Citation Information
Patent Citations
Method and equipment for providing recommended video list
CN111083534A
Video recommendation method and device, electronic equipment and computer readable storage medium
CN111966909A
System and method for recommendation of music and moving video based on audio signal processing
KR1020080107143A
Recommending a media item by using audio content from a seed media item
US20110276567A1
System and method for content recommendation
US20130132988A1
