Moving picture data creation system, and program for moving picture data creation system

Abstract

To provide a moving picture data creation system allowing a user to simply create page feeding moving picture data for file data having a plurality of pages of contents.SOLUTION: A moving picture data creation system 100 includes a user terminal 110 and a server 120. When file data FL having a plurality of pages of contents is designated and a predetermined operation is performed in a browser 111 of the user terminal, the user terminal 110 transmits the designated file data FL to the server 120, and the server 120 uses artificial intelligence moving picture creation means 131 to create moving picture data MV on the basis of the received content of the file data FL.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a moving image data creation system that includes a user terminal and a server and creates moving image data from file data having multiple pages of content, and a program therefor. [Background technology]

[0002] Conventionally, a presentation support device is known in which a presentation support server broadcasts a real-time video of a presentation taking place at a presentation venue, and when the presentation begins, receives information from the viewer's terminal indicating the viewer's reaction to the presentation, and appropriately controls the display of slide materials on the monitor in response to the reaction (as described below, the displayed slide material is either automatically switched to another slide material, or switched manually by the presenter) (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-36640 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional presentation support devices described above were configured to display slide materials on a monitor during the presentation and capture images of the presentation in real time using an imaging device. Therefore, in order for a user to obtain a video of the contents of the slide materials, the user had to actually present the contents of the slide materials, which made it difficult to obtain a video of the contents of the slide materials.

[0005] Therefore, the present invention is intended to solve the problems of the prior art as described above, that is, the object of the present invention is to provide a video data creation system and a program therefor that allow a user to easily create page-flip video data for file data containing multiple pages. [Means for solving the problem]

[0006] The invention of claim 1 is a video data creation system that comprises a user terminal and a server and creates video data from file data having content of multiple pages, and when file data having content of multiple pages is specified in a browser of the user terminal and a specified operation is performed, the user terminal transmits the specified file data to the server, and the server creates video data using an artificial intelligence video generation means based on the content of the received file data, thereby solving the above-mentioned problem.

[0007] The invention of claim 2 further solves the above-mentioned problem by, in addition to the configuration of the video data creation system described in claim 1, being configured such that when there is text-format explanatory information added to each page in the specified file data, the artificial intelligence video generation means adds audio data of the explanatory information in correspondence with the display of each page in the video data.

[0008] The invention of claim 3 further solves the above-mentioned problem by configuring the video data creation system as described in claim 1 or claim 2, in addition to the above-mentioned problem, in which an avatar having a human face can be freely selected in the browser of the user terminal, and when the avatar is selected, the avatar can be freely positioned in the editing layout display of the video data, and when the specified operation is performed, the server uses the artificial intelligence video generation means to add the action of the avatar speaking in response to the audio data to a position in the video data based on the positioning operation.

[0009] The invention of claim 4 further solves the above-mentioned problem by configuring the video data creation system as described in claim 3, in addition to the configuration, in which any facial photo data can be freely designated and selected as an avatar in the browser of the user terminal, and when any facial photo data is designated / selected as the avatar, the server uses the artificial intelligence video generation means to recognize the mouth of the face in the facial photo data, generate facial data showing the mouth moving, and add it to a position in the video data based on a placement operation.

[0010] The invention of claim 5 further solves the above-mentioned problem by configuring the video data creation system as described in claim 4, in which the voice of the audio data to be added to the video data in the browser of the user terminal can be freely selected from among a plurality of options, and when a voice is specified / selected from among the plurality of options, the server creates the audio data using an artificial intelligence video generation means based on information of the specified / selected voice.

[0011] The invention of claim 6 further solves the above-mentioned problem by, in addition to the configuration of the video data creation system described in claim 5, being configured such that when the user's own voice is selected from a plurality of options in the browser of the user terminal, the user's voice can be freely recorded using the microphone of the user terminal, and the server creates the audio data using an artificial intelligence video generation means based on the recorded user's voice data.

[0012] The invention of claim 7 is a program for a video data creation system that creates video data from file data having content of multiple pages, and solves the above-mentioned problem by having a file data designation determination step of determining whether file data having content of multiple pages has been designated in a browser of a user terminal and a specified operation has been performed, a file data transmission step in which the user terminal transmits the designated file data to a server, and a video data creation step in which the server creates video data using an artificial intelligence video generation means based on the content of the received file data. Effect of the Invention

[0013] The video data creation system of the present invention, by comprising a user terminal and a server, not only enables communication between the user terminal and the server, but also provides the following unique effects.

[0014] According to the video data creation system of the invention of claim 1, the content of multiple pages is displayed in a page-flip manner in the video data, so that the user can easily create video data in which the content of multiple pages is page-flip.

[0015] According to the video data creation system of the invention of claim 2, in addition to the effects achieved by the invention of claim 1, the information in the so-called description column in file data having content on multiple pages is read as description information in text format by the artificial intelligence video generation means and added as audio data corresponding to the display of each page in the video data, so that the user can easily add the information in the so-called description column to the video data as audio data. In other words, by adding auditory sound in addition to visual moving images, moving image data that is highly satisfying to other users, i.e., viewers, can be provided.

[0016] According to the video data creation system of the invention of claim 3, in addition to the effects of the invention of claim 1 or claim 2, the selected avatar is placed at a desired position in the video data and displayed with its mouth moving in response to the audio data, allowing the user to easily display the avatar as a narrator. In other words, a narrator who moves his mouth in response to the audio data is displayed as if he is speaking to other viewers who are users, so that the other viewers feel as if he is speaking directly to them. This allows the user to convey the contents of file data having multiple pages of content to viewers in a manner that is more attention-grabbing than a simple slide display configuration.

[0017] According to the video data creation system of the invention of claim 4, in addition to the effects achieved by the invention of claim 3, by specifying any facial photo data, facial data of an original avatar moving its mouth is generated and added to the video data, so that the user can easily display an avatar with the desired facial photo as a narrator on the video data.

[0018] According to the video data creation system of the invention of claim 5, in addition to the effect achieved by the invention of claim 4, by specifying a desired voice, audio data of the specified voice is generated and added to the video data, so that the user can easily insert narration in the desired voice.

[0019] According to the video data creation system of the invention of claim 6, in addition to the effect achieved by the invention of claim 5, audio data is generated based on sampling data of the user's own voice recording data, so that narration in the user's own voice can be easily inserted.

[0020] According to the program of the video data creation system of the invention of claim 7, similar to the effect achieved by the invention of claim 1, the content of multiple pages is displayed in video data as if it were being paged forward, so that the user can easily create video data in which the content of multiple pages is paged forward. [Brief description of the drawings]

[0021] [Figure 1] 1 is a diagram showing the concept of a moving image data creation system according to an embodiment of the present invention; [Diagram 2] 1 is a flowchart showing an example of the operation of a video data creation system according to an embodiment of the present invention. [Diagram 3] 13 is a diagram showing a state in which file data is uploaded on a video create loading screen displayed by a browser of a user terminal of the video data creation system according to an embodiment of the present invention. FIG. [Figure 4] 13 is a diagram showing a state in which uncompleted video data is edited on a video create editing screen displayed by a browser on a user terminal of the video data creation system according to an embodiment of the present invention. FIG. [Diagram 5] 13 is a diagram showing how text data is input on a video creation editing screen displayed by a browser on a user terminal of the video data creation system according to an embodiment of the present invention. FIG. [Figure 6] 13 is a diagram showing the state when selecting an avatar on a video creation editing screen displayed by a browser on a user terminal of the video data creation system according to an embodiment of the present invention. FIG. [Figure 7] 13 is a diagram showing the state when a user creates an original avatar on a video creation editing screen displayed by a browser on a user terminal of the video data creation system according to an embodiment of the present invention. FIG. [Figure 8] 13 is a diagram showing the state when selecting a voice for audio data on a video creation editing screen displayed by a browser of a user terminal of the video data creation system according to an embodiment of the present invention. FIG. [Figure 9]13 is a diagram showing the state when a user inputs his or her own voice on a video creation and editing screen displayed by a browser on a user terminal of the video data creation system according to an embodiment of the present invention to generate audio of the user's voice. [Figure 10] 3A to 3C are diagrams showing examples of video data displayed by a browser on a user terminal of the video data creation system according to an embodiment of the present invention. [Figure 11] 13 is a diagram showing details of moving image data displayed on a moving image list screen displayed by a browser on a user terminal of the moving image data creation system according to an embodiment of the present invention. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0022] The video data creation system of the present invention comprises a user terminal and a server, and when file data having content of multiple pages is specified in the browser of the user terminal and a specified operation is performed, the user terminal transmits the specified file data to the server, and the server creates video data using an artificial intelligence video generation means based on the content of the received file data.As long as the user can easily create video data that is page-flip through content of multiple pages, the specific implementation of the system can be any one. In addition, the program of the video data creation system of the present invention has a file data designation determination step of determining whether file data having content of multiple pages has been designated in the browser of the user terminal and a specified operation has been performed, a file data transmission step in which the user terminal transmits the designated file data to a server, and a video data creation step in which the server creates video data using an artificial intelligence video generation means based on the content of the received file data, so that the specific implementation can be any as long as the user can easily create video data that is page-flip through content of multiple pages.

[0023] For example, the user terminal may be a desktop personal computer terminal, a notebook personal computer terminal, a smartphone terminal, a tablet terminal, or the like that sends and receives information, and may be any terminal that can be freely connected to a server via a communication network including a wide area network, such as the Internet, a local network, or a telephone line. Also, the servers may each be a single server or multiple servers on a cloud. The artificial intelligence moving image generating means creates moving image data based on still image data in accordance with a text script (prompt), which is instruction command information, and may be configured to be provided on one server or multiple servers on a cloud. File data having multiple pages of content may be in any format as long as it has multiple pages of content, such as slide format data having multiple pages of content, spreadsheet file data in cell display format spanning multiple pages, or document format file data spanning multiple pages. Furthermore, the artificial intelligence video generation means is capable of being plugged into an interactive pre-trained artificial intelligence means, also known as a large-scale language model, such as ChatGPT (Generative Pre-trained Transformer) (hereinafter referred to as ChatGPT). In addition, the pre-trained artificial intelligence means is configured to generate text data with a high probability of being the correct answer based on a text script (prompt), which is instruction and command information, and may be configured to be installed on one server or multiple servers on a cloud. EXAMPLES

[0024] A moving image data creation system 100 according to an embodiment of the present invention will be described below with reference to FIGS. 1 is a diagram showing the concept of moving image data creation system 100 according to an embodiment of the present invention, FIG. 2 is a chart showing an example of the operation of moving image data creation system 100 according to an embodiment of the present invention, FIG. 3 is a diagram showing a state when file data FL is uploaded on moving image create reading screen 112 displayed by browser 111 of user terminal 110 of moving image data creation system 100 according to an embodiment of the present invention, FIG. 4 is a diagram showing a state when pre-completed moving image data MV is edited on moving image create editing screen 114 displayed by browser 111 of user terminal 110 of moving image data creation system 100 according to an embodiment of the present invention, FIG. 5 is a diagram showing a state when text data is input on moving image create editing screen 114 displayed by browser 111 of user terminal 110 of moving image data creation system 100 according to an embodiment of the present invention, FIG. 6 is a diagram showing a state when an avatar AV is selected on moving image create editing screen 114 displayed by browser 111 of user terminal 110 of moving image data creation system 100 according to an embodiment of the present invention, and FIG. FIG. 8 is a diagram showing a state where a user creates an original avatar AV on a video create editing screen 114 displayed by a browser 111 of a user terminal 110 of a video data creation system 100, which is an embodiment of the present invention. FIG. 8 is a diagram showing a state where a voice for audio data MV1 is selected on a video create editing screen 114 displayed by a browser 111 of a user terminal 110 of a video data creation system 100, which is an embodiment of the present invention. FIG. 9 is a diagram showing a state where a user inputs his or her own voice to generate audio of the user's voice on a video create editing screen 114 displayed by a browser 111 of a user terminal 110 of a video data creation system 100, which is an embodiment of the present invention. FIGS. 10(A) to 10(C) are diagrams showing an example of video data MV displayed by a browser 111 of a user terminal 110 of a video data creation system 100, which is an embodiment of the present invention. FIG. 11 is a diagram showing a state where details of video data MV are displayed on a video list screen 118 displayed by a browser 111 of a user terminal 110 of a video data creation system 100, which is an embodiment of the present invention.

[0025] As shown in FIG. 1, a moving image data creation system 100 according to an embodiment of the present invention includes a user terminal 110, and a first server 120 and a second server 130, which are examples of servers. The moving image data creation system 100 is provided to create moving image data MV from file data FL having content of multiple pages. Specifically, it is assumed that file data FL having contents of multiple pages is specified in browser 111 of user terminal 110 and a predetermined operation is performed. At this time, the user terminal 110 transmits the specified file data FL to the first server 120.

[0026] Then, the first server 120 is configured to create video data MV using the artificial intelligence video generating means 131 of the second server 130 based on the contents of the received file data FL. At this time, the first server 120 transmits command information to the artificial intelligence moving image generating means 131 of the second server 130 as a prompt to generate moving image data MV based on the contents of the file data FL.

[0027] This allows the contents of multiple pages to be displayed as if they were being paged through in the video data MV. As a result, the user can easily create video data MV that can be paged through multiple pages of content.

[0028] Next, an example of the operation of the video data creation system 100 will be described in more detail. As shown in FIG. 2, in step S1, as a file data designation determination step, it is determined whether or not file data FL having contents of multiple pages is designated in browser 111 of user terminal 110 and a predetermined operation is performed. More specifically, as shown in FIG. 3, when a user logs in to the video data creation system 100 by inputting a user ID and password in the browser 111 of the user terminal 110, the browser 111 of the user terminal 110 displays a video creation loading screen 112.

[0029] The video creation loading screen 112 is provided with, as an example, an "Import" button 112a and a "Create video data" button 112b. When the "Import" button 112a is operated, the browser 111 pops up and displays a window 113 for file specification and dragging operations. The file designation / drag operation window 113 is provided with a drag area 113a.

[0030] Then, for example, it is assumed that the user performs a drag operation using the mouse to move the icon of the desired file data FL having the content of multiple pages to the drag area 113a. In this manner, when the icon of file data FL is dragged to drag area 113a, user terminal 110 determines that file data FL has been designated.

[0031] If the drag area 113a of the file specification / drag operation window 113 is clicked without dragging, the browser 111 pops up a file selection window 115, and a list of files is displayed in the file selection window 115. The desired file data FL may be selected and specified from this file list. Furthermore, when the "Create video data" button 112b is operated, a template that will become background data for the video data MV can be freely selected, and when selected, a display such as that shown in FIG. 4 appears.

[0032] When the file data FL is specified, the browser 111 switches the display to a moving image creation editing screen 114, as shown in FIG. The video creation editing screen 114 includes, for example, a "Preview" button 114a, a "Send" button 114b, an avatar candidate display area 114c, a layout display area 114h which displays a layout for editing, a speech display area 114k, and a frame display area 114p.

[0033] Then, the contents of the file data FL are read into the browser 111 and displayed in the layout display area 114h. The contents of multiple pages of the file data FL are read and displayed as thumbnails in the frame display area 114p. When a thumbnail of each page is selected, the display content in the layout display area 114h changes in response to the selection operation.

[0034] Furthermore, when the "Preview" button 114a is operated, a preview of the video data MV of the content at the time of the operation is displayed in the layout display area 114h. Furthermore, as an example of a predetermined operation, it is assumed that the "Send" button 114b is operated. In this way, when the "Send" button 114b is operated as an example of a specified operation, the user terminal 110 determines that the "Send" button 114b has been operated as an example of a specified operation and proceeds to step S2; on the other hand, if it determines that the operation has not yet been performed, step S1 is repeated.

[0035] In step S2, as a file data transmission step, user terminal 110 transmits the specified file data FL to first server 120. In step S3, as a moving image data creation step, the first server 120 creates moving image data MV using the artificial intelligence moving image generating means 131 of the second server 130 based on the contents of the received file data FL. As a result, as described above, the contents of multiple pages are displayed as if they were being paged through in the video data MV. As a result, the user can easily create video data MV that can be paged through multiple pages of content.

[0036] Furthermore, in this embodiment, when there is explanatory information FL1 in text format added to each page in the specified file data FL, the artificial intelligence video generation means 131 is configured to add audio data MV1 of the explanatory information FL1 in the video data MV in correspondence with the display of each page. More specifically, as shown in FIG. 5, when file data FL is loaded on the video creation editing screen 114 of the browser 111 and the contents of the page of the file data FL are displayed in the layout display area 114h, explanatory information FL1 in text format added to each page in the file data FL is also loaded and input into the text input field 114m of the speech display area 114k. Then, when the "Send" button 114b is operated, the artificial intelligence video generation means 131 creates video data MV based on the contents of the file data FL, and at this time adds audio data MV1 of the explanatory information FL1 to the video data MV in correspondence with the display of each page.

[0037] As a result, the so-called explanatory column information in the file data FL having content on multiple pages is read as explanatory information FL1 in text format by the artificial intelligence video generation means 131 and added as audio data MV1 corresponding to the display of each page in the video data MV. As a result, the user can easily add so-called description information to the video data MV as audio data MV1. In other words, by adding auditory sound in addition to visual moving images, it is possible to provide moving image data MV with high satisfaction to other users, i.e., viewers.

[0038] In this embodiment, the user can freely select avatars AV having the faces of living beings such as people and animals on the browser 111 of the user terminal 110. More specifically, as shown in FIG. 6, an avatar candidate display area 114c on a moving image creation editing screen 114 of the browser 111 is provided with, as an example, a "Library" tab 114d and a "My" tab 114f that can be freely switched. When the "library" tab 114d is selected, a plurality of avatar icons 114e are displayed in an avatar candidate display area 114c so as to be freely selectable. Then, when an arbitrary avatar icon 114e is clicked, for example, to select an avatar AV, the avatar AV can be freely arranged in layout display area 114h of video data MV.

[0039] For example, the user places the avatar AV at the bottom left in layout display area 114h for video data MV. Furthermore, as an example of a specified operation by the user, when the "Send" button 114b is pressed, the first server 120 is configured to use the artificial intelligence video generation means 131 of the second server 130 to add the action of the avatar AV speaking in response to the audio data MV1 to a position in the video data MV based on the placement operation.

[0040] As a result, the selected avatar AV is placed at a desired position in the video data MV and is displayed with its mouth moving in response to the audio data MV1 (see FIGS. 10(A) to 10(C)). As a result, users can easily have the avatar AV appear as the narrator. In other words, the narrator, whose mouth moves in response to the audio data MV1, is displayed as if he is speaking to other viewers who are users, and the other viewers feel that he is speaking to them. As a result, the user can convey the contents of the file data FL having multiple pages of content to the audience in a manner that is more attention-grabbing than a simple slide display configuration.

[0041] In addition, the avatar AV may have the face of a living creature such as a human or animal, and may be an animal other than a human, such as a monkey, deer, rabbit, or dolphin, or a living creature such as a frog, fish, octopus, or squid. Furthermore, the face of the avatar AV is not limited to being displayed in a realistic manner like the real thing, but may be displayed in an illustrated or cartoon form, etc.

[0042] Furthermore, in this embodiment, any facial photograph data can be freely specified and selected as the avatar AV on the moving image creation editing screen 114 of the browser 111 of the user terminal 110. More specifically, as shown in FIG. 7, when a "My" tab 114f is selected in the avatar candidate display area 114c, an upload button 114g is displayed. When the upload button 114g is clicked, the browser 111 displays a pop-up file selection window 115. Suppose that the user then designates any face photo data in the file selection window 115 and operates the "Select" button 115a. Then, any facial photograph data is loaded into the browser 111, and an original user avatar AV of the face in the designated / selected facial photograph data is arranged in the layout display area 114h of the video data MV.

[0043] As an example of a specified operation by the user, when the "Send" button 114b is pressed, the first server 120 is configured to use the artificial intelligence video generation means 131 of the second server 130 to add the action of the user's original avatar AV speaking in response to the audio data MV1 to a position in the video data MV based on the placement operation. In other words, when any facial photo data is specified / selected as the avatar AV, the first server 120 uses the artificial intelligence video generation means 131 of the second server 130 to recognize the mouth of the face in the facial photo data, generate facial data showing the mouth moving, and add it to a position based on the placement operation in the video data MV.

[0044] In this way, by specifying any face photo data, face data of a user's original avatar AV moving its mouth is generated and added to the video data MV (see Figs. 10(A) to 10(C)). As a result, the user can easily display an avatar AV with a desired facial photo as a narrator on the video data MV.

[0045] In this embodiment, the voice of the audio data MV1 to be added to the video data MV on the video creation editing screen 114 of the browser 111 of the user terminal 110 can be freely selected from a plurality of options. More specifically, as shown in FIG. 8, the speech display area 114k is provided with a voice setting field 114n. An arbitrary voice is set by default, but when a voice setting field 114n is clicked, for example, the browser 111 pops up and displays a voice selection window 116. The voice selection window 116 is provided with, for example, a voice candidate button 116a for various settings, a "Generate from your own voice" button 116b, and an "Import your own voice" button 116c.

[0046] When the user selects a desired one from a plurality of voice candidate buttons 116a with various settings, the voice setting field 114n is switched to the setting of the selected voice candidate button 116a. In other words, when a voice is specified / selected from a plurality of options, the first server 120 is configured to create voice data MV1 using the artificial intelligence animation generation means 131 of the second server 130 based on the information of the specified / selected voice. In this way, a desired voice is designated, and audio data MV1 of the designated voice is generated and added to the moving image data MV. As a result, the user can easily input narration in the desired voice.

[0047] When the "import your own voice" button 116c is operated, voice data generated by other applications can be freely imported. Furthermore, when the user's own voice is selected from among a number of options in browser 111 of user terminal 110, the user's voice can be freely recorded using the microphone of user terminal 110. More specifically, when the "Generate from your own voice" button 116b is operated, the browser 111 pops up a voice recording window 117 as shown in FIG. The voice recording window 117 is provided with a "Start" button 117a.

[0048] When "Start" button 117a is operated, user terminal 110 activates the microphone of user terminal 110, enabling recording of the user's voice. Then, by transmitting the user's voice recording data from this recording to the first server 120, the first server 120 can create voice data MV1 using the artificial intelligence video generation means 131 of the second server 130 based on the specified / selected voice recording data. This generates voice data MV1 based on sampling data of the user's own voice recording data. As a result, narration in the user's own voice can be easily added. That is, as shown in Figs. 10(A) to 10(C), a narration can be created using the user's voice.

[0049] The audio data MV1 is generated based on the text information entered in the text input field 114m of the speech display area 114k of the video creation editing screen 114. In addition to this, a so-called caption MV2 may be displayed (subtitle display) based on the text information in the video data MV in accordance with the narration.

[0050] Furthermore, in this embodiment, as shown in FIG. 11, when the user operates a list display button (not shown) on the video creation editing screen 114, for example, the browser 111 of the user terminal 110 displays a video list screen 118. The video list screen 118 is provided with a search item selection field 118a, a search word input field 118b, a "Search" button 118c, a log management tab, and a detailed content tab. Of these, when the log management tab is selected, log information (operation history information) of user operations on the moving image creation loading screen 112 and the moving image creation editing screen 114 is displayed. In addition, when the detailed content tab is selected, as an example, the following items are displayed: video creation date and time, user ID, original file name, speech summary, full speech, image content, and information corresponding to these items.

[0051] Among these, the original file name item displays file name information of the file data FL having the contents of the multiple pages that have been read. Also, in the speech summary item, summary information AB of the text information entered in the text entry field 114m of the speech display area 114k for all pages is displayed. As for the summary information AB, the text information entered in the text input field 114m of the speech display area 114k for all pages is sent to the chat GPT, which is an example of a pre-trained artificial intelligence means, along with instruction information to create a summary as a prompt, and the summary information AB is generated.

[0052] Further, in the section for the entire speech, text information input in the text input field 114m of the speech display area 114k for all pages is displayed. Furthermore, in the section for the image content, the image recognition means reads character information in the background of the video data MV and converts it into text, and the text content information is displayed. In addition, in the search item selection field 118a, each item in the detailed contents tab is provided in a pull-down format so that it can be freely selected. Then, when the user selects an arbitrary item in the search item selection field 118a, inputs a desired keyword in the search word input field 118b, and operates the "Search" button 118c, information on the desired video data MV is displayed.

[0053] This will result in searches that include the content of the narration in video data MVs. As a result, the user can find the desired video data MV without having to play back and watch the video data MV from start to finish. In other words, it is not necessary to take time to play back the video data MV to check the contents, and the video data MV with the desired contents can be found in a short time.

[0054] The video data creation system 100, an embodiment of the present invention obtained in this manner, comprises a user terminal 110 and a first server 120 and a second server 130, which are examples of servers. When file data FL having content of multiple pages is specified on the video create loading screen 112 of the browser 111 of the user terminal 110 and a "Send" button 114b, which is an example of a predetermined operation, is operated on the video create editing screen 114, the user terminal 110 transmits the specified file data FL to the first server 120, and the first server 120 creates video data MV using the artificial intelligence video generation means 131 of the second server 130 based on the content of the received file data FL, so that the user can easily create video data MV that is page-fed for content of multiple pages.

[0055] Furthermore, if the specified file data FL contains explanatory information FL1 in text format added to each page, the artificial intelligence video generation means 131 is configured to add audio data MV1 of the explanatory information FL1 in the video data MV in correspondence with the display of each page, allowing the user to easily add information in the so-called explanatory column to the video data MV as audio data MV1, and by adding auditory audio in addition to the visual video, video data MV that provides high satisfaction to other users, the viewers, can be provided.

[0056] In addition, an avatar AV having a human face can be freely selected on the video creation editing screen 114 of the browser 111 of the user terminal 110, and when an avatar AV is selected, the avatar AV can be freely positioned in the layout display area 114h of the video data MV. When the "Send" button 114b, which is an example of a predetermined operation, is operated, the first server 120 uses the artificial intelligence video generation means 131 of the second server 130 to add the action of the avatar AV speaking in response to the audio data MV1 to a position based on the positioning operation in the video data MV. This allows the user to easily display the avatar AV as a narrator, and the user can convey the contents of file data FL having content on multiple pages to the viewer with greater attention than with a simple slide display configuration.

[0057] Furthermore, any facial photo data can be freely specified and selected as the avatar AV on the video creation editing screen 114 of the browser 111 of the user terminal 110, and when any facial photo data is specified / selected as the avatar AV, the first server 120 uses the artificial intelligence video generation means 131 of the second server 130 to recognize the mouth of the face in the facial photo data and generate face data showing the mouth moving, and adds it to a position based on the placement operation in the video data MV, so that the user can easily display the avatar AV of the desired facial photo as a narrator on the video data MV.

[0058] Furthermore, the voice of the audio data MV1 to be added to the video data MV on the video creation editing screen 114 of the browser 111 of the user terminal 110 can be freely selected from a plurality of options, and when a voice is specified / selected from the plurality of options, the first server 120 creates the audio data MV1 using the artificial intelligence video generation means 131 of the second server 130 based on the information of the specified / selected voice, so that the user can easily insert narration in the desired voice.

[0059] Furthermore, when the user's own voice is selected from among multiple options on the video creation editing screen 114 of the browser 111 of the user terminal 110, the user's voice can be freely recorded using the microphone of the user terminal 110, and the first server 120 creates audio data MV1 using the artificial intelligence video generation means 131 of the second server 130 based on the recorded user's voice recording data, so that narration in the user's own voice can be easily inserted.

[0060] Furthermore, the program of the video data creation system 100, which is an embodiment of the present invention, includes a file data designation determination step S1 in which it is determined whether file data FL having content of multiple pages has been designated on the video create loading screen 112 of the browser 111 of the user terminal 110 and whether the ``Send'' button 114b, which is an example of a predetermined operation, has been operated on the video create editing screen 114, a file data transmission step S2 in which the user terminal 110 transmits the designated file data FL to the first server 120, and a video data creation step S3 in which the first server 120 creates video data MV using the artificial intelligence video generation means 131 of the second server 130 based on the content of the received file data FL, thereby providing enormous benefits, such as allowing the user to easily create video data MV that is page-fed for content of multiple pages. [Explanation of symbols]

[0061] 100 ··· Video data creation system 110 User terminal 111 ··· Browser 112 ··· Video Creator loading screen 112a "Import" button 112b "Create video data" button 113 File selection and drag operation window 113a... Drag area 114 ··· Video creation editing screen 114a "Preview" button 114b "Send" button 114c···Avatar candidate display area 114d... "Library" tab 114e··· Avatar Icon 114f... "My" tab 114g... Upload button 114h Layout display area (layout display for editing) 114k... Speech display area 114m··· Text field 114n...Voice setting field 114p... Frame display area 115 File selection window 115a "Select" button 116 Voice selection window 116a··· Voice candidate button 116b "Generate from your own voice" button 116c "Import your own voice" button 117 ··· Voice recording window 117a "Start" button 118 ··· Video list screen 118a··· Search item selection field 118b··· Search word input field 118c... "Search" button 120 1st Server 130 Second Server 131 ··· Artificial intelligence video generation means FL: File data (containing multiple pages of content) FL1... Description AV...Avatar MV...Video data MV1: Audio data MV2 ... Caption AB Summary Information

Claims

1. A video data creation system that includes a user terminal and a server and creates video data from file data having content on multiple pages, comprising: When file data having contents of multiple pages is specified in a browser of the user terminal and a predetermined operation is performed, the user terminal transmits the specified file data to a server; A video data creation system characterized in that the server is configured to create video data using an artificial intelligence video creation means based on the contents of the received file data.

2. The video data creation system of claim 1, characterized in that when the specified file data contains explanatory information in text format added to each page, the artificial intelligence video generation means is configured to add audio data of the explanatory information to the video data in correspondence with the display of each page.

3. The video data creation system of claim 1 or claim 2, characterized in that an avatar having a human face can be freely selected in the browser of the user terminal, and when the avatar is selected, the avatar can be freely positioned in the editing layout display of the video data, and when the specified operation is performed, the server uses the artificial intelligence video generation means to add the action of the avatar speaking in response to the audio data to a position in the video data based on the positioning operation.

4. The video data creation system described in claim 3, characterized in that any facial photo data can be freely designated and selected as an avatar in the browser of the user terminal, and when any facial photo data is designated and selected as the avatar, the server uses the artificial intelligence video generation means to recognize the mouth of the face in the facial photo data, generate facial data showing the mouth moving, and add it to a position based on a placement operation in the video data.

5. The video data creation system described in claim 4, characterized in that the voice of the audio data to be added to the video data can be freely selected from among a plurality of options in the browser of the user terminal, and when a voice is specified / selected from among the plurality of options, the server creates the audio data using an artificial intelligence video generation means based on the information of the specified / selected voice.

6. The video data creation system described in claim 5, characterized in that when the user's own voice is selected from a plurality of options in the browser of the user terminal, the user's voice can be freely recorded using the microphone of the user terminal, and the server creates the audio data using an artificial intelligence video generation means based on the recorded user's voice data.

7. A program for a video data creation system that creates video data from file data having content on multiple pages, comprising: a file data designation determination step of determining whether or not a predetermined operation has been performed by designating file data having content of multiple pages in a browser of the user terminal; a file data transmission step in which the user terminal transmits designated file data to a server; a video data creation step in which the server creates video data using artificial intelligence video generation means based on the contents of the received file data.

Images