Moving image evaluation system, moving image evaluation method, and program

Abstract

To provide a technique that enables more efficient shooting of moving images with high presentation effect. [Solution] One aspect of the present invention is a moving image evaluation system that includes a simulator that performs a real environment simulation, simulating the state of a real environment, which is the actual environment in which a user shoots moving images to be presented to viewers, and the shooting of the moving images in the real environment, and an evaluation device that evaluates the results of the real environment simulation from a first evaluation perspective related to the purpose of presenting the moving images to the viewers.The real environment simulation reproduces the real environment in a virtual space and outputs moving images captured in the virtual space by a virtual camera as simulation results, and the evaluation device inputs the moving images captured in the real environment simulation into a predetermined trained model, thereby outputting evaluation results for the purpose of the moving images.

Description

[Technical Field]

[0001] The present invention relates to a moving image evaluation system, a moving image evaluation method, and a program technology. [Background technology]

[0002] Conventionally, a technique has been proposed in which the effect (presentation effect) of a production such as a video on a presentation target is estimated using a trained model constructed by machine learning, and the production is evaluated based on the estimation result (see, for example, Patent Document 1 and Non-Patent Document 1). Such a technique enables users to efficiently produce productions with high presentation effect.

[0003] Meanwhile, a technique has been proposed for improving the efficiency of shooting moving images in a real environment through simulation (see, for example, Non-Patent Document 2). According to the technique in Non-Patent Document 2, a user can decide on a satisfactory shooting pattern through simulation and then shoot in a real environment, thereby enabling the user to efficiently create a desired moving image. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6993947 [Non-patent literature]

[0005] [Non-Patent Document 1] "AI revolutionizes advertising creative production, launching 'Extreme Predictive AI', a fee structure where compensation is only paid when advertising is effective," [online], May 15, 2020, CyberAgent, Inc., [Retrieved July 29, 2024], Internet<URL:https: / / www.cyberagent.co.jp / news / detail / id=24647> [Non-patent document 2] “Why FrameForge”, [online], Innoventive Software, LLC, [Retrieved July 29, 2024], Internet<URL:https: / / www.frameforge.com / pages / why-frameforge> Summary of the Invention [Problem to be solved by the invention]

[0006] However, conventional technologies have not always been able to efficiently capture moving images with a high presentation effect that matches the purpose. For example, with the technologies of Patent Document 1 and Non-Patent Document 1, if the number of productions to be evaluated is increased in order to improve the presentation effect, the shooting process in the real environment becomes a bottleneck, resulting in a trade-off between improved quality and efficiency. This is also true even if the technology of Non-Patent Document 2 replaces much of the shooting with simulation.

[0007] In view of the above circumstances, an object of the present invention is to provide a technique that enables more efficient shooting of moving images that are suited to a purpose and have a high presentation effect. [Means for solving the problem]

[0008] One aspect of the present invention is a moving image evaluation system that includes a simulation device that performs a real environment simulation, which simulates the state of a real environment, which is the actual environment in which a user shoots moving images to be presented to viewers, and the shooting of the moving images in the real environment, and an evaluation device that evaluates the results of the real environment simulation from a first evaluation perspective related to the purpose of presenting the moving images to the viewers, wherein the real environment simulation reproduces the real environment in a virtual space and outputs moving images captured in the virtual space by a virtual camera as simulation results, and the evaluation device evaluates the results of the real environment simulation based on the moving images as the simulation results or parameters of the real environment simulation.

[0009] One aspect of the present invention is the above-mentioned moving image evaluation system, wherein the evaluation device inputs moving images captured in the virtual space into a trained model that has been trained to output evaluation results for the moving images from the first evaluation perspective, thereby outputting evaluation results for the moving images with respect to the objective.

[0010] One aspect of the present invention is the above-mentioned moving image evaluation system, wherein the evaluation device inputs the parameters to be evaluated into a trained model that has been trained to use the parameters as input and output evaluation results from the first evaluation perspective of moving images obtained by real-world environment simulation using the parameters of the object to be evaluated, thereby outputting evaluation results for the purpose of moving images obtained by real-world environment simulation using the parameters of the object to be evaluated.

[0011] One aspect of the present invention is the above-mentioned video evaluation system, further comprising a shooting plan generation device that generates a shooting plan that describes, in a human-understandable manner, information for shooting video images acquired as a result of the real environment simulation in the real environment based on the parameters, and the evaluation device outputs an evaluation result of the video images with respect to the purpose by inputting the shooting plan to be evaluated into a trained model that is trained to use the shooting plan as input and output an evaluation result from the first evaluation perspective of video images acquired by the real environment simulation using the parameters related to the shooting plan.

[0012] One aspect of the present invention is the above-mentioned moving image evaluation system, further comprising a scanning device that reads information about the real environment, and the simulating device reproduces the real environment in the virtual space using the scan results obtained by the scanning device reading the information about the real environment.

[0013] One aspect of the present invention is the above-mentioned moving image evaluation system, wherein the simulator reproduces sound, light, or weather in the real environment in the virtual space in the real environment simulation.

[0014] One aspect of the present invention is the above-mentioned moving image evaluation system, further comprising a parameter generation device that generates parameters used by the simulator to execute the real environment simulation, the parameter generation device having a function of changing part or all of a parameter set to generate a new parameter set, and repeatedly executing the real environment simulation using the changed parameter set by the parameter generation device and the simulator.

[0015] One aspect of the present invention is the above-mentioned moving image evaluation system, wherein the parameter generation device comprises: By inputting a third parameter set to be estimated into a trained model that has learned the relationship between a first parameter set of the real environment simulation and an evaluation result of a real environment simulation using a second parameter set, which has some parameter values ​​different from those of the first parameter set and has obtained a higher evaluation result than the evaluation result of the first parameter set, a fourth parameter set that can obtain a higher evaluation result than the third parameter set is estimated.

[0016] One aspect of the present invention is the above-mentioned moving image evaluation system, wherein the parameter generation device estimates parameters for reproducing the moving image of the object to be reproduced in the real environment simulation by inputting the moving image of the object to be reproduced into a trained model that has been trained to take the moving image as input and output parameters for obtaining the moving image as a result of the real environment simulation.

[0017] One aspect of the present invention is the above-mentioned moving image evaluation system, in which a second evaluation perspective of the real environment simulation is input in text format to the evaluation device via the user's terminal device, and the evaluation device evaluates the results of the real environment simulation based on the first evaluation perspective or the second evaluation perspective.

[0018] One aspect of the present invention is a moving image evaluation method having a first step in which a simulation device performs a real environment simulation, in which the real environment is the actual environment in which a user shoots a moving image to be presented to a viewer, to simulate the state of the real environment and the shooting of the moving image in the real environment, and a second step in which an evaluation device evaluates the results of the real environment simulation from a first evaluation perspective related to the purpose of presenting the moving image to the viewer, wherein the real environment simulation reproduces the real environment in a virtual space and outputs a moving image captured in the virtual space by a virtual camera as a simulation result, and the second step evaluates the results of the real environment simulation based on the moving image as the simulation result or the real environment simulation parameters.

[0019] One aspect of the present invention is a program for causing one or more processors to execute: a first step of performing a real environment simulation, which simulates the state of a real environment, which is the actual environment in which a user shoots a moving image to be presented to a viewer, and the shooting of the moving image in the real environment; and a second step of evaluating the results of the real environment simulation from a first evaluation perspective related to the purpose of presenting the moving image to the viewer, wherein the real environment simulation reproduces the real environment in a virtual space and outputs a moving image captured of the virtual space by a virtual camera as a simulation result, and the second step evaluates the results of the real environment simulation based on the moving image as the simulation result or the real environment simulation parameters. [Effects of the Invention]

[0020] According to the present invention, it is possible to more efficiently capture moving images that are suited to a purpose and have a high presentation effect. [Brief explanation of the drawings]

[0021] [Figure 1] FIG. 1 is a diagram showing an example of a system configuration of a moving image evaluation system 1A according to a first embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of a functional configuration of a simulation device 300 according to the first embodiment. [Figure 3] FIG. 2 is a diagram illustrating an example of a functional configuration of a shooting plan generating device 400 according to the first embodiment. [Figure 4] FIG. 2 is a diagram illustrating an example of a functional configuration of an evaluation device 500 according to the first embodiment. [Figure 5] This is an image (part 1) showing an outline of the real-world environment simulation. [Figure 6] This is an image (part 2) showing an outline of the real-world environment simulation. [Figure 7] FIG. 2 is a diagram showing an example of the processing flow of the moving image evaluation system 1A of the first embodiment. [Figure 8] FIG. 10 is a diagram showing an example of the system configuration of a moving image evaluation system 1B according to a second embodiment. [Figure 9] FIG. 10 is a diagram showing an example of the system configuration of a moving image evaluation system 1C according to a third embodiment. [Figure 10] FIG. 10 is a diagram illustrating a third modified example of the moving image evaluation system 1 according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0022] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0023] First Embodiment FIG. 1 is a diagram illustrating an example of the system configuration of a video evaluation system 1A according to a first embodiment. The video evaluation system 1A simulates the shooting of a video in a real environment R, evaluates the simulation results (videos acquired through the simulation), and presents the results to a user U. The video evaluation system 1A according to the embodiment applies the shooting conditions under which the user U obtained highly rated simulation results to the real environment R, thereby enabling efficient production of a video that matches the purpose and has a high presentation effect. The video may be an image, a video that plays multiple time-series images, or both. For example, the video may be one that the user U presents to a viewer for the above-mentioned purpose. As an example, the video may be a video promoting an advertisement, in which case the purpose may be to enhance the advertising effect.

[0024] The video evaluation system 1A includes, for example, a user terminal device 100, a parameter generation device 200, a simulation device 300, a shooting plan generation device 400, and an evaluation device 500. The user terminal device 100, the parameter generation device 200, the simulation device 300, the shooting plan generation device 400, and the evaluation device 500 can communicate with each other via a network NW. The network NW may be a network using wireless communication or a network using wired communication. The network NW may be configured using, for example, the Internet or a local area network (LAN). The network NW may be configured by combining a plurality of networks.

[0025] The user terminal device 100 is a terminal device used by a user U of the video evaluation system 1A. For example, the user terminal device 100 may be a terminal device such as a smartphone, a tablet, or a personal computer. A user interface runs on the user terminal device 100. The user U can interact with the video evaluation system 1A by operating the user interface. The user interface may be a dedicated application program or a web application provided via a web browser.

[0026] The parameter generating device 200 is a device that generates parameters for a process (hereinafter referred to as "real environment simulation process") in which a simulator 300, which will be described later, simulates the shooting of moving images in a real environment R in a virtual space. The parameter generating device 200 accepts a parameter setting operation from the user terminal device 100 and supplies the set parameters to the simulator 300 and the photography plan generating device 400. The parameters are parameters for reproducing the shooting in the real environment R in a virtual space. More specifically, the parameters include parameters (space reproduction parameters) for virtually reproducing the state of the space to be shot in the real environment R, and parameters (shooting parameters) for shooting the state of the virtually reproduced space (virtual space) with a virtual camera. The space reproduction parameters include parameters related to the shape and decoration of the virtual space, and parameters related to the placement and movement of objects in the virtual space. The shooting parameters include parameters related to camerawork control, etc. 3D objects include static objects such as tables, chairs, and desks, as well as dynamic objects that move within the virtual space (such as walking people, running animals, moving machines, and moving objects).

[0027] The parameter generation device 200 can generate and change parameters based on setting operations by the user, and can also change a part of a group of parameters (hereinafter referred to as a "parameter set") used in one real environment simulation to generate a new parameter set. The parameter generation device 200 may randomly select parameters to be changed, or may select parameters to be changed based on the results of a simulation using a parameter set before change. The parameter generation device 200 may also randomly change the values ​​of parameters, or may determine the values ​​of the changed parameters based on the results of a simulation using the parameter set before change.

[0028] The simulator 300 is a device that executes a real environment simulation. More specifically, the simulator 300 executes a first simulation that reproduces the state of a virtual space in time series, and a second simulation that captures the state of the virtual space reproduced by the first simulation in time series. The simulator 300 supplies the moving images captured by the second simulation to the evaluation device 500 as a simulation result. The simulator 300 may also include a parameter set used in the real environment simulation in the simulation result and supply it to the evaluation device 500.

[0029] The photographing plan generating device 400 is a device that generates information (hereinafter referred to as "photography plan") indicating a plan for a user U to reproduce simulation results in a real environment R. The photographing plan generating device 400 generates a photographing plan based on parameters supplied from the parameter generating device 200. For example, the photographing plan includes information for reproducing, in the real environment R, the simulation environment reproduced in a virtual space. For example, when a performance by a virtual actor (an example of a dynamic object defined by parameters) is reproduced in the real environment simulation, the photographing plan may include information as a script or storyboard that instructs a real actor who will perform in the real environment R on the content of the performance by the virtual actor (for example, standing position, movement, facial expression, lines, etc.). The photographing plan generating device 400 supplies the generated photographing plan to the evaluation device 500.

[0030] As described above, the state of the virtual space reproduced in the real environment simulation is based on the parameters generated by the parameter generation device 200, and therefore the photography plan is essentially synonymous with the parameters of the real environment simulation. However, parameters are generally data expressed in a format that can be interpreted by the simulation device 300, and are not necessarily expressed in a format that allows a person to visually understand the content and meaning. Therefore, the photography plan generation device 400 generates a photography plan by converting the content and meaning of the parameters of the real environment simulation into a format that can be visually understood by a person. Note that the photography plan only needs to include information necessary for the user U to perform photography in the real environment R, and does not necessarily need to include information corresponding to all parameters.

[0031] The evaluation device 500 is a device that evaluates the simulation results obtained by the simulation device 300. More specifically, the evaluation device 500 scores each of the videos provided as simulation results from the simulation device 300 to determine how well the videos match the objectives. The evaluation device 500 determines the videos to be presented to the user U based on the scores of multiple videos generated by real-environment simulations for the same objective, and provides a shooting plan for the videos to the user terminal device 100.

[0032] The user U can create a moving image that matches the purpose (highly effective presentation) by performing shooting in a real environment using the shooting plan provided to the user terminal device 100.

[0033] FIG. 2 is a diagram illustrating an example of the functional configuration of the simulator 300 according to the first embodiment. The simulator 300 includes, for example, a parameter input unit 310, a storage unit 320, and a control unit 330. The control unit 330 includes, for example, a processor such as a central processing unit (CPU) and a memory. The control unit 330 functions as a first simulation execution unit 331 and a second simulation execution unit 332 when the processor executes a program. Note that all or part of the functions of the control unit 330 may be implemented using hardware such as an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA). The program may be recorded on a computer-readable recording medium. Examples of the computer-readable recording medium include portable media such as a flexible disk, a magneto-optical disk, a read-only memory (ROM), a CD-ROM, and a semiconductor storage device (e.g., a solid-state drive (SSD)), as well as storage devices such as a hard disk or semiconductor storage device built into a computer system. The program may be transmitted via a telecommunications line.

[0034] The parameter input unit 310 includes a network interface for communicating with other devices via the network NW, and receives input of parameters for executing a real environment simulation from the parameter generation device 200. The network interface may be a device that performs wireless communication or a device that performs wired communication. The parameter input unit 310 stores the input parameters in the storage unit 320.

[0035] The storage unit 320 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 320 stores the parameters of the real environment simulation input from the parameter generation device 200 by the parameter input unit 310. The storage unit 320 may be used as an area for storing a program for performing the real environment simulation, an area for saving temporary data generated during the execution of the real environment simulation, or an area for saving the execution results of the real environment simulation.

[0036] The control unit 330 controls the first simulation execution unit 331 and the second simulation execution unit 332 to realize a real environment simulation. The first simulation execution unit 331 executes the first simulation, and the second simulation execution unit 332 executes the second simulation. The control unit 330 runs the first simulation and the second simulation simultaneously in parallel to generate a moving image in which the state of the virtual space is captured in time series. The control unit 330 supplies the moving image generated by the second simulation execution unit 332 to the evaluation device 500 as a result of the real environment simulation.

[0037] FIG. 3 is a diagram showing an example of the functional configuration of the shooting plan generating device 400 of the first embodiment. The shooting plan generating device 400 includes, for example, a parameter input unit 410, a storage unit 420, and an shooting plan generating unit 430. The shooting plan generating unit 430 is configured using, for example, a processor such as a CPU (Central Processing Unit) and a memory. The shooting plan generating unit 430 is realized by the processor executing a program. Note that all or a part of the shooting plan generating unit 430 may be realized using hardware such as an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array). The above program may be recorded on a computer-readable recording medium. Examples of the computer-readable recording medium include portable media such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, and a semiconductor storage device (e.g., an SSD: Solid State Drive), and storage devices such as a hard disk and a semiconductor storage device built into a computer system. The above program may be transmitted via a telecommunications line.

[0038] The parameter input unit 410 includes a network interface for communicating with other devices via the network NW, and receives input of parameters for generating a shooting plan from the parameter generation device 200. The network interface may be a device that performs wireless communication or a device that performs wired communication. The parameter input unit 410 stores the input parameters in the storage unit 420.

[0039] The storage unit 420 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 420 stores the parameters of the real environment simulation input from the parameter generating device 200 by the parameter input unit 410. The storage unit 420 may be used as an area for storing a program for executing a process for generating a photoshoot plan, may be used as an area for saving temporary data generated during the execution of the process for generating a photoshoot plan, or may be used as an area for saving the generated photoshoot plan.

[0040] The shooting plan generation unit 430 generates a shooting plan based on the parameters of the real environment simulation input from the parameter generation device 200. For example, the shooting plan generation unit 430 may generate a shooting plan by converting the parameters of the virtual space into a predetermined format (such as a script or storyboard) that is understandable to humans. The conversion may be performed using a rule-based conversion model, or may be performed using a trained model that has learned the relationship between parameters and formats through machine learning. Furthermore, the shooting plan generation unit 430 may be configured to output a shooting plan with improved readability by using a natural language processing model such as an LLM (Large Language Model). The shooting plan generation unit 430 supplies the generated shooting plan to the evaluation device 500. Any machine learning model may be used, such as a neural network, deep learning, or reinforcement learning.

[0041] FIG. 4 is a diagram illustrating an example of the functional configuration of the evaluation device 500 according to the first embodiment. The evaluation device 500 includes, for example, a simulation result input unit 510, a storage unit 520, and a simulation result evaluation unit 530. The simulation result evaluation unit 530 is configured using a processor such as a central processing unit (CPU) and a memory. The simulation result evaluation unit 530 is implemented by the processor executing a program. Note that all or part of the functions of the simulation result evaluation unit 530 may be implemented using hardware such as an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA). The program may be recorded on a computer-readable recording medium. Examples of the computer-readable recording medium include portable media such as a flexible disk, a magneto-optical disk, a read-only memory (ROM), a CD-ROM, and a semiconductor storage device (e.g., a solid-state drive (SSD)), as well as storage devices such as a hard disk or semiconductor storage device built into a computer system. The program may be transmitted via a telecommunications line.

[0042] The simulation result input unit 510 includes a network interface for communicating with other devices via the network NW, and receives input of the results (moving images) of the real environment simulation from the simulator 300. The network interface may be a device that performs wireless communication or a device that performs wired communication. The simulation result input unit 510 stores the input simulation results in the storage unit 320.

[0043] The storage unit 520 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 520 stores information such as the results of the real environment simulation input from the simulator 300 by the simulation result input unit 510, and an evaluation model 521 used to evaluate the simulation results. The storage unit 520 may be used as an area for storing a program for performing a process for evaluating the simulation results, may be used as an area for saving temporary data generated in the evaluation process, or may be used as an area for saving the execution results of the real environment simulation.

[0044] The simulation result evaluation unit 530 evaluates the results of the real-environment simulation input from the simulation device 300 using the evaluation model 521. The evaluation model 521 is a trained model trained by machine learning to input a video of the simulation result and output an evaluation score for the video based on a predetermined evaluation criterion. For example, the evaluation model 521 can be constructed by supervised learning using a pair of video data and evaluation scores as training data. The training data may be video captured by simulation or may be video captured in a real environment based on a shooting plan or simulation results. The training data may reflect the advertising effectiveness obtained by actually presenting video captured in a real environment or a simulation to viewers, or may reflect the results of an advertiser's evaluation of the video. In addition, when there are multiple evaluation criteria, for example, the evaluation model 521 may be configured as a collection of multiple trained models with different evaluation criteria. In addition, for example, in training the evaluation model 521, feature quantities extracted from video data may be used instead of the video data itself. Any machine learning model may be used, such as a neural network, deep learning, or reinforcement learning.

[0045] Furthermore, for example, the evaluation model 521 may be configured as a multimodal LLM capable of combining and processing multiple information sources, such as text data, image data, video data, and audio data. In this case, for example, the evaluation model 521 may be configured to recognize the content and features of the video of the simulation result and score the recognition result by evaluating it against evaluation criteria. For example, examples of multimodal LLM algorithms include LENS, IDEFICS, and GPT-4o. With such a multimodal LLM, the simulation result evaluation unit 530 can evaluate the simulation result more flexibly and accurately by utilizing various data related to the real-environment simulation in addition to the video of the simulation result. For example, the simulation result evaluation unit 530 may be configured to evaluate the simulation result using parameters used in the real-environment simulation and a shooting plan generated based on the parameters.

[0046] The simulation result evaluation unit 530 acquires an evaluation score for each simulation result by performing evaluation processing using the evaluation model 521 for each simulation result to be evaluated. The simulation result evaluation unit 530 ranks the simulation results using the acquired evaluation scores, determines a photoshoot plan to be presented to the user U based on the ranking result, and supplies the determined photoshoot plan to the user terminal device 100.

[0047] Fig. 5 is an image diagram showing an outline of the real environment simulation. Fig. 5 illustrates how the real environment simulation is performed simultaneously with a first simulation that reproduces the state of the virtual space VR and a second simulation that uses virtual cameras CV1 to CV4 to capture the state of the virtual space VR reproduced by the first simulation. The first simulation execution unit 331 generates the virtual space VR by applying space reproduction parameters generated by the parameter generation device 200 to a 3D simulation model. The second simulation execution unit 332 also reproduces the camerawork used by the cameras CV1 to CV4 when capturing the virtual space VR by applying the capture parameters generated by the parameter generation device 200 to the 3D camera model.

[0048] 6, the first simulation execution unit 331 may be configured to reproduce, in the virtual space VR, not only the subject and its movements, but also other audiovisual elements related to the appeal of the video, such as sound and light. For example, sound effects, dialogue, background sounds, sounds emitted by objects, light emitted by objects, changes in light, and effects using light may be reproduced. Furthermore, for example, environmental elements such as weather may be reproduced by combining sound and visual effects.

[0049] The second simulation executing unit 332 may also be configured to record audio reproduced in the virtual space VR in synchronization with the shooting of the virtual space VR. In this case, the simulation device 300 can simulate shooting in a form closer to the real environment R, and the evaluation device 500 can perform highly accurate evaluation of the moving image of the simulation result at a level closer to the real environment R.

[0050] In this case, the parameter generating device 200 may be configured to generate a combination of parameters (parameter set) including variations in audio and visual effects. This allows the user U to obtain a shooting plan with a higher presentation effect from among shooting plans corresponding to a greater number of shooting patterns, and enables the user U to shoot a moving image in the real environment R that better matches the purpose.

[0051] 7 is a diagram showing an example of the processing flow of the video evaluation system 1A of the first embodiment. First, a user U operates the user terminal device 100 to set parameters related to the real environment simulation (S101). Next, the parameter generation device 200 generates parameters for the real environment simulation based on the settings made in S101 (S102). Here, a case will be described in which the parameter generation device 200 generates a plurality of parameter sets. The parameter generation device 200 selects one of the plurality of parameter sets and supplies it to the simulator device 300 and the shooting plan generation device 400 (S103, S104).

[0052] Next, the simulator 300 executes a real environment simulation using the parameter set input from the parameter generating device 200 in S103 (S105). The simulator 300 supplies the result of the real environment simulation executed in S105 to the evaluation device 500 (S106). In S106, in addition to the moving image of the simulation result, the parameter set corresponding to the executed real environment simulation may be supplied.

[0053] Meanwhile, the shooting plan generation device 400 generates a shooting plan based on the parameter set input from the parameter generation device 200 in S103 (S107). The shooting plan generation device 400 supplies the shooting plan generated in S107 to the evaluation device 500 (S108). Subsequently, the evaluation device 500 executes evaluation processing on the simulation result input from the simulator 300 in S106 (S109). The evaluation device 500 stores the simulation result in S109 in association with the shooting plan generated in S107.

[0054] The above steps correspond to one parameter set selected and input in S103, and the group of steps S103 to S109 (indicated by dashed lines) is executed for each of the parameter sets generated in S102. After the steps S103 to S109 have been executed for all of the parameter sets generated in S102, the evaluation device 500 then determines a shooting plan to be presented to the user U based on the evaluation results of the real-environment simulations corresponding to the parameter sets (S110). For example, the evaluation device 500 may determine the shooting plan corresponding to the simulation result with the highest evaluation score as the shooting plan to be presented to the user U, or may determine the shooting plan corresponding to the simulation result with an evaluation score equal to or higher than a reference value as the shooting plan to be presented to the user U. The evaluation device 500 supplies the shooting plan determined in S110 to the user terminal device 100 (S111). Then, the user U performs shooting in the real environment using the shooting plan provided in S111, thereby efficiently capturing a video that matches the purpose and has a high presentation effect.

[0055] According to the video evaluation system 1A of the first embodiment configured as described above, a shooting pattern to be applied to shooting in a real environment can be searched for by repeating evaluations by simulation, and therefore it becomes possible to shoot a video that matches the purpose and has a high presentation effect more efficiently. Furthermore, according to the video evaluation system 1A of the first embodiment, a shooting pattern (parameter) related to a simulation result that has obtained a high evaluation score is presented to the user in the form of a shooting plan that is easy to understand for those involved in the shooting, so that the user can shoot in a real environment more efficiently.

[0056] Second Embodiment FIG. 8 is a diagram showing an example of the system configuration of a moving image evaluation system 1B of the second embodiment. The moving image evaluation system 1B of the second embodiment differs from the moving image evaluation system 1A of the first embodiment in that it further includes a scanning device 600. The scanning device 600 is a device that reads (scans) the state of the real environment R and supplies the state to the simulator 300. More specifically, the scanning device 600 captures images of people and objects present in the real environment R and supplies the moving images to the simulator 300 as the scan result. The scanning device 600 may also record sounds generated in the real environment R and supply the sound data to the simulator 300 as the scan result.

[0057] The simulator 300 performs a real-environment simulation based on the parameters generated by the parameter generator 200 and the scan results of the real environment R supplied from the scanner 600. By using the scan results of the real environment R in addition to the parameters of the real-environment simulation, the simulator 300 can recreate a virtual space that is closer to the real environment R. Recreating a virtual space that is closer to the real environment R is expected to reduce the difference between the video captured in the simulation and the video captured by recreating the same in the real environment R. As a result, if the video captured in the simulation is evaluated as being in line with the purpose, the likelihood that the video captured by recreating the same in the real environment R will also be in line with the purpose increases, thereby improving the reliability and practicality of the evaluation device 500. From another perspective, it is expected that the degree of agreement between the evaluation scores for the video captured in the simulation and the evaluation scores for the video captured by recreating the same in the real environment R is increased, thereby improving the reliability and practicality of the evaluation device 500.

[0058] <Third embodiment> 9 is a diagram showing an example of the system configuration of a moving image evaluation system 1C of the third embodiment. The moving image evaluation system 1C of the third embodiment differs from the moving image evaluation system 1A of the first embodiment in that the simulator 300 does not supply the results (moving images) of the real environment simulation to the evaluation device 500, but supplies only the parameters of the real environment simulation. The moving image evaluation system 1C of the third embodiment also differs from the moving image evaluation system 1A of the first embodiment in that the evaluation device 500 performs evaluation processing using the parameters of the real environment simulation as input, rather than using the results of the real environment simulation as input.

[0059] As described above, the moving images resulting from the real environment simulation are generated by capturing images of a virtual space reproduced based on the parameters of the real environment simulation. Therefore, it can be considered that there is a correlation between the content of the moving images resulting from the real environment simulation and the parameters of the real environment simulation. Based on this concept, the moving image evaluation system 1C of the third embodiment estimates the evaluation results of the moving images resulting from the simulation using the parameters of the real environment simulation.

[0060] For example, by using machine learning to learn training data paired with the evaluation results of the video evaluation system 1A of the first embodiment and corresponding parameters, an estimation model can be constructed that inputs parameters of a real-environment simulation and outputs an estimated value of an evaluation score. Any machine learning model, such as a neural network, deep learning, or reinforcement learning, can be used. By pre-storing the estimation model constructed in this manner as the evaluation model 521 in the storage unit 520 of the evaluation device 500, the evaluation device 500 can estimate an evaluation score based on the parameters of the real-environment simulation. Furthermore, this configuration reduces the time required for the real-environment simulation, thereby enabling the user U to be provided with a shooting plan for capturing a video that meets the purpose in a shorter time. Furthermore, when the evaluation device 500 inputs a video and performs evaluation, factors related to the quality of the simulation, such as the realism of the rendering, may also affect the evaluation results. In contrast, when the evaluation device 500 inputs parameters and a shooting plan and performs evaluation, the aforementioned factors related to the quality of the simulation can be excluded from the evaluation. This allows evaluation that is not affected by factors specific to the simulation, thereby improving the reliability of the evaluation device 500.

[0061] According to at least one of the embodiments described above, moving images that match the purpose and have a high presentation effect can be captured more efficiently.

[0062] <Modification> Modifications of the moving image evaluation systems 1A to 1C of the embodiment will be described below. Hereinafter, the moving image evaluation systems 1A to 1C will be collectively referred to as the moving image evaluation system 1 unless otherwise specified.

[0063] (First Modification) The parameter generation device 200 may be configured to have a function (hereinafter referred to as a "parameter change function") of estimating parameters (hereinafter referred to as "change target parameters") that should be changed to improve the evaluation score of the simulation result for a parameter set of the real environment simulation, and changing the estimated change target parameters to generate a new parameter set. For example, the change target parameters may be estimated using a trained model (hereinafter referred to as a "change target parameter estimation model") that learns, by machine learning, the relationship between a parameter set (hereinafter referred to as a "first parameter set") for the real environment simulation and an evaluation score for a parameter set (hereinafter referred to as a "second parameter set") that has some parameter values ​​different from the first parameter set. Here, the second parameter set is a parameter set that has obtained an evaluation score higher than the evaluation score of the first parameter set. The change target parameter estimation model is configured to output the difference between the first parameter set and the second parameter set. The change target parameter estimation model may be configured to output the second parameter set.

[0064] By inputting a parameter set to be estimated into the parameter estimation model to be changed that has been trained in this way, the parameter generation device 200 can acquire a parameter set that is (considered to) be able to obtain a higher evaluation score than the input parameter set. In this case, the video evaluation system 1 may be configured to repeatedly estimate the parameters to be changed and execute a real environment simulation with a parameter set in which the parameters to be changed have been changed. This allows the user U to efficiently generate a video with a higher presentation effect.

[0065] (Second Modification) The parameter generating device 200 may be configured to have a function of presenting parameters (hereinafter referred to as "reproduction parameters") for reproducing a moving image specified by a user U in a virtual space of a real environment R. For example, the reproduction parameters may be estimated by a trained model (hereinafter referred to as "reproduction parameter estimation model") that has learned, by machine learning, the relationship between the parameters of a real environment simulation and the results (moving image) of a real environment simulation performed with the parameters. Here, the reproduction parameter estimation model is configured to input a moving image of the simulation results and output a parameter set that is (considered to) be able to obtain the moving image.

[0066] Generally, when shooting a moving image, even if there is a sample of the moving image that the user wants to capture, the user may not know the camerawork or composition required to capture the moving image like the sample, and so must repeatedly perform trial and error in a real environment simulation, which may increase the shooting costs. In contrast, according to the parameter generation device 200 of the second modified example, the user U can input the moving image that the user wants to use as reference into the parameter generation device 200 to obtain parameters for obtaining the moving image through a real environment simulation, thereby efficiently generating a moving image with a higher presentation effect. Note that, when the reproduction parameter estimation model is trained using the results of the real environment simulation, it is desirable that the sample of the moving image that the user wants to capture be captured in the real environment R or a virtual space that simulates the real environment R.

[0067] (Third Modification) FIG. 10 is a diagram illustrating a third modified example of the video evaluation system 1 according to the embodiment. In the third modified example, the user terminal device 100 receives input of evaluation criteria for the simulation results and provides the input evaluation criteria in text format to the evaluation device 500. The user terminal device 100 may receive input of evaluation criteria for each real-world simulation, may receive input of new evaluation criteria to overwrite default evaluation criteria, or may receive input of new evaluation criteria to be added to the default evaluation criteria. In this case, for example, by configuring the evaluation model 521 using a multimodal LLM, the evaluation device 500 can input information about the evaluation criteria provided by the user terminal device 100 into the evaluation model 521, thereby obtaining an evaluation score for the simulation results that takes the evaluation criteria into consideration.

[0068] According to the third variant of the video evaluation system 1, the user U can perform a real-world environment simulation while flexibly changing the evaluation viewpoint, taking into account past simulation results, etc., thereby making it possible to more efficiently capture video images that are highly effective in presenting the intended purpose.

[0069] The moving image evaluation system 1 of the embodiment may be configured in a form that appropriately combines the first to third embodiments and the first to third modified examples. For example, the moving image that is the result of the real environment simulation, the parameters of the real environment simulation, or the shooting plan based on the parameters may be input, and the evaluation result of the real environment simulation may be output.

[0070] Although an embodiment of the present invention has been described above in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and includes designs within the scope of the gist of the present invention. [Industrial Applicability]

[0071] The present invention is applicable to applications that support the creation of moving images having a predetermined presentation effect. [Explanation of symbols]

[0072] 1. 1A~1C Video Evaluation System 100 User terminal device 200 Parameter Generation Device 300 Simulator 310 Parameter input section 320 Storage section 330 Control Unit 331 First Simulation Execution Unit 332 Second Simulation Execution Unit 400 Shooting plan generation device 410 Parameter input section 420 Storage section 430 Shooting plan generation unit 500 Evaluation Device 510 Simulation result input section 520 Storage section 521 Evaluation Model 530 Simulation Results Evaluation Section 600 Scanning Device

Claims

1. a simulator that performs a real environment simulation for simulating a state of a real environment in which a user shoots a moving image to be presented to viewers and for simulating the shooting of the moving image in the real environment; an evaluation device that evaluates a result of the real environment simulation from a first evaluation perspective related to a purpose of presenting the moving image to the viewer; Equipped with The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the evaluation device outputs an evaluation result of the moving image acquired by the real environment simulation from the first evaluation viewpoint based on the parameters of the real environment simulation. Video image evaluation system.

2. a simulator that performs a real environment simulation for simulating a state of a real environment in which a user shoots a moving image to be presented to viewers and for simulating the shooting of the moving image in the real environment; an evaluation device that evaluates a result of the real environment simulation from a first evaluation perspective related to a purpose of presenting the moving image to the viewer; a shooting plan generation device that generates a shooting plan in which information for shooting moving images acquired as a result of the real environment simulation in the real environment is described in a human-understandable manner based on parameters of the real environment simulation; Equipped with The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the evaluation device evaluates a result of the real environment simulation based on the moving image as a result of the simulation or parameters of the real environment simulation, the evaluation device inputs the shooting plan to be evaluated into a trained model that has been trained to output a result of evaluating a moving image acquired by a real environment simulation using the parameters related to the shooting plan from the first evaluation perspective, and outputs an evaluation result of the moving image with respect to the purpose. Video image evaluation system.

3. a simulator that performs a real environment simulation for simulating a state of a real environment in which a user shoots a moving image to be presented to viewers and for simulating the shooting of the moving image in the real environment; an evaluation device that evaluates a result of the real environment simulation from a first evaluation perspective related to a purpose of presenting the moving image to the viewer; a parameter generating device that generates parameters used by the simulator to execute the real environment simulation; Equipped with The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the evaluation device evaluates a result of the real environment simulation based on the moving image as a result of the simulation or parameters of the real environment simulation, A moving image evaluation system that repeatedly changes a parameter set by the parameter generation device and executes the real environment simulation with the changed parameter set by the simulator, The parameter generating device a first parameter set for the real environment simulation; an evaluation result of a real environment simulation using a second parameter set, which is a parameter set having some parameter values ​​different from those of the first parameter set and which has obtained a higher evaluation result than the evaluation result of the first parameter set; and By inputting the third parameter set to be estimated into a trained model that has learned the relationship between the above, a fourth parameter set that can obtain a higher evaluation result than the third parameter set is estimated. Video image evaluation system.

4. a simulator that performs a real environment simulation for simulating a state of a real environment in which a user shoots a moving image to be presented to viewers and for simulating the shooting of the moving image in the real environment; a parameter generating device that generates parameters used by the simulator to execute the real environment simulation; an evaluation device that evaluates a result of the real environment simulation from a first evaluation perspective related to a purpose of presenting the moving image to the viewer; Equipped with The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the evaluation device evaluates a result of the real environment simulation based on the moving image as a result of the simulation or parameters of the real environment simulation, the parameter generation device has a function of changing a part or all of a parameter set to generate a new parameter set, A moving image evaluation system that repeatedly changes a parameter set by the parameter generation device and executes the real environment simulation with the changed parameter set by the simulator, the parameter generation device inputs a moving image to be reproduced into a trained model that has been trained to receive a moving image as an input and output parameters for acquiring the moving image as a result of the real environment simulation, thereby estimating parameters for reproducing the moving image of the object to be reproduced in the real environment simulation; Video image evaluation system.

5. a simulator that performs a real environment simulation for simulating a state of a real environment in which a user shoots a moving image to be presented to viewers and for simulating the shooting of the moving image in the real environment; an evaluation device that evaluates a result of the real environment simulation based on a first evaluation viewpoint related to a purpose of presenting the moving image to the viewer; Equipped with The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the evaluation device is configured using a multimodal large-scale language model, and evaluates a result of the real environment simulation based on the video as the simulation result or parameters of the real environment simulation, the evaluation device inputs, with respect to the evaluation of the real environment simulation, a moving image to be evaluated from the simulation device, and inputs, in text format, a second evaluation perspective to be added to the first evaluation perspective via the user's terminal device; the evaluation device evaluates a result of the real environment simulation based on the first evaluation perspective and the second evaluation perspective. Video image evaluation system.

6. The evaluation device inputs the parameters to be evaluated into a trained model that has been trained to input the parameters and output an evaluation result from the first evaluation perspective of a moving image acquired by a real-environment simulation using the parameters to be evaluated, thereby outputting an evaluation result for the purpose of the moving image acquired by a real-environment simulation using the parameters of the moving image to be evaluated. The moving image evaluation system according to any one of claims 1 to 5.

7. The evaluation device inputs a moving image captured in the real environment simulation into a trained model that has been trained to input a moving image captured in the virtual space and output an evaluation result of the moving image from the first evaluation perspective, thereby outputting an evaluation result of the moving image with respect to the purpose. The moving image evaluation system according to any one of claims 2 to 5.

8. further comprising a scanning device that reads information about the real environment; the simulation device reproduces the real environment in the virtual space using the scan results obtained by the scanning device reading information about the real environment; The moving image evaluation system according to any one of claims 1 to 5.

9. The simulator reproduces sound, light, or weather in the real environment in the virtual space in the real environment simulation. The moving image evaluation system according to any one of claims 1 to 5.

10. a first step of performing a real environment simulation by a simulator, in which a real environment is an actual environment in which a user shoots a moving image to be presented to a viewer, and the simulator simulates a state of the real environment and the shooting of the moving image in the real environment; a second step in which an evaluation device evaluates a result of the real environment simulation from a first evaluation viewpoint related to a purpose of presenting the moving image to the viewer; A moving image evaluation method comprising: The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; In the second step, an evaluation result of the moving image acquired by the real environment simulation from the first evaluation viewpoint is output based on the parameters of the real environment simulation. Video evaluation methods.

11. a first step of performing a real environment simulation by a simulator, in which a real environment is an actual environment in which a user shoots a moving image to be presented to a viewer, and the simulator simulates a state of the real environment and the shooting of the moving image in the real environment; a second step in which an evaluation device evaluates a result of the real environment simulation from a first evaluation viewpoint related to a purpose of presenting the moving image to the viewer; a third step in which the shooting plan generation device generates a shooting plan, based on parameters of the real environment simulation, the shooting plan describing information for shooting the moving images acquired as a result of the real environment simulation in the real environment in a human-understandable manner; A moving image evaluation method comprising: The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the second step is to evaluate a result of the real environment simulation based on the moving image as the simulation result or parameters of the real environment simulation, the evaluation device inputs the shooting plan to be evaluated into a trained model that has been trained to output a result of evaluating a moving image acquired by a real environment simulation using the parameters related to the shooting plan from the first evaluation perspective, and outputs an evaluation result of the moving image with respect to the purpose. Video evaluation methods.

12. a first step of performing a real environment simulation by a simulator, in which a real environment is an actual environment in which a user shoots a moving image to be presented to a viewer, and the simulator simulates a state of the real environment and the shooting of the moving image in the real environment; a second step in which an evaluation device evaluates a result of the real environment simulation from a first evaluation viewpoint related to a purpose of presenting the moving image to the viewer; a third step in which a parameter generation device generates parameters to be used by the simulator device to execute the real environment simulation; and The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the second step is to evaluate a result of the real environment simulation based on the moving image as the simulation result or parameters of the real environment simulation, A moving image evaluation method that repeatedly changes a parameter set by the parameter generation device and executes the real environment simulation with the changed parameter set by the simulator, In the third step, the parameter generating device a first parameter set for the real environment simulation; an evaluation result of a real environment simulation using a second parameter set, which is a parameter set having some parameter values ​​different from those of the first parameter set and which has obtained a higher evaluation result than the evaluation result of the first parameter set; and By inputting the third parameter set to be estimated into a trained model that has learned the relationship between the above, a fourth parameter set that can obtain a higher evaluation result than the third parameter set is estimated. Video evaluation methods.

13. a first step of performing a real environment simulation by a simulator, in which a real environment is an actual environment in which a user shoots a moving image to be presented to a viewer, and the simulator simulates a state of the real environment and the shooting of the moving image in the real environment; a second step in which an evaluation device evaluates a result of the real environment simulation from a first evaluation viewpoint related to a purpose of presenting the moving image to the viewer; a third step in which a parameter generation device generates parameters to be used by the simulator device to execute the real environment simulation; and The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the second step is to evaluate a result of the real environment simulation based on the moving image as the simulation result or parameters of the real environment simulation, A moving image evaluation method that repeatedly changes a parameter set by the parameter generation device and executes the real environment simulation with the changed parameter set by the simulator, In the third step, the parameter generation device inputs the moving image of the object to be reproduced into a trained model that has been trained to receive a moving image as an input and output parameters for acquiring the moving image as a result of the real environment simulation, thereby estimating parameters for reproducing the moving image of the object to be reproduced in the real environment simulation. Video evaluation methods.

14. a first step of performing a real environment simulation by a simulator, in which a real environment is an actual environment in which a user shoots a moving image to be presented to a viewer, and the simulator simulates a state of the real environment and the shooting of the moving image in the real environment; a second step in which an evaluation device evaluates a result of the real environment simulation based on a first evaluation viewpoint related to a purpose of presenting the moving image to the viewer; A moving image evaluation method comprising: The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the evaluation device is configured using a multimodal large-scale language model, and evaluates a result of the real environment simulation based on the video as the simulation result or parameters of the real environment simulation, the evaluation device inputs, with respect to the evaluation of the real environment simulation, a moving image to be evaluated from the simulation device, and inputs, in text format, a second evaluation perspective to be added to the first evaluation perspective via the user's terminal device; the evaluation device evaluates a result of the real environment simulation based on the first evaluation perspective and the second evaluation perspective. Video evaluation methods.

15. One or more processors, a first step of performing a real environment simulation, which simulates a state of a real environment in which a user shoots a moving image to be presented to a viewer, and the shooting of the moving image in the real environment; a second step of evaluating a result of the real environment simulation from a first evaluation perspective related to a purpose of presenting the moving image to the viewer; A program for executing The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the second step outputs an evaluation result from the first evaluation viewpoint of the moving image acquired by the real environment simulation based on parameters of the real environment simulation. program.

16. One or more processors, a first step of performing a real environment simulation, which simulates a state of a real environment in which a user shoots a moving image to be presented to a viewer, and the shooting of the moving image in the real environment; a second step of evaluating a result of the real environment simulation from a first evaluation perspective related to a purpose of presenting the moving image to the viewer; a third step of generating a photography plan based on parameters of the real environment simulation, the photography plan describing information for photographing the moving images acquired as a result of the real environment simulation in the real environment in a human-understandable manner; A program for executing The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the second step is to evaluate a result of the real environment simulation based on the moving image as the simulation result or parameters of the real environment simulation, a trained model that has been trained to input the shooting plan and output a result of evaluating a moving image acquired by a real environment simulation using the parameters related to the shooting plan from the first evaluation perspective, and outputs an evaluation result of the moving image with respect to the purpose by inputting the shooting plan to the trained model; program.

17. One or more processors, a first step of performing a real environment simulation, which simulates a state of a real environment in which a user shoots a moving image to be presented to a viewer, and the shooting of the moving image in the real environment; a second step of evaluating a result of the real environment simulation from a first evaluation perspective related to a purpose of presenting the moving image to the viewer; a third step of generating parameters to be used to perform the real-world simulation; Execute The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the second step is to evaluate a result of the real environment simulation based on the moving image as the simulation result or parameters of the real environment simulation, a program for repeatedly executing the change of the parameter set in the third step and the execution of the real environment simulation with the parameter set after the change in the first step, In the third step, a first parameter set for the real environment simulation; an evaluation result of a real environment simulation using a second parameter set, which is a parameter set having some parameter values ​​different from those of the first parameter set and which has obtained a higher evaluation result than the evaluation result of the first parameter set; and By inputting the third parameter set to be estimated into a trained model that has learned the relationship between the above, a fourth parameter set that can obtain a higher evaluation result than the third parameter set is estimated. program.

18. One or more processors, a first step of performing a real environment simulation, which simulates a state of a real environment in which a user shoots a moving image to be presented to a viewer, and the shooting of the moving image in the real environment; a second step of evaluating a result of the real environment simulation from a first evaluation perspective related to a purpose of presenting the moving image to the viewer; a third step of generating parameters to be used to perform the real-world simulation; Execute The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the second step is to evaluate a result of the real environment simulation based on the moving image as the simulation result or parameters of the real environment simulation, A program for repeatedly changing a parameter set and executing the real environment simulation with the changed parameter set, In the third step, a moving image of an object to be reproduced is input to a trained model that has been trained to receive a moving image as an input and output parameters for acquiring the moving image as a result of the real environment simulation, thereby estimating parameters for reproducing the moving image of the object to be reproduced in the real environment simulation. program.

19. One or more processors, a first step of performing a real environment simulation, which simulates a state of a real environment in which a user shoots a moving image to be presented to a viewer, and the shooting of the moving image in the real environment; a second step of evaluating a result of the real environment simulation based on a first evaluation viewpoint related to a purpose of presenting the moving image to the viewer; A program for executing The real environment simulation reproduces the real environment in a virtual space, and outputs a moving image of the virtual space captured by a virtual camera as a simulation result; the second step is realized by using a multimodal large-scale language model, and evaluates a result of the real environment simulation based on the video image as the simulation result or parameters of the real environment simulation; Regarding the evaluation of the real environment simulation, a moving image to be evaluated is input, and a second evaluation viewpoint to be added to the first evaluation viewpoint is input in text format via the terminal device of the user; evaluating a result of the real environment simulation based on the first evaluation perspective and the second evaluation perspective; program.

Images