Evaluation system

Abstract

Provided is an evaluation system that quickly and appropriately evaluates video content and outputs an evaluation result. 【Solution means】The evaluation system includes at least one or more control units 210 and a storage unit 220. The control unit acquires video content, stores it in the storage unit, generates a script of the video content based on the video content stored in the storage unit, performs an evaluation on the video content based on the video content stored in the storage unit and the script of the video content, generates output data including the result of the evaluation on the video content, and outputs the output data.

Description

Technical Field

[0001] The present invention relates to an evaluation system.

Background Art

[0002] There are people called social media creators and digital creators who post videos on social media platforms and earn income. Also, companies post videos on social media platforms for purposes such as improving brand awareness, direct engagement with customers, low-cost marketing, and differentiation from competing companies. Whether a video becomes popular or not is a problem directly related to the income of social media creators and digital creators. It is also a problem for companies in terms of the instability of the brand image and the efficiency of the marketing budget.

[0003] Patent Document 1 discloses a technique for reducing the burden of modifying materials to fit the content.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] There is room for improvement in evaluating video content and outputting the evaluation results.

Means for Solving the Problems

[0006] (1) An evaluation system for video content posted on a social media platform, having at least one or more control units and a storage unit, The control unit acquires video content, stores it in the storage unit, generates a script for the video content based on the video content stored in the storage unit, evaluates the video content based on the video content stored in the storage unit and the script of the video content, generates output data including the result of the evaluation of the video content, and outputs the output data, an evaluation system. (2) The evaluation system according to (1), wherein the output data includes, as the result of the evaluation of the video content, the score of the evaluation result of the script related to the video content, the score of the evaluation result of the story structure related to the video content, the score of the evaluation result of the video production related to the video content, and the score of the evaluation result of the entire short video related to the video content. an evaluation system. (3) The evaluation system according to (2), wherein the output data further includes the overall score of the video content obtained based on the score of the evaluation result of the script related to the video content, the score of the evaluation result of the story structure related to the video content, the score of the evaluation result of the video production related to the video content, and the score of the evaluation result of the entire short video related to the video content. an evaluation system. (4) The evaluation system according to any one of (1) to (3), wherein the output data includes, as the result of the evaluation of the video content, the scene-by-scene evaluation related to the video content. an evaluation system. (5) The evaluation system according to (4), wherein the scene-by-scene evaluation includes the score of the evaluation result of the script related to the video content for each scene, the score of the evaluation result of the video production related to the video content, and the score of the evaluation result of the entire short video related to the video content. Evaluation system. (6) The evaluation system according to any one of (1) to (5), The evaluation of video content includes qualitative evaluation and quantitative evaluation. Evaluation system. (7) The evaluation system according to any one of (1) to (6), The output data includes information on the next action related to the video content generated based on the evaluation result of the video content. Evaluation system. (8) The evaluation system according to (1), The video content is short video content. Evaluation system. (9) An evaluation system for video content posted on a social media platform, including a server device and a client device, The server device has at least one or more control units and a storage unit, The control unit acquires video content from the client device and stores it in the storage unit, generates a script for the video content based on the video content stored in the storage unit, evaluates the video content based on the video content stored in the storage unit and the script of the video content, generates output data including the evaluation result of the video content, and transmits the output data to the client device. Evaluation system.

Advantages of the Invention

[0007] The video content can be evaluated quickly and appropriately, and the evaluation result can be output.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings. The various features shown in the embodiments below can be combined with each other.

[0010] <Embodiment 1> 1. System Configuration Diagram FIG. 1 is a diagram showing an example of the system configuration of the evaluation system 1000. As shown in FIG. 1, the evaluation system 1000 includes, as a system configuration, a server device 100, a client device 110, and an AI server device 120. The server device 100, the client device 110, and the AI server device 120 are communicably connected via a network 150. The network 150 is any one of a WAN (Wide Area Network), a LAN (Local Area Network), and the Internet, or any combination thereof. The network 150 is configured to enable communication between devices connected to the network 150 via wired and / or wireless means. The evaluation system 1000 is a system that provides a so-called SaaS (Software as a Service) function.

[0011] The server device 100 is a device that executes the main processing of Embodiment 1. More specifically, the server device 100 causes various AIs (artificial intelligence) etc. to evaluate a script generated based on a video file and / or a story composition of a video, video production, short video, script, etc. based on a video file etc., generates a comprehensive analysis report based on the evaluation results, and outputs the generated comprehensive analysis report. The video file is a file of video content posted on a social media platform. In the specification, for the sake of simplicity of explanation, short video content will be taken as an example of video content for explanation. A social media platform is a general term for services that enable users to create, share content (text, images, videos, etc.) on the Internet and communicate with other users to form and maintain communities and / or networks. Short video content generally refers to video content that is produced and viewed in a short length of several tens of seconds to several minutes. Short video content can also be called short-length video.

[0012] The client device 110 is a device operated by a content creator who creates short video content and posts it on a social media platform. The content creator operates the client device 110, accesses the server device 100, checks the comprehensive analysis report output from the server device 100, and creates new short video content or modifies or edits the created short video content based on the content of the comprehensive analysis report.

[0013] The AI server device 120 is a server device that efficiently and on a large scale performs processing (learning and inference of machine learning) related to various AIs (artificial intelligence) described later. Although the various AIs described later may be implemented in different AI server devices, the description will be given assuming that they are implemented in one AI server. The various AIs include a voice analysis AI 120, a video analysis AI 121, a script generation AI 122, a story structure evaluation AI 123, a video production evaluation AI 124, a short video evaluation AI 125, a script evaluation AI 126, and a comprehensive analysis AI 127, as shown in Figs. 5 and 6 described later. Note that AI can also be called a trained model. A trained model is a model that is optimized so that the internal parameters (weights, biases, etc.) of the model are adjusted using a specific data set (training data) and can perform a given task (classification, regression, generation, etc.). A trained model can also be called a model that has been trained to output output data for given input data, as described later. In addition, when various AIs are collectively referred to, they are simply called AI.

[0014] 2. Hardware Configuration (1) Hardware Configuration of Server Device 100 FIG. 2 is a diagram illustrating an example of a hardware configuration of the server device 100. As shown in FIG. As shown in FIG. 2, the server device 100 includes, as its hardware configuration, a control unit 210, a storage unit 220, and a communication unit 230.

[0015] The control unit 210 is a CPU (Central Processing Unit) or the like, and controls the entire server device 100 and executes processes based on input information and the like.

[0016] The storage unit 220 is any one of an HDD (Hard Disk Drive), a ROM (Read Only Memory), a RAM (Random Access Memory), an SSD (Solid State Drive), or any combination thereof, and stores programs, data, etc. that the control unit 210 uses when executing processes based on the programs. The storage unit 220 is an example of a storage medium. In the specification, although it is described that the data used when the control unit 210 executes processes based on programs is stored in the storage unit 220, it may be stored in the storage unit of another device communicable with the server device 100. That is, the data may be stored in the storage unit of any device as long as the control unit 210 can refer to it. By the control unit 210 executing processes based on the programs stored in the storage unit 220, the functions of the server device 100, the processes of the flowchart shown in FIG. 4 described later, the control processes related to the screen transitions shown in FIGS. 12 to 14 described later, etc. are realized.

[0017] The communication unit 230 connects the server device 100 to the network 150 and controls communication with other devices.

[0018] Note that the number of control units included in the server device 100 is not limited to one and may be plural. The same applies to other components.

[0019] (2) Hardware Configuration of the Client Device 110 FIG. 3 is a diagram showing an example of the hardware configuration of the client device 110. The client device 110 includes, as a hardware configuration, a control unit 310, a storage unit 320, an input unit 330, an output unit 340, and a communication unit 350.

[0020] The control unit 310 is a CPU or the like, and controls the entire client device 110 or executes processes based on the input information or the like.

[0021] The storage unit 320 is any one of a ROM, a RAM, an SSD, or any combination thereof, and stores a program, data, etc. that the control unit 310 uses when executing processing based on the program. The functions of the client device 110 are realized by the control unit 310 executing processing based on the program stored in the storage unit 320. The storage unit 320 is an example of a storage medium.

[0022] The input unit 330 is a keyboard and / or a mouse, etc., and inputs operation information, input information, etc. of an operator. The output unit 340 is a display, etc., and displays the result of processing by the control unit 310. The communication unit 350 connects the client device 110 to the network 150 and controls communication with other devices.

[0023] 3. Information Processing (1) Outline of Processing The control unit 210 acquires short video content and stores it in the storage unit 220. The control unit 210 generates a script for the short video content based on the short video content stored in the storage unit 220. The control unit 210 generates a script for the short video content using a predetermined AI as described later. The control unit 210 performs an evaluation of the short video content based on the short video content stored in the storage unit 220 and the script of the short video content. The control unit 210 performs an evaluation of the short video content using a predetermined AI as described later. The control unit 210 generates output data including the result of the evaluation of the short video content. An example of the output data is a comprehensive analysis report. The control unit 210 generates a comprehensive analysis report using a predetermined AI as described later. The control unit 210 outputs the comprehensive analysis report. The control unit 210 outputs the comprehensive analysis report by transmitting the comprehensive analysis report to the client device 110 or storing it in a predetermined storage area of the storage unit 220.

[0024] By executing such processing, video content can be quickly and appropriately evaluated, and the evaluation result can be output.

[0025] (2) Details of the processing FIG. 4 is a flowchart showing an example of information processing in the evaluation system 1000. FIGS. 5 and 6 are diagrams for explaining each process of the flowchart in more detail.

[0026] (Step S410) In step S410, the control unit 210 receives input data and the like via a predetermined screen displayed on a Web browser or the like of the client device 110. As the input data, as shown in FIG. 5, a video file 510 of short video content (also simply referred to as a short video), category information 520 of the short video selected via the screen, and the purpose 530 of the short video are included.

[0027] (Step S420) In step S420, the control unit 210 analyzes the video content based on the video file. More specifically, the control unit 210 passes the video file to the speech analysis AI 120 and requests analysis of the speech included in the video file. The speech analysis AI 120 is an AI learned with the video file as input data and the speech included in the video file as output data. Also, the control unit 210 passes the video file to the video analysis AI 121 and requests analysis of the video included in the video file. The video analysis AI 121 is an AI learned with the video file as input data and the telop (telop information), visual information, and camera work (camera work information) included in the video file as output data.

[0028] When the control unit 210 passes data to the AI or receives data from the AI, it passes data to the AI or receives data from the AI via an API (Application Programming Interface).

[0029] The control unit 210 receives the voice 540 from the voice analysis AI 120. The voice 540 includes a text file and an audio file. The text file contains the results of speech recognition. The text file is output as structured data. The results of speech recognition include the speech content, time stamps, speaker identification, confidence scores, etc. The speech content is text data obtained by transcribing the words spoken in the video into characters. The time stamp is time information indicating at what timing each word or sentence was spoken in the video. The speaker identification is information identifying who spoke which part when multiple people are speaking. The confidence score is a numerical value indicating how confident the voice analysis AI 120 is in the results of speech recognition. The audio file contains audio waveform data such as noise-removed audio and speaker-separated audio.

[0030] The control unit 210 receives the caption, visual information, and camera work 550 from the video analysis AI 121. The caption, visual information, and camera work 550 include caption information, visual information, and camera work information.

[0031] The caption information is information about all the character information displayed in the video. The caption information is all the character information displayed in the video. The caption information includes, for example, text content, display interval (time stamp), display position, font information, etc.

[0032] The visual information is information about visible elements such as specific objects, people, backgrounds, scenes, and their states and movements reflected in the video. The visual information includes, for example, object recognition information (labels, positions / ranges, confidence levels), scene recognition information (information about what kind of place and situation each scene of the video is, time of day, weather, etc.), face recognition and person attribute information (faces of people in the screen, positions, who they are, attribute information such as age, gender, expression, etc.), and action recognition information (information about the actions and movements of people).

[0033] Camera work information is information regarding how a video was shot, such as the movement and angle of the camera, the type of shot, etc. Camera work information includes, for example, camera movement information, shot type information, cut detection information, shooting angle information, and the like. Camera movement information includes, for example, information on pan, tilt, zoom, dolly, track, etc. Shot type information includes, for example, information regarding the size of the subject and framing, such as long shot, medium shot, close-up, etc. Cut detection information includes, for example, information on the timing (cut point) at which the scene of the video changes (start time and end time of each shot).

[0034] The control unit 210 passes the audio 540 and the telop / visual information / camera work 550 to the scenario generation AI 122 and requests the generation of a scenario. The scenario generation AI 122 is a learned model that has learned the audio and the telop / visual information / camera work as input data and an object array (scenes) as shown in FIG. 7 described later as output data. The object array is a list (array) in which a collection of multiple pieces of information (objects) are arranged in order.

[0035] FIG. 7 is a diagram showing an example of an array of objects output by the scenario generation AI 122. The array of objects includes, as fields, sceneId, sceneTitle, sceneDescription, start, end, audioTranscription, extractedTeletext, cameraWork, and otherVisualInfo. The sceneId stores the ID of the scene (in ascending order of 1, 2, 3,...). The sceneTitle stores the title of the scene. The sceneDescription stores the description of the scene. The start stores the start time (in seconds) of the scene. The end stores the end time (in seconds) of the scene. The audioTranscription stores the result of the speech recognition of the audio within the scene. The extractedTeletext stores the caption characters within the scene. The cameraWork stores the camera work information within the scene. The otherVisualInfo stores other visual information within the scene.

[0036] (Step S430) In step S430, the control unit 210 receives the output data output by the scenario generation AI 122 as the scenario 560 of the video.

[0037] (Step S440) In step S440, the control unit 210 analyzes and evaluates the video from various viewpoints based on the scenario and the like. More specifically, the control unit 210 passes the scenario 560 and the purpose 530 of the video to the story composition evaluation AI 123 and requests an evaluation of the story composition. The story composition evaluation AI 123 is a learned model that has been learned with the purpose of the video and the scenario (scene information) as input data, and the overall comment on the entire video, the composition score, and the object array (sceneEvaluations) as shown in FIG. 8 described later as output data.

[0038] FIG. 8 is a diagram showing an example of an object array output from the story composition evaluation AI 123. The object array shown in FIG. 8 includes a sceneId and an aibacElement as fields. The sceneId stores the ID of the scene (in ascending order of 1, 2, 3,...). The aibacElement stores Attention (attention / focus), or Interest (interest / concern), or Benefit (benefit / advantage), or Action (action).

[0039] The control unit 210 receives, as an evaluation of the story composition, a comment (overallComment) on the entire video, a composition score (score), and an object array (sceneEvaluations) as shown in FIG. 8 from the story composition evaluation AI 123. The composition score (score) shown in FIG. 8 is an example of a quantitative evaluation.

[0040] The control unit 210 passes the scenario 560, the category information 520, the output data of the story composition evaluation AI 123, and the scenario evaluation AI 126 to request an evaluation of the scenario. The scenario evaluation AI 126 is a learned model trained with the scenario, the category information, and the evaluation of the story composition as input data, and the comment (overallComment) on the entire video and the object array (sceneEvaluations) as shown in FIG. 9 described later as output data.

[0041] FIG. 9 is a diagram showing an example of an object array output from the scenario evaluation AI 126. The object array shown in FIG. 9 includes, as fields, sceneId, aibac, entertainmentFactor, scriputClarity, and comment. In sceneId, the ID of the scene (in ascending order of 1, 2, 3, ···) is stored. In aibac, the evaluation of the AIBAC element is stored. The A in AIBAC indicates Attention. The I in AIBAC indicates Interest. The B in AIBAC indicates Benefit. The AC in AIBAC indicates Action. In entertainmentFactor, the score of the entertainment element or the enjoyment from the user's perspective is stored. In scriptClarity, the score of the subtitle / dialogue is stored. In comment, the comment on the scenario of the entire scene is stored. The score of the entertainment element or the enjoyment from the user's perspective and the score of the subtitle / dialogue shown in FIG. 9 are examples of quantitative evaluations. The comment on the scenario of the entire scene is an example of a qualitative evaluation.

[0042] The control unit 210 passes the scenario 560, the video file 510, and the subtitle / visual information / camera work 550 to the video production evaluation AI 124 and requests an evaluation of the video production. The video production evaluation AI 124 is a learned model that has been trained with the scenario, the video file, and the subtitle / visual information / camera work as input data, and the comment on the entire video (overallComment) and the (sceneEvaluations) as shown in FIG. 10 described later as output data.

[0043] FIG. 10 is a diagram showing an example of an object array output from the video production evaluation AI 124. The object array shown in FIG. 10 includes, as fields, sceneId, cameraWorkComment, lightingComment, edittingComment, and overallScore. The sceneId stores the ID of the scene (in ascending order of 1, 2, 3,...). The cameraWorkComment stores comments on camera work. The lightingComment stores comments on lighting. The edittingComment stores comments on editing. The overallScore stores an evaluation (0 to 5 points, with 5 points being the highest) of the video of the entire scene. Comments on camera work, comments on lighting, comments on editing, etc. are examples of qualitative evaluations. The evaluation of the video of the entire scene is an example of a quantitative evaluation.

[0044] The control unit 210 passes the scenario 560 and the video file 510 to the short video evaluation AI 125 and requests an evaluation of the short video. The short video evaluation AI 125 is a learned model that is learned with the scenario and the video file as input data, and the overallComment on the entire video and the sceneEvaluations as shown in FIG. 11 described later as output data.

[0045] FIG. 11 is a diagram showing an example of an object array output from the short video evaluation AI 125. The object array shown in FIG. 11 includes, as fields, sceneId, tempo, textVisibility, engagementInduction, trendUse, and comment. In sceneId, the ID of the scene (in ascending order of 1, 2, 3, ···) is stored. In tempo, the tempo score is stored. The tempo score can be said to be an index that comprehensively quantifies the speed of the visual development of the video, the sense of rhythm of the editing, and the accompanying physical sense of speed of the viewer. In textVisibility, the text visibility score is stored. The text visibility score can be said to be an index that quantifies the degree to which the text displayed in the video can be clearly and easily recognized and read by the viewer. In engagementInduction, the engagement induction score is stored. The engagement induction score can be said to be an index that comprehensively evaluates and quantifies the potential power of the video to attract the viewer's interest, continue viewing, or elicit some active reaction (such as like, comment, share, channel registration, click on a link, etc.). In trendUse, the score of the trend element is stored. The score of the trend element can be said to be an index that quantifies the degree to which the video effectively incorporates the topics, expressions, styles, or topics that are attracting attention in the world or on a specific social media platform at the time of production and publication. In comment, the comment on the entire scene is stored. The tempo score, the text visibility score, the engagement induction score, and the score of the trend element are examples of quantitative evaluations. The comment on the entire scene is an example of a qualitative evaluation.

[0046] (Step S450) In step S450, the control unit 210 acquires overallComment as the evaluation 580 for the entire video from the output data by various AIs, and acquires the rest of the output data by various AIs as the extended script 570 that integrates the evaluations of various experts.

[0047] (Step S460) In step S460, the control unit 210 analyzes and evaluates the entire video based on the extended script 570 and the evaluation 580 of the entire video. More specifically, the control unit 210 passes the extended script 570 and the evaluation 580 of the entire video to the comprehensive analysis AI 127 and requests an overview and a next action for the entire video. The comprehensive analysis AI 127 is a learned model that has learned the extended script and the evaluation of the entire video as input data, and the overview and the next action for the entire video as output data.

[0048] The overview includes considerations, advantages, and improvement points. The considerations describe the overall considerations of the video. The advantages describe the excellent points of the video. The improvement points describe the points that need to be improved in the video. The next action includes the following content. · Text or subtitle content of the scene · Specific improvement content · Why such improvement is highly prioritized and necessary, its purpose and background · KPIs (Key Performance Indicators) expected from the improvement

[0049] (Step S470) In step S470, the control unit 210 generates and outputs a comprehensive analysis report 590 based on the output data of the comprehensive analysis AI 127 and the like. The comprehensive analysis report 590 includes the overview and the next action output by the comprehensive analysis AI 127. In addition, the control unit 210 calculates a comprehensive score based on the video production score, the script score, the story structure score, and the short video score. The comprehensive analysis report 590 also includes the comprehensive score.

[0050] For example, the control unit 210 calculates a weighted average based on the following weighting. Note that the weighting values may be set in a predetermined storage area such as the storage unit 220. · Video production score: 20% · Script score: 40% · Story composition score: 20% · Short video score: 20%

[0051] Based on the scores for each scene given by the video production evaluation AI 124, the control unit 210 averages the scores for each scene to obtain a video production score. The video production score is an example of the score of the evaluation result of the video production related to the video content.

[0052] The control unit 210 obtains the following three pieces of information output by the scenario evaluation AI 126. · Evaluation of AIBAC elements · Score of entertainment elements or enjoyment from the user's perspective · Score of subtitles and dialogues Based on the above three pieces of information, the control unit 210 calculates the score for each scene. Here, when the scene is an "Attention" scene, the control unit 210 calculates the score of the scene by weighted average, which weights the evaluation of the AIBAC elements more heavily than the other two pieces of information. On the other hand, when the scene is not an "Attention" scene, the control unit 210 calculates the score of the scene by the average score of the above three pieces of information. The control unit 210 takes the average of the scores of each scene calculated according to such rules as the scenario score. The scenario score is an example of the score of the evaluation result of the scenario related to the video content.

[0053] The control unit 210 takes the score output by the story composition evaluation AI 123 as the story composition score. The story composition score is an example of the score of the evaluation result of the story composition related to the video content.

[0054] The control unit 210 obtains the following three scores output by the short video evaluation AI 125. · Tempo score · Text visibility score · Engagement induction score The control unit 210 uses, for example, the average value of the above three scores as the score for each scene. Then, the control unit 210 uses the average of the scores for each scene as the short video score. The short video score is an example of the score of the evaluation result of the entire short video regarding the video content.

[0055] The control unit 210 generates an analysis result screen of the video including the comprehensive analysis report 590 and transmits it to the client device 110. When the control unit 310 of the client device 110 receives the analysis result screen of the video (hereinafter simply referred to as the analysis result screen), it displays it on the output unit 340 and the like.

[0056] FIG. 12 is a diagram (part 1) showing an example of the analysis result screen 1200. The analysis result screen 1200 includes a comprehensive report tab 1210 and a scene-by-scene analysis tab 1220. When the comprehensive report tab 1210 is selected, the control unit 210 displays the comprehensive analysis report 590 on the analysis result screen. The comprehensive analysis report 590 includes an overview 1230 and a next action 1240. In addition, the comprehensive analysis report 590 includes a performance score 1250, which includes a video production score, a script score, a story structure score, and a short video score. By default, the analysis result screen 1200 with the comprehensive report tab 1210 selected is displayed.

[0057] FIG. 13 is a diagram (part 2) showing an example of the analysis result screen 1200. FIG. 13 shows an example of the analysis result screen 1200 when the scene-by-scene analysis tab 1220 is selected. In the analysis result screen 1200 of FIG. 13, the improvement points for each scene are listed. When one scene (scene 1310 in the example of FIG. 13) is selected in the analysis result screen 1200 of FIG. 13, the control unit 210 controls to display the details of the selected scene on the screen.

[0058] FIG. 14 is a diagram (part 3) showing an example of the analysis result screen 1200. FIG. 14 shows an example in which scene 1 is selected on the analysis result screen 1200 of FIG. 13. Details of scene 1 show the scenario score 1410, video production score 1420, and short video score 1430 of scene 1.

[0059] As described above, according to Embodiment 1, video content can be quickly and appropriately evaluated, and the evaluation result can be output.

[0060] (Modification example) Some of the various learned models described above may be replaced with a large language model or a multimodal model. A large language model is a model that mainly learns a huge amount of text data (such as websites, books, articles, conversation data, etc.). As the name implies, a large language model is "large-scale" and has a very large number of parameters. A multimodal model is a model that is trained by combining multiple different types of data (modalities) such as not only text but also images, audio, video, and sensor data. Note that large language models and multimodal models can also be regarded as learned models that have learned various data.

[0061] Finally, although various embodiments according to the present disclosure have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. Embodiments and their modifications are included in the scope and gist of the invention, and are also included in the invention described in the claims and the equivalent scope thereof. Embodiment 1 and each of the above-described modification examples can be arbitrarily combined.

Explanation of reference numerals

[0062] 100 Server device 110 Client device 210 Control unit 220 Storage unit 230 Communication Department

Claims

1. An evaluation system for video content posted on a social media platform, having at least one or more control units and a storage unit, wherein the control unit acquires the video content, stores it in the storage unit, generates a script of the video content based on the video content stored in the storage unit, evaluates the video content based on the video content stored in the storage unit and the script of the video content, generates output data including the result of the evaluation regarding the video content, and outputs the output data. Evaluation system.

2. The evaluation system according to Claim 1, wherein the output data includes, as the result of the evaluation regarding the video content, a score of the evaluation result of the script regarding the video content, a score of the evaluation result of the story structure regarding the video content, a score of the evaluation result of the video production regarding the video content, and a score of the evaluation result of the entire short video regarding the video content. Evaluation system.

3. The evaluation system according to Claim 2, wherein the output data further includes an overall score of the video content obtained based on the score of the evaluation result of the script regarding the video content, the score of the evaluation result of the story structure regarding the video content, the score of the evaluation result of the video production regarding the video content, and the score of the evaluation result of the entire short video regarding the video content. Evaluation system.

4. The evaluation system according to Claim 1, wherein the output data includes, as the result of the evaluation regarding the video content, an evaluation by scene regarding the video content. Evaluation system.

5. The evaluation system according to Claim 4, wherein the evaluation by scene includes, for each scene, a score of the evaluation result of the script regarding the video content, a score of the evaluation result of the video production regarding the video content, and a score of the evaluation result of the entire short video regarding the video content. Evaluation system.

6. The evaluation system according to Claim 1, wherein the evaluation regarding the video content includes a qualitative evaluation and a quantitative evaluation. Evaluation system.

7. The evaluation system according to Claim 1, The output data includes information on the next action regarding the video content generated based on the result of the evaluation of the video content. Evaluation system. **Claim 8** The evaluation system according to claim 1, wherein the video content is short video content. Evaluation system. **Claim 9** An evaluation system for video content posted on a social media platform, comprising a server device and a client device, wherein the server device has at least one or more control units and a storage unit, and the control unit acquires the video content from the client device and stores it in the storage unit, generates a script for the video content based on the video content stored in the storage unit, evaluates the video content based on the video content stored in the storage unit and the script for the video content, generates output data including the result of the evaluation of the video content, and transmits the output data to the client device. Evaluation system.

Images