Information processing device and information processing method

Abstract

An information processing device (10) is provided with: a reception unit (11) that receives information for providing instruction regarding the generation of a video preview, said information relating to at least a video or a video preview generation instruction including a comment relating to the video; a determination unit (12) that, on the basis of the information pertaining to the video preview generation instruction, determines, for each previously-classified target layer, video preview generation policy information which is information relating to a policy for generating a video preview; and an output unit (13) that outputs, to a LLM (30), generation request information for instructing the generation of a video preview for each target layer on the basis of the video preview generation policy information for each target layer.

Description

Information processing device and information processing method

[0001] The present disclosure relates to an information processing device and an information processing method.

[0002] There is known a technique for generating a video (hereinafter referred to as a "video preview") that saves some scenes of one or more video contents in order to convey an image of the video content. The "video preview" is also sometimes called a highlight video, a digest video, a summary video, etc. For example, Patent Document 1 listed below discloses a technique for extracting important scenes (video portions) and linking them together to generate a video preview, based on the assumption that the closer the distance between two objects in a scene of a target video or the higher the stillness of the video (the less blurring).

[0003] On the other hand, the needs of each target demographic, which is classified based on their personal viewing experience, attribute information, etc., differ with regard to the scenes they want to include in the video preview.

[0004] Japanese Patent Application Laid-Open No. 2023-159776

[0005] However, Patent Document 1 does not consider determining a video preview generation policy for each target group (e.g., a video preview generation policy for beginners, a video preview generation policy for channel subscribers, etc.) and generating a video preview based on the determined policy.

[0006] Meanwhile, in recent years, various types of content have been generated using generative artificial intelligence (AI) models. A generative AI model is a model that can generate content (generation results) in response to a prompt containing input information, according to any one or a combination of instructions, context, questions, and output formats indicated by the prompt, and return the generated content as response information.

[0007] In view of the above situation, the present disclosure aims to utilize a generative AI model to easily obtain video previews with content appropriate for the target demographic.

[0008] The information processing device according to the present disclosure includes a receiving unit that receives information regarding a video preview generation instruction, the information being for instructing the generation of a video preview and including at least a video or a comment related to the video; a determination unit that determines video preview generation policy information, which is information regarding a generation policy for a video preview, for each pre-classified target group based on the information regarding the video preview generation instruction; and an output unit that outputs generation request information for instructing the generation of a video preview for each target group based on the video preview generation policy information for each target group to a generation AI model.

[0009] According to the present disclosure, video previews with content appropriate for a target demographic can be easily obtained.

[0010] FIG. 1 is a configuration diagram of an entire system including an information processing device. FIG. 2 is a flow diagram of processing executed by the information processing device. FIG. 3 is a diagram showing an example of information related to a video preview generation instruction, and FIG. 4 is a diagram showing an example of information indicating emotions every second. FIG. 4 is a diagram showing an example of determination of video preview generation policy information. FIG. 5 is a diagram showing an example of a command statement. FIG. 6 is a diagram showing another example of video preview generation policy information and a command statement. FIG. 7 is a diagram showing an example of a generation result (answer). FIG. 8 is a diagram showing a first modified example related to the system configuration, and FIG. 9 is a diagram showing a second modified example related to the system configuration. FIG. 9 is a diagram showing an example of the hardware configuration of an information processing device.

[0011] Hereinafter, an embodiment of an information processing device and an information processing method according to the present disclosure will be described with reference to the drawings. In the following embodiment, a form will be described in which a large language model (LLM) that is mainly used for text generation is used as an example of a generative AI model.

[0012] [Configuration of a System Including an Information Processing Device] FIG. 1 illustrates a configuration diagram of a system 1 including an information processing device 10 according to the present disclosure. As illustrated in FIG. 1, the system 1 includes a terminal 20 operated by a user, an external server (hereinafter referred to as "LLM") 30 running a large-scale language model (LLM), and the information processing device 10. The information processing device 10 is a device constituting a Retrieval-Augmented Generation (RAG) system. The RAG system is a type of prompt extension technology used for corporate information linkage of LLMs. Specifically, when issuing a generation request to an LLM based on an instruction statement (generation request information), the system searches for similar documents, etc. in a search system in advance, and outputs the obtained similar documents, etc., along with the instruction statement to the LLM to request generation. To realize the functions according to the present disclosure, the information processing device 10 includes a receiving unit 11, a determining unit 12, and an output unit 13. The functions of each unit are described below.

[0013] The reception unit 11 is a functional unit that receives information for instructing the generation of a video preview (hereinafter referred to as "information related to the instruction to generate a video preview") from an external source (e.g., the terminal 20 or an external server instructed by the terminal 20). The received information related to the instruction to generate a video preview includes at least a video or a comment related to the video, and includes, for example, video of multiple scenes into which the video is divided, and description information and attribute information for each video (each scene).

[0014] The determination unit 12 is a functional unit that determines information regarding a video preview generation policy (hereinafter referred to as "video preview generation policy information") for each pre-classified target demographic based on information regarding the video preview generation instruction received by the reception unit 11. For example, the determination unit 12 determines video preview generation policy information for each target demographic, including information regarding which scenes in the video are to be used to generate the video preview. The "target demographic" is classified based on the user's viewing experience and user attributes (e.g., gender, age, place of origin, nationality), etc., and examples of target demographics include "beginners" with little viewing experience and "channel subscribers" who have registered as viewers of a specific channel on a video site. In addition, the information regarding the video preview generation instruction received by the reception unit 11 may further include emotion information that indicates the viewer's emotion regarding a scene included in the video. In this case, the determination unit 12 determines the video preview generation policy information based on information regarding the video preview generation instruction including the emotion information. Various determination processes by the determination unit 12 will be described later.

[0015] The output unit 13 is a functional unit that outputs to the LLM 30 an instruction statement (generation request information) for instructing the generation of a video preview for each target demographic based on the video preview generation policy information for each target demographic. The output unit 13 also receives task management advice from the LLM 30 as a generation result output from the LLM 30 in response to the input of the instruction statement, and outputs the advice to the terminal 20. Specific examples of the instruction statement and the advice that is the generation result will be described later.

[0016] (Processing Executed in Information Processing Device 10) Hereinafter, processing executed in the information processing device 10 (processing related to the information processing method of the present disclosure) will be described with reference to the flow diagram of FIG.

[0017] First, the receiving unit 11 receives information related to a video preview generation instruction from an external source (e.g., the terminal 20 or an external server instructed by the terminal 20) (step S1). The "information related to a video preview generation instruction" includes video images for each of a plurality of scenes obtained by dividing a video into multiple scenes, and related information corresponding to the video images for each scene (e.g., information outlining each scene, scene attribute information, etc.).

[0018] As an example of information related to a video preview generation instruction, Fig. 3(a) shows an example in which a game commentary video is divided into four scenes. Fig. 3(a) illustrates the "type" of video, "video file specification information" that specifies which scene, and "related information (1)" and "related information (2)" related to that scene. Related information (1) shows an overview of the scene, such as an intro, a game commentary, an explanation of new features, or promotions for other games, while related information (2) shows the number of comments posted about that scene.

[0019] The "scene attribute information" included in the "related information" may include emotional information representing the viewer's emotions in a scene. The emotional information may be, for example, "numerical information for each emotion (anger, sadness, joy, etc.) (e.g., anger = 36, sadness = 1, etc.)" output by an existing AI system, or an evaluation result derived based on the numerical information for each emotion (e.g., positive level = 80, negative level = 32). Specifically, the emotional information may be acquired based on comments included in the information regarding the video preview generation instruction as follows: For example, a learning model that has learned the relationship between the analysis results of various viewer comments (feedback) and emotions may be used. In response to inputting the analysis results of viewer comments about a target scene into the learning model, the learning model may output information (e.g., a score) indicating the degree of each viewer's emotion. For example, if a viewer's comment contains an aggressive expression (e.g., "This isn't funny" in a comment) during a certain time period during video playback, a generative AI model may output an anger level of 76% for that time period or a related time period (e.g., a time period after the time required for posting the comment has elapsed since the time period). The emotional information output by such an existing generative AI model may be stored in association with the viewer's comment. Furthermore, the emotional information of a viewer for a certain time period may be determined based on the emotional information determined for each of multiple comments made by the viewer over a predetermined period of time (e.g., 5 seconds). For example, the average emotional information of all comments made during a certain time period may be determined as the viewer's emotional information for that time period or a related time period.

[0020] Furthermore, among the various scenes in videos such as gameplay broadcasts, there are also scenes in which viewers "quietly get excited." A "quietly exciting scene" is a scene in which viewers hold their breath, as it depicts a story that approaches its core. Although the audio is quiet, the viewer feels anxious and excited. Since such a "quietly exciting scene" is expected to be immediately followed by a scene with high audio and comments, it is possible to estimate which scene it corresponds to by working backward from the exciting scene. Furthermore, it is possible to determine which scene is a "quietly exciting scene" based on the emotional information of the scene from the content of remarks and comments made in the video. A "quietly exciting scene" that can be identified in this way is one of the scenes that should be included when generating video previews for the target audience of "experts."

[0021] Furthermore, information indicating emotions may be received not for each scene but for each second. For example, information indicating a change in excitement level over time may be received, as shown in the graph in FIG. 3B (the horizontal axis represents time, and the vertical axis represents excitement level).

[0022] Next, the determination unit 12 determines video preview generation policy information for each of the pre-classified target demographics based on the information related to the video preview generation instruction (step S2). Here, the determination unit 12 may determine which scene in the video to use for each of the target demographics.

[0023] In the example shown in FIG. 4, the determination unit 12 determines the following "video preview generation policy" as a "target demographic": users who are unfamiliar with the work featured in the video or unsubscribed to the channel; scenes that are highly positive or have a high level of fun or joy are utilized as the emotion of the scene. Specific examples of such scenes include: scenes that explain the worldview or system of the work; scenes that do not use much technical terminology; and scenes with dramatic visual changes.

[0024] Next, the output unit 13 outputs an instruction to the prompt, which is input information to the LLM 30, to instruct the LLM 30 to generate a video preview for each target demographic based on the video preview generation policy information for each target demographic (i.e., instructs the LLM 30 to generate a video preview) (step S3). Figure 5 shows an example of an instruction based on the determination example shown in Figure 4. Examples of instructions include the following: "Role: Video Creator. Task: Generate a video preview based on the following information. Also, output the relevant playback time of the original video, comment information for the relevant scene, and other recommended videos. Condition: The target demographic should be "users who are unfamiliar with the work featured in the video or unsubscribed to the channel." - Output video candidates suitable for the target demographic as other recommended videos. - Check the generated video preview so as not to damage the image of the original video. - When selecting a scene, wait until the conversation has finished so as not to interrupt the conversation. - When selecting a scene, output the selected scenes in a ranking format in order of suitability for the target demographic."

[0025] As an example different from the above-described Figures 4 and 5, an example of video preview generation policy information determination and instruction sentences is shown in Figure 6. As shown in Figure 6, the determination unit 12 determines, based on the above (1) and (2), "Scene 1," which is an "intro," as a video for the target demographic "beginners," and "Scenes 2 and 3," which are "game play-by-play videos," as candidates for the target demographic "channel subscribers." Furthermore, comparing Scene 2 and Scene 3, Scene 2 has a larger number of posted comments, and therefore determines "Scene 2," which has a relatively larger number of posted comments.

[0026] Here, as an "alternative option," instead of a single scene, "both Scenes 2 and 3," which are "live game broadcasts," may be determined as the video for the target demographic "channel subscribers." Here, the output unit 13 may associate Scene 2 and Scene 3 with the "number of comments posted" in an instruction statement, and output the following instruction, which instructs prioritization based on the number of comments posted, to the prompt that serves as input information to the LLM 30. Examples of instructions in this case include: "Generate a video preview by referring to the following video information for channel subscribers: - Generate using all enclosed video files. - Give priority to files with the most comments posted. - Video information for channel subscribers: Scene 2, number of comments posted: 100 - Video information for channel subscribers: Scene 3, number of comments posted: 80." In this case, multiple videos can be used to generate a video by referring to related information. This has the advantage of preventing unused videos and avoiding situations where any videos go to waste.

[0027] 2, if there is a response of the generation result (advice on task management) from the LLM 30 (YES in step S4), the output unit 13 acquires advice information, as described below, from the LLM 30 as the generation result from the LLM 30, and outputs the acquired advice information to the terminal 20 (step S5), thereby allowing the user to check the content of the advice information.

[0028] As shown in Figure 7, examples of generated results (advice) include: Video (from what minute to what minute); Comments (author, time of entry, comment, emotional information); Ranking of exciting scenes (top three scenes) (for example, scenes with frequent changes in audio and video, scenes with a large number of comments, scenes with drastic changes in emotions, etc.).

[0029] According to the embodiment described above, by utilizing a generative AI model (here, LLM), it is possible to easily obtain video previews with content appropriate for the target demographic.

[0030] Various modifications of the above embodiment are described below. (Modification 1) Video data for each target demographic, which is useful for generating videos with retroactive effects for each target demographic, may be stored in advance in a database provided within the information processing device 10 or in an external device accessible from the information processing device 10. The output unit 13 may output to the LLM 30 generation request information including the video data for each target demographic that is useful for the current target demographic from among the stored video data for each target demographic. For example, the database may store (a) scene types and (b) information on "target demographics with high retroactive effects" associated with the scene types. Furthermore, for the "retroactive effect," a numerical value indicating the degree of effect for each target demographic (e.g., for non-viewers = 70, for subscribers of related channels = 30, for all channel subscribers = 20) may be derived using a learning model that has previously learned related information about the video (e.g., the number of video changes from start to finish, the number of comments posted on the video, etc.) and the retroactive effect on the target demographic. As the above learning model, for example, a learning model may be used in which target demographic nodes and related information nodes of a video are characterized, and the model is trained based on whether or not each target viewer has given a "high rating (e.g., a "like")" as feedback.

[0031] (Variation 2) The output unit 13 may acquire emotional information for each playback time of the video, and output to the LLM 30 (1) the acquired emotional information for each playback time, and (2) an instruction statement including a command to generate a video preview using video from a time around the time when the emotion is changing or the joy exceeds a certain threshold.

[0032] (Variations Related to the Configuration of System 1) System 1 is not limited to the configuration shown in FIG. 1 . As shown in FIG. 8( a), the system 1 may have a configuration in which the information processing device 10 is included in the terminal 20. This configuration can be realized, for example, by installing an application that executes the functions of the information processing device 10 on the terminal 20. The LLM 30 exists externally (e.g., on the cloud). Alternatively, as shown in FIG. 8( b), the information processing device 10 and the LLM 30 may be included in the terminal 20. This configuration can be realized, for example, by installing an application that executes the functions of the information processing device 10 and an application that executes the functions of the LLM 30 on the terminal 20. In any of the configurations shown in FIGS. 1, 8( a), and 8( b), an external server (e.g., an internal server of a company) that can be a source of information related to business operations exists externally (e.g., on a network).

[0033] The gist of the present disclosure lies in the following [1] to [8]. [1] An information processing device comprising: a receiving unit that receives information related to a video preview generation instruction, the information being for instructing the generation of a video preview and including at least video or comments related to the video; a determination unit that determines video preview generation policy information, which is information related to a policy for generating a video preview, for each pre-classified target demographic based on the information related to the video preview generation instruction; and an output unit that outputs generation request information for instructing the generation of a video preview for each target demographic based on the video preview generation policy information for each target demographic to a generation AI model. [2] The information related to the video preview generation instruction further includes emotion information that expresses a viewer's emotion at a scene included in the video, and the determination unit determines the video preview generation policy information based on the information related to the video preview generation instruction including the emotion information. [3] The information processing device described in [1] or [2], wherein the output unit outputs the generation request information including video data corresponding to a target demographic from pre-stored video data for each target demographic that is useful for generating a video with a retroactive effect for each target demographic. [4] The information processing device according to any one of [1] to [3], wherein the output unit acquires emotion information for each playback time of the video, and outputs the acquired emotion information for each playback time and the generation request information including a request to generate a video preview using video of scenes extracted based on a time-series change in the emotion information. [5] The information processing device according to any one of [1] to [4], wherein the output unit outputs a plurality of reference video data prepared in advance for each target demographic, the reference video data including video data of one or more scenes in the video and comment post count information of comments posted on the scenes, and the generation request information including a request to generate a video preview by referring to at least one of the reference video data prioritized based on the comment post count information.[6] The information processing device according to any one of [1] to [5], wherein the output unit receives and outputs the video preview for each of the target demographics as a generation result output from the generative AI model in response to input of the generation request information to the generative AI model. [7] An information processing method comprising: a step of the information processing device receiving information related to a video preview generation instruction, the video preview generation instruction including at least video or comments related to the video, a step of the information processing device determining video preview generation policy information, which is information related to a generation policy of the video preview, for each of pre-classified target demographics, based on the information related to the video preview generation instruction, and a step of the information processing device outputting generation request information for instructing generation of a video preview for each of the target demographics, based on the video preview generation policy information for each of the target demographics, to the generative AI model.

[0034] [Explanation of Terms, Explanation of Hardware Configuration (FIG. 9), etc.] The block diagrams used in the description of the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may be realized by combining the single device or multiple devices with software.

[0035] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0036] For example, an information processing device according to an embodiment of the present disclosure may function as a computer that executes the processes of the present disclosure. Fig. 9 is a diagram illustrating an example of a hardware configuration of an information processing device 10 according to an embodiment of the present disclosure. The information processing device 10 described above 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, etc.

[0037] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information processing device 10 may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0038] Each function of the information processing device 10 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0039] The processor 1001 controls the entire computer by running, for example, an operating system, and may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc.

[0040] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and 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-described embodiments. While the 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 by one or more chips. The programs may be transmitted from a network via a telecommunications line.

[0041] The memory 1002 is a computer-readable recording medium and may be configured by, for example, at least one of 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 an embodiment of the present disclosure.

[0042] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, 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 (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) 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 at least one of memory 1002 and storage 1003.

[0043] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD).

[0044] 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).

[0045] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0046] The information processing 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 using at least one of these pieces of hardware.

[0047] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0048] Each aspect / embodiment described in the present disclosure may be implemented using any of the following standards: LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), 6th generation mobile communication system (6G), xth generation mobile communication system (xG) (xG (x is, for example, an integer or a decimal number)), FRA (Future Radio Access), NR (new Radio), New radio access (NX), Future generation radio access (FX), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.17 (WiMAX (registered trademark)), IEEE 802.19 (WiMAX (registered trademark)), IEEE 802.20 (WiMAX (registered trademark)), IEEE 802.21 (Wi-Fi (registered trademark)), IEEE 802.22 (WiMAX (registered trademark)), IEEE 802.23 (WiMAX (registered trademark)), IEEE 802.24 (WiMAX (registered trademark)), IEEE 802.25 (WiMAX (registered trademark)), IEEE 802.26 (WiMAX (registered trademark)), IEEE 802.27 (WiMAX (registered trademark)), IEEE 802.28 (WiMAX (registered trademark)), IEEE 802.29 (WiMAX (registered trademark)), IEEE 802.30 (WiMAX (registered trademark)), IEEE 802.31 (Wi-Fi (registered trademark)), IEEE 802.32 (WiMAX (registered trademark)), IEEE 802.33 (WiMAX (registered trademark)), IEEE 802.34 ( The present invention may be applied to at least one of systems using 802.20, Ultra-Wideband (UWB), Bluetooth, or other suitable systems, and next-generation systems that are extended, modified, created, or defined based on these systems. It may also be applied to a combination of multiple systems (e.g., a combination of LTE and / or LTE-A with 5G).

[0049] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0050] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0051] 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).

[0052] The aspects / embodiments described in this disclosure may be used alone, in combination, or 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).

[0053] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0054] 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.

[0055] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0056] The information, signals, etc. described in this disclosure may be represented using any 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.

[0057] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0058] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0059] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information. For example, a radio resource may be indicated by an index.

[0060] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0061] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0062] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0063] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure 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 or that the first element must in some way precede the second element.

[0064] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0065] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0066] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0067] 1...system, 10...information processing device, 11...reception unit, 12...decision unit, 13...output unit, 20...terminal, 30...LLM, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device, 1007...bus.

Claims

1. An information processing device comprising: a reception unit that receives information regarding a video preview generation instruction, the information being for instructing the generation of a video preview and including at least video or comments related to the video; a determination unit that determines video preview generation policy information, which is information regarding a policy for generating a video preview, for each pre-classified target group based on the information regarding the video preview generation instruction; and an output unit that outputs generation request information for instructing the generation of a video preview for each target group to a generation AI model based on the video preview generation policy information for each target group.

2. The information processing device of claim 1, wherein the information regarding the video preview generation instruction further includes emotional information that represents the viewer's emotions at the scene included in the video, and the determination unit determines the video preview generation policy information based on the information regarding the video preview generation instruction that includes the emotional information.

3. The information processing device according to claim 1, wherein the output unit outputs the generation request information including the video data corresponding to the target demographic among the pre-stored video data for each target demographic that is useful for generating a video with retroactive effect for each target demographic.

4. The information processing device according to claim 1, wherein the output unit acquires emotional information for each playback time of the video, and outputs the acquired emotional information for each playback time and the generation request information including a request to generate a video preview using video of a scene extracted based on chronological changes in the emotional information.

5. The information processing device of claim 1, wherein the output unit outputs: a plurality of reference video data prepared in advance for each target demographic, including video data of one or more scenes in the video and comment count information for comments posted about the scenes; and generation request information indicating that a video preview is to be generated by referring to at least one of the plurality of reference video data prioritized based on the comment count information.

6. The information processing device according to claim 1, wherein the output unit receives and outputs the video preview for each target demographic as a generation result output from the generation AI model in response to input of the generation request information to the generation AI model.

7. An information processing method comprising: a step in which an information processing device receives information regarding a video preview generation instruction, the information being for instructing the generation of a video preview and including at least video or comments related to the video; a step in which the information processing device determines video preview generation policy information, which is information regarding a generation policy for a video preview, for each pre-classified target group based on the information regarding the video preview generation instruction; and a step in which the information processing device outputs generation request information to a generation AI model, for instructing the generation of a video preview for each target group based on the video preview generation policy information for each target group.

Images