Text-to-video generation method, apparatus, electronic device, and storage medium

Abstract

An embodiment of the present invention provides a text video generation method, apparatus, electronic device, and storage medium, which display a text editing page including a text input area, display target text in the text input area in response to a first input command on the text editing page, and generate a target video to display the target text in the text input area, where the target text has a first font state in the text input area, the first font state characterizing a font size and / or line spacing of the target text, the first font state being determined by the length of the target text. By dynamically changing the font size and / or line spacing of the target text edited in the text input area according to the length of the text and then converting the target text in the text input area, the generated target video can clearly and comprehensively display the entire content of the target text, thereby improving video generation efficiency and video quality in the video creation process.

Description

Technical Field

[0001] [Cross-reference to Related Applications] This application claims the priority of a Chinese patent application for invention with the title "Text Video Generation Method, Apparatus, Electronic Device, and Storage Medium", application number 202211567282.4, filed on December 7, 2022, and the entire content disclosed in the above application is incorporated herein by reference.

[0002] [Technical Field] Embodiments of the present invention relate to the field of Internet technologies, and in particular, to a text video generation method, apparatus, electronic device, and storage medium.

Background Art

[0003] Currently, short video platforms are being loved by more and more users due to their rich and diverse content. A posting portal is installed on the client of the short video platform for the public to use by general users. Creator users can post by shooting and uploading videos. The service side of the short video platform pushes the content uploaded by the creator users to the viewing users for consumption.

[0004] In the prior art, short video platforms usually only receive video works created by users and cannot edit and generate text videos. As a result, users have to manually create plain text works into videos and upload them to the short video platform, which reduces the video generation efficiency and quality in the video creation process.

Summary of the Invention

Problems to be Solved by the Invention

[0005] Embodiments of the present invention provide a text-to-video generation method, apparatus, electronic device, and storage medium for overcoming the problem of not being able to generate videos in plain text format. [Means for solving the problem]

[0006] In a first embodiment, an embodiment of the present invention provides a text-video generation method, the method is Displaying a text editing page, the text editing page including a text input area; displaying target text in the text input area in response to a first input command to the text editing page, the target text having a first font state within the text input area, the first font state characterizing the font size and / or line spacing of the target text, the first font state being determined by the length of the target text; and generating a target video for displaying the target text within the text input area.

[0007] In a second embodiment, an embodiment of the present invention provides a text-video generation device, the device is An editing module for displaying a text editing page, wherein the text editing page includes an editing module that includes a text input area, A display module for displaying target text in a text input area in response to a first input command to a text editing page, wherein the target text has a first font state within the text input area, the first font state characterizes the font size and / or line spacing of the target text, and the first font state is determined by the length of the target text; The system includes a generation module for generating a target video to display the target text in the text input area.

[0008] In a third embodiment, an embodiment of the present invention provides an electronic device, the electronic device is The system comprises a processor and a memory that is communicably connected to the processor, The aforementioned memory stores computer execution instructions, The processor implements the text-video generation method described in the first embodiment and various possible designs of the first embodiment by executing computer execution instructions stored in the memory.

[0009] In a fourth embodiment, an embodiment of the present invention provides a computer-readable storage medium in which computer execution instructions are stored, and when a processor executes the computer execution instructions, the text-video generation method described in the first embodiment and various possible designs of the first embodiment described above is realized.

[0010] In a fifth embodiment, an embodiment of the present invention provides a computer program product including a computer program, wherein the text-video generation method described in the first embodiment and various possible designs of the first embodiment is realized when the computer program is executed by a processor. [Effects of the Invention]

[0011] The text video generation method, apparatus, electronic device, and storage medium provided by this embodiment display a text editing page including a text input area, display target text in the text input area in response to a first input command to the text editing page, and generate a target video to display the target text in the text input area, wherein the target text has a first font state in the text input area, the first font state characterizes the font size and / or line spacing of the target text, and the first font state is determined by the length of the target text. By setting a text input area, dynamically changing the font size and / or line spacing of the target text edited in the text input area according to the length of the text, and then transforming the target text in the text input area, the generated target video can clearly and comprehensively display all the contents of the target text, achieving the objective of generating text videos based on plain text, and improving video generation efficiency and video quality in the video creation process. [Brief explanation of the drawing]

[0012] In the following, in order to more clearly illustrate embodiments of the present invention or technical solutions of the prior art, the drawings used to illustrate the embodiments or prior art will be briefly described. Clearly, the drawings described below represent only a few embodiments of the present invention, and those skilled in the art can obtain other drawings based on these without requiring any creative effort. [Figure 1] This is a diagram illustrating an application scenario for the text-video generation method provided by an embodiment of the present invention. [Figure 2] This is a schematic flowchart of the text-to-video generation method provided by an embodiment of the present invention. [Figure 3] This is a schematic diagram showing the target text displayed in the text input area provided by an embodiment of the present invention. [Figure 4] Figure 2 is a flowchart showing the specific implementation of step S103 in the embodiment. [Figure 5] Another flowchart schematic diagram of the text video generation method provided by an embodiment of the present invention. [Figure 6] It is a flowchart of a specific implementation form of step S203 in the embodiment shown in FIG. 5. [Figure 7] It is a schematic diagram of the area size of the text input area provided by an embodiment of the present invention. [Figure 8] It is a flowchart of a specific implementation form of step S2033 in the embodiment shown in FIG. 6. [Figure 9] It is a schematic diagram of the background image provided by an embodiment of the present invention. [Figure 10] It is a flowchart of a specific implementation form of step S205 in the embodiment shown in FIG. 5. [Figure 11] It is a block diagram of the configuration of the text video generation device provided by an embodiment of the present invention. [Figure 12] It is a schematic diagram of the configuration of the electronic device provided by an embodiment of the present invention. [Figure 13] It is a schematic diagram of the hardware configuration of the electronic device provided by an embodiment of the present invention.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, in order to make the purpose, technical solution, and advantages of the embodiments of the present invention clearer, in conjunction with the drawings of the embodiments of the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by those skilled in the art without creative labor based on the embodiments in the present invention all belong to the protection scope of the present invention.

[0014] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) related to the present invention are all information and data approved by the user or fully approved by all relevant parties. The collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. It should be noted that a corresponding operation portal is provided so that the user can select approval or rejection.

[0015] In the following, the application scenarios of the embodiments of the present invention will be interpreted.

[0016] FIG. 1 is an application scenario diagram of the text video generation method provided by the embodiment of the present invention. The text video generation method provided by the embodiment of the present invention can be applied to an application scenario of editing and uploading videos on the client side of a short video platform. Specifically, as shown in FIG. 1, the method provided by the embodiment of the present invention can be applied to terminal devices such as smartphones. Inside the terminal device, the client of the short video platform operates. Inside the client, a text editing page is set. The terminal device responds to user operations, triggers the corresponding component, and enters the text editing page. Within the document editing page,A text input area is set up, and the user edits text within that text input area using the input method. Specifically, as shown in the diagram, for example, when the user clicks on the text input area, the text input area enters edit mode and a text input cursor appears. At the same time, an input method interface pops up on the text editing page, and the user operates this input method interface to enter text into the text input area and generate the target text (in the diagram, "X" represents a character). After completing the input of the target text, the input method interface disappears, and the complete text input area is displayed on the text editing page. Then, when the "Done" button is clicked, the target text in the text input area is rendered, video material is generated, and it is uploaded to the short video platform service side (shown as the platform server in the diagram), thus completing the process of generating a video work from a plain text work and uploading it to the short video platform. On the other hand, clicking the "Back" button exits the text editing page, and the details will not be repeated.

[0017] In conventional technology, the client side of a short video platform typically receives user-created video content, implements necessary steps such as transcoding and compression, and then uploads it to the service's video pool. The service then pushes the videos to different users based on the videos in the video pool. However, for videos with plain text content, short video platform clients typically do not provide a function page for editing and creation. This is because, in the plain text editing process, the length of the text is determined by the text content edited by the user, and if the text is displayed with a fixed font size and line spacing, problems arise where the font and line spacing become too small or too large. For example, taking fonts as an example, if the target text edited by the user contains 5 Chinese characters, the font size is appropriate when displayed with a fixed font size of 3 (example). However, if the target text edited by the user contains 500 Chinese characters, and it is still displayed with a fixed font size of 3, the font becomes too large, and it becomes impossible to display all of the target text content on the same screen. On the other hand, since text videos are videos that statically display text (i.e., the video always displays the same frame's content), this can lead to the problem of missing content in the text video generated based on the rendering of the target text. Conversely, in the example above, if the target text edited by the user contains five Chinese characters, the font will be too small, resulting in the text video generated based on the rendering of the target text having an excessively small font, which affects the video display effect. Because the font size and line spacing cannot be automatically adjusted, the generated text video will not have proper text content, making it difficult to achieve the purpose of video display for text videos.Therefore, with conventional technology, each short video platform can typically receive text videos created by users, but it cannot automatically generate text videos with good display effects.

[0018] An embodiment of the present invention provides a text-to-video generation method for solving the above problems.

[0019] Referring to Figure 2, Figure 2 is a schematic flowchart of a text-to-video generation method provided by an embodiment of the present invention. The method of this embodiment may be applied to a terminal device, and the text-to-video generation method includes the following steps.

[0020] In step S101, a text editing page is displayed, which includes a text input area.

[0021] For illustrative purposes, the schematic diagram of the application scenario shown with reference to Figure 1 shows that a client of the short video platform (hereinafter abbreviated as "client") launches a text editing page in response to a trigger operation, specifically referring to the configuration shown in Figure 1, where the functional component for triggering the text editing page may be set on the client's video playback page (i.e., the default page for short video application) or on the video recording page for uploading video works, i.e., the frame page. Subsequently, after receiving a user trigger operation on the functional component, the text editing page is displayed.

[0022] Furthermore, a text input area is set within the text editing page. For example, after a terminal device receives a user click on the text input area, it activates the text input area and gains input focus. The user can then input text, symbols, and other character information into the text input area using the input method. Here, the position and size of the text input area are set as needed and are not limited to these.

[0023] In step S102, in response to a first input command to the text editing page, target text is displayed in the text input area, where the target text has a first font state within the text input area, the first font state characterizes the font size and / or line spacing of the target text, and the first font state is determined by the length of the target text.

[0024] For example, after the text input area gains input focus, the terminal device receives a first input command entered by the user, where the first input command is used to generate text information for the target text, and the first input command may include identifiers corresponding to specific characters or symbols, or identifiers for forming the pronunciation elements of characters, such as Chinese pinyin, the alphabet, etc., which are not repeated here. After receiving the first input command, the terminal device converts the first input command into the corresponding text and symbols using the input method within the system, displays it in the text input area, and forms the target text, which is the final text awaiting publication.

[0025] Here, the target text may contain one or more characters and symbols. Note that the symbols entered and displayed in the text input area include visible and invisible symbols. Visible symbols include text editing symbols such as commas and periods (details will not be repeated), while invisible symbols include spaces, blank lines, and line breaks. The target text, composed of characters and symbols, has a paragraph structure; for example, the target text is divided into multiple paragraphs, and the target text includes blank lines, etc., thereby making the target text in the text input area more visually readable.

[0026] Furthermore, the target text within the display text input area has a first font state, where the first font state characterizes the font size and / or line spacing of the target text, and the first font state is determined by the length of the target text. Specifically, the longer the target text, the smaller the font size of the text and symbols within the target text, and / or the smaller the line spacing between lines within the target text. Conversely, the shorter the target text, the larger the font size of the text and symbols within the target text, and / or the larger the line spacing between lines within the target text. Simply put, when the target text is longer, the terminal device compresses the target text within the text input area to allow the text input area to contain more characters and symbols, and when the target text is shorter, it increases the font size to make the content of the target text more prominent and improve the visual display effect. Of course, there is a certain tolerance range for adjusting the first font state (i.e., the font size and / or line spacing of the target text), and there is a predetermined non-linear correspondence between the first font state and the length of the target text. The specific implementation of this will be explained in subsequent examples, so it is understood that it will not be repeated here.

[0027] Herein, further, based on the above-described description of the implementation of the target text, the length of the target text may be determined by the number of characters in the target text, by the total number of characters and symbols in the target text, or by the overall length occupied by the target text within the text input area. For example, if the target text contains blank line characters, one blank line character occupies one blank line in the text input area. Therefore, if the target text contains blank lines, determining the length of the target text based on the overall length occupied by the target text within the text input area allows for a more accurate measurement of the actual length of the target text, thereby improving the display effect of the final produced target video.

[0028] Figure 3 is a schematic diagram showing the display of target text in a text input area provided by an embodiment of the present invention. As shown in Figure 3, in this embodiment, the total number of characters in the target text is defined as the length of the target text. Based on a first input command, the terminal device continuously displays the corresponding target text in the text input area. When the length of the target text N=10 (first time step), the first font state of the target text is Info_1, and the font size characterizing each character and symbol in the target text is #4. As the first input command is continuously input, the length of the target text continues to increase. When the length of the target text N=50 (second time step), the first font state of the target text is Info_2, and the font size characterizing each character and symbol in the target text is #5 (one step smaller than #4). This achieves the objective of displaying the font size of the dynamic target text in the text input area.

[0029] Furthermore, based on the embodiments described above, the first font state further includes information characterizing the line spacing, and the first font state can be used to further adjust the line spacing of the target text. For example, when the length of the target text is N=10, the first font state of the target text is Info_l, the font size characterizing each character and symbol in the target text is #4, and the line spacing is 1. When the length of the target text is N=50, the first font state of the target text is Info_2, the font size characterizing each character and symbol in the target text is #5, and the line spacing is 0.8.

[0030] Alternatively, in another possible implementation, the line spacing of the target text can also be determined based solely on the length of the target text. For example, as shown in Figure 3, when the length of the target text N=10, the first font state of the target text is Info_l, characterized by a line spacing of 1; and when the length of the target text N=50, the first font state of the target text is Info_2, characterized by a line spacing of 0.8.

[0031] In step S103, a target video is generated to display the target text in the text input area.

[0032] For example, the target text in a text input area has a corresponding first font state, and then the text input area is rendered to generate a video of a predetermined length, i.e., a target video. Here, since the target video corresponds to a restored display of the target text in the text input area, the target video can not only display the text content of the target text but also restore the first font state of the target text, i.e., the size of the characters and / or line spacing within the target text, so that the target text displayed in the target video can visually match the target text displayed in the text input area. Furthermore, this ensures that the display effect of the final generated target video (i.e., text video) can be accurately expected during the process of editing text content in the text input area, and improves the video quality of the final generated target video. Problems such as the text in the generated text video being too small to read or the text in the text video being too large to be fully displayed can be avoided.

[0033] In one possible implementation, as shown in Figure 4, the specific implementation of step S103 is: Step S1031: Generate a rendering image containing the target text having a first font state based on the target text. Step S1032: Determine the video length based on the target text length. Step S1033 includes generating a target video based on the video duration and rendering images.

[0034] For example, first, after the target text has been entered into the text input area, the target text having a first font state within the text input area is converted into an image, i.e., a rendered image, based on the target text within the text input area. Here, there are various specific implementations for converting text to an image, such as generating a rendered image by taking a picture of the text input area, or generating a corresponding rendered image by inputting the target text and the corresponding first font state as input parameters into an image converter. The specific implementation steps for converting characters to an image are prior art known to those skilled in the art and will not be repeated here.

[0035] Furthermore, the corresponding video length is determined based on the length of the target text, such as the number of characters in the target text. The final generated target video needs to match the user's viewing time when displaying the target text. Therefore, the longer the target text, the longer the time it takes for the user to view the target text within the target video. By setting the video length to match the length of the target text, the display effect of the target video can be improved. Subsequently, a video conversion is performed using the rendered image as source material and the video length as a parameter to generate a static video, i.e., the target video.

[0036] In this embodiment, a text editing page including a text input area is displayed, and in response to a first input command to the text editing page, target text in the text input area is displayed, and a target video is generated to display the target text in the text input area, where the target text has a first font state in the text input area, the first font state characterizes the font size and / or line spacing of the target text, and the first font state is determined by the length of the target text. By setting a text input area, dynamically changing the font size and / or line spacing of the target text edited in the text input area according to the length of the text, and then transforming the target text in the text input area, the generated target video can display all the contents of the target text clearly and comprehensively, achieving the objective of generating a text video based on plain text, improving the efficiency of video generation in the video creation process, and improving the diversity of video content within the video platform.

[0037] Figure 5 is a schematic flowchart of another text video generation method provided by an embodiment of the present invention. This embodiment further refines step S102 based on the embodiment shown in Figure 2, adding a step to configure a background image and background music for the target video, and the text video generation method is Step S201, displaying a text editing page, the text editing page including a text input area, Step S202: In response to the first input command, generate the target text and obtain the total number of characters in the target text. Step S203 includes determining a first font state based on the total number of characters and the area size of the text input area.

[0038] For example, an editing page can be displayed, and in response to a first input command for the editing page, corresponding characters and symbols can be generated based on the information in the first input command, and further, target text can be generated. The specific implementation steps have been described in detail in the embodiment shown in Figure 2 and will not be repeated here. Subsequently, the total number of characters in the target text can be obtained by calling a statistical function and processing the string corresponding to the target text. Here, the total number of characters in this embodiment may be only the number of characters in the target text, or it may be the sum of the number of characters and the number of symbols.

[0039] For example, a text input area on a text editing page has an area size. If the text input area is rectangular, the area size may be its length and width. Furthermore, the area size can represent the area of ​​the text input area; the larger the area, the greater the total number of characters that can be displayed. The area size of a text input area is a predetermined fixed value, which can be determined according to the screen pixel size of the terminal device, and this will not be repeated here.

[0040] Furthermore, after determining the total number of characters and the area size of the text input area, the total area of ​​the text input area is first calculated based on the area size of the text input area. Then, the unit area occupied by the font size (and symbols) is obtained using the ratio between the total area and the total number of characters. Finally, the font size and / or the corresponding line spacing, i.e., the first font state, can be determined based on the unit area and a predetermined correction coefficient. The above implementation does not take into account the effects of blank areas caused by line breaks and blank lines, and is therefore suitable for a rough calculation of the first font state.

[0041] In another possible implementation, the area size includes the area width and the area height, and as shown in Figure 6, the specific implementation of step S203 is: Step S2031: Determine the number of characters per line based on the font width corresponding to the base font size and the horizontal size of the area, wherein the number of characters per line is characterized by the number of characters that can be displayed on one line of the text input area. Step S2032: Determine the first vertical size based on the number of characters per line and the total number of characters. Step S2033 includes determining a first font state based on a first vertical size and an area vertical size.

[0042] Figure 7 is a schematic diagram of the area size of a text input area provided by an embodiment of the present invention. As shown in Figure 7, within the client's text editing page, the text input area is a vertically oriented rectangular area (suitable for smartphone display screens). In the drawing, the horizontal area size is shown as dim_x, and the vertical area size is shown as dim_y. The user enters the target text into the text input area. The base font size is the font size of a predetermined input character, having corresponding font width and font height. For example, if the font is a Chinese font, the font width and font height of the text may be the same. Based on the proportional value between the horizontal area size and the font width corresponding to the base font size, the number of characters per line, i.e., the number of characters that can be displayed in one line of the text input area, can be determined. For example, 20 characters. Then, the total number of characters in the target text can be divided by the number of characters per line to obtain the total number of lines. Based on the font height and base line spacing, the average height of the lines can be obtained, and the product of the average line height and the total number of lines can be calculated to obtain the first vertical size, indicated as dim_Y in the drawing. Here, the base line spacing, like the base font size, may be a predetermined value, and we will not repeat it here by giving an example.

[0043] Furthermore, after determining the first vertical size, the first vertical size is compared with the area vertical size. If the first vertical size is larger than the area vertical size, this indicates that the font size and / or line spacing are larger at this point, resulting in the text exceeding the text input area. This makes it impossible to display all the content of the target text in a static display manner for the subsequently generated target video. In this case, the base font size and / or base line spacing, which affect the first vertical size, are reduced to obtain the first font state. Specifically, for example, the base font size and / or base line spacing are multiplied by a proportionality coefficient of less than 1 to obtain the first font state. Alternatively, if the first vertical size is smaller than the area vertical size, this indicates that the font size and / or line spacing are smaller at this point. This results in the target text not being reasonably laid out within the text input area, affecting the display effect of the subsequently generated target video. In this case, the base font size and / or base line spacing, which affect the first vertical size, are increased to obtain the first font state. Specifically, for example, the base font size and / or base line spacing are multiplied by a proportionality coefficient greater than 1 to obtain the first font state.

[0044] Here, as an example, the proportional relationship between the first vertical size and the area vertical size can be determined by adjusting the proportionality coefficient of the base font size and / or base line spacing. As shown in Figure 8, a specific implementation of step S2033 is as follows: Step S2033A: Obtain the proportional value between the first vertical size and the area vertical size, Step S2033B, if the proportional value is less than the first proportional threshold, determine the first font state based on the base font size and / or base line spacing. Step S2033C includes, if the proportional value is greater than the first proportional threshold, reducing the base font size and / or base line spacing based on the proportional value to obtain a first font state.

[0045] For example, after determining the first vertical size and the area vertical size, a proportional value is calculated between the first vertical size and the area vertical size. For instance, if the first vertical size is 8 (in a predetermined unit) and the area vertical size is 10, the proportional value between the first vertical size and the area vertical size is 0.8. The first proportional threshold characterizes the proportion of the text input area, i.e., the screen proportion after the target video is generated. If the first proportional threshold is 1, it characterizes the entire area of ​​the text input area; if the first proportional threshold is 0.8, it characterizes 80% of the area of ​​the text input area (the ideal display area). Furthermore, in one possible case, if the proportional value is smaller than the first proportional threshold, it indicates that the target text does not extend beyond the text input area, preventing the problem of the generated target video not being able to display all of the target text. At the same time, the base font size and / or base line spacing can be considered ideal parameters set according to specific needs, and therefore the base font size and / or base line spacing can be set to the first font state.

[0046] In another possible case, if the proportional value is greater than the first proportional threshold, it indicates that the target text has exceeded the text input area or the ideal display area of ​​the text input area, which may result in the generated target video not being able to display all of the target text. In this case, the base font size or base line spacing is adjusted based on the proportional value, where the first proportional threshold is, for example, 1. Specifically, for example, if the proportional value is between 0.8 and 1, the font size is reduced by one step; if the proportional value is between 0.6 and 0.8, the font size is reduced by two steps; and so on, by analogy, thereby determining the target font size and / or target line spacing obtained by reducing the base font size and / or base line spacing as the first font state.

[0047] In step S204, the target text is displayed in the text input area based on the first font state.

[0048] In the steps of this embodiment, a proportional value between the first vertical size and the area vertical size is calculated, and the matching first font state is dynamically determined by reducing the proportional value based on the base font size and base line spacing. This allows for more precise control over the length of the target text within the text input area, improving the content length of the ultimately generated target video and enhancing the display effect of the text video and the user's viewing experience.

[0049] In step S205, in response to a second input command for the text editing page, a background image is displayed within the text editing page.

[0050] Exemplary, based on the steps above, the text editing page is further configured with components for composing a background image, and the user can display the background image within the text editing page by triggering these components through an operation command. Here, specifically, the display area corresponding to the background image is the background image area, and this background image area covers the text input area. Figure 9 is a schematic diagram of a background image provided by an embodiment of the present invention, and as shown in Figure 9, after the terminal device receives a user click operation on the “Add Background” control, it generates and executes a second input command, Within the document editing page The background image is automatically added to the background image area, where the background image area covers the text input area and the text input area is centered within the background image. In the next step, the background image area is rendered as the target area, and a corresponding target video is generated. This displays the target text in the generated target video on top of the background image, improving the display effect of the target text in the target video.

[0051] Here, illustratively, the target text further has a second font state, the second font state characterizes the font color of the target text, and a specific implementation of step S205 is shown in Figure 10. Step S2051, in response to the second input command, matching the target color based on the second font state, wherein the color difference between the target color and the font color is greater than the color difference threshold. Step S2052 includes obtaining a background image whose main color is the target color based on a given gallery, and displaying the background image within the text editing page.

[0052] For example, after receiving a second input command, the system first obtains the second font state of the target text, i.e., the font color of the target text. This second font state may be set by an operation command entered by the user, and the specific implementation is prior art, so the details will not be repeated. Subsequently, based on the font color characterized by the second font state, another color whose color difference is greater than the color difference threshold, i.e., the target color, is determined. Simply put, a color with a high color difference from the target text font is determined as the target color. For example, if the font of the target text is black, the target color is white, light green, light blue, etc. (a color whose color difference from black is greater than the threshold). Subsequently, the system obtains a main color from a predetermined gallery as the background image for the target color. This ensures that the background image has a higher contrast with the font color of the target text, thereby avoiding the problem of the target text being difficult to identify due to the similarity of the background image and the target text's colors, and improving the display clarity of the target text within the target video.

[0053] In step S206, background music is obtained based on the background image.

[0054] Furthermore, after obtaining a background image, the system automatically selects background music that matches the background image. For example, if the background image is a "landscape," the system obtains song tags for music with a calming rhythm that matches the image based on its semantic information. If the background image is "people dancing on a dance floor," the system obtains song tags for music with a dynamic rhythm that matches the image based on its semantic information. Subsequently, the system selects the corresponding target music from the music library as background music based on the song tags. The specific implementation of obtaining semantic information from a background image and obtaining corresponding song tags based on that semantic information can be achieved using a pre-trained image semantic model, so it will not be repeated here.

[0055] In the steps of this embodiment, by obtaining background music that matches the background image, the background image and background music have semantic consistency, resulting in a better video representation of the final generated target video and improved text video quality.

[0056] In step S207, a target video is generated based on the target text in the text input area, the background image, and the background music.

[0057] The process of obtaining target text, background image, and background music, and then rendering based on the target text and background image to obtain a corresponding rendered image, has already been described in the embodiment shown in Figure 2, so it will not be repeated here. Subsequently, the rendered image and background music are merged and transformed to obtain the target video. Here, exemplary, the video duration of the target video in this embodiment may be determined by the music duration of the background music, and the specific implementation steps have already been described in the embodiment shown in Figure 2, so they will not be repeated here.

[0058] Of course, in other possible embodiments, after obtaining the target text and the corresponding first font state, only the background image or background music that matches the target text can be obtained, and further, a target video can be generated based on the target text and background image, or a target video can be generated based on the target text and background music, where it is understood that the background music is determined based on the semantic information of the target text. The specific implementation process is the same as the implementation process in the embodiment steps described above, and the details will not be repeated.

[0059] Corresponding to the text-video generation method of the above embodiment, Figure 11 is a block diagram of the configuration of the text-video generation device provided by an embodiment of the present invention. For convenience of explanation, only the parts related to the embodiment of the present invention are shown. Referring to Figure 11, the text-video generation device 3 is: An editing module 31 for displaying a text editing page, wherein the text editing page includes an editing module 31 and a text input area. A display module 32 for displaying target text in a text input area in response to a first input command to a text editing page, wherein the target text has a first font state within the text input area, the first font state characterizes the font size and / or line spacing of the target text, and the first font state is determined by the length of the target text, and the display module 32 The system includes a generation module 33 for generating a target video to display the target text in a text input area.

[0060] In one embodiment of the present invention, the display module 32 specifically generates target text in response to a first input command, obtains the total number of characters in the target text, determines a first font state based on the total number of characters and the area size of the text input area, and displays the target text in the text input area based on the first font state.

[0061] In one embodiment of the present invention, the area size includes the horizontal area size and the vertical area size, and when the display module 32 determines the first font state based on the total number of characters and the area size of the text input area, it specifically determines the number of characters per line based on the font width corresponding to the base font size and the horizontal area size, the number of characters per line is characterized by the number of characters that can be displayed in one line of the text input area, the first vertical size is determined based on the number of characters per line and the total number of characters, and the first font state is determined based on the first vertical size and the vertical area size.

[0062] In one embodiment of the present invention, when the display module 32 determines a first font state based on a first vertical size and an area vertical size, it specifically obtains a proportional value between the first vertical size and the area vertical size, and if the proportional value is smaller than a first proportional threshold, it determines a first font state based on the base font size and / or base line spacing, and if the proportional value is larger than the first proportional threshold, it reduces the base font size and / or base line spacing based on the proportional value to obtain a first font state.

[0063] In one embodiment of the present invention, the generation module 33 specifically generates a rendering image containing target text having a first font state based on the target text, determines the video duration based on the length of the target text, and generates a target video based on the video duration and the rendering image.

[0064] In one embodiment of the present invention, before generating a target video for displaying the target text in a text input area, the display module 32 further displays a background image in the text editing page in response to a second input command to the text editing page, and the generation module 33 specifically generates a target video based on the target text in the text input area and the background image.

[0065] In one embodiment of the present invention, the target text further has a second font state, the second font state characterizes the font color of the target text, and when the display module 32 displays a background image in the text editing page in response to a second input command to the text editing page, specifically, in response to the second input command, it matches the target color based on the second font state, where the color difference between the target color and the font color is greater than a color difference threshold, and also obtains a background image whose main color is the target color based on a predetermined gallery, and displays the background image in the text editing page.

[0066] In one embodiment of the present invention, the generation module 33 further acquires background music based on a background image, and when generating a target video to display the target text in a text input area, the generation module 33 specifically generates the target video based on the target text in the text input area and the background music.

[0067] Here, the editing module 31, the display module 32, and the generation module 33 are connected in order. The text video generation device 3 provided by this embodiment can implement the technical solutions of the embodiments of the method described above, and its implementation principle and technical effects are similar, and this embodiment will not be repeated here.

[0068] Figure 12 is a schematic diagram of the configuration of an electronic device provided by an embodiment of the present invention, and as shown in Figure 12, the electronic device 4 is The system comprises a processor 41 and a memory 42 that is communicatively connected to the processor 41. Memory 42 stores computer execution instructions. The processor 41 executes computer execution instructions stored in the memory 42 to realize the text-video generation method shown in the embodiments in Figures 2 to 10.

[0069] Here, the processor 41 and memory 42 are selectively connected via the bus 43.

[0070] Related explanations can be understood by referring to the related explanations and effects corresponding to the steps in the embodiments shown in Figures 2 to 10, and will not be repeated here.

[0071] Embodiments of the present invention provide a computer-readable storage medium in which computer execution instructions are stored, and when the computer execution instructions are executed by a processor, a text-video generation method provided by any embodiment in the embodiments corresponding to Figures 2 to 10 of the present invention is realized.

[0072] Figure 13 is a schematic diagram of the configuration of an electronic device provided by an embodiment of the present invention, and as shown in Figure 13, the electronic device 1300 may be a terminal device or a server. Here, the terminal device is a mobile phone, a notebook computer, a digital broadcast receiver, a personal digital assistant (PDA), a tablet computer (Portable The present invention may include, but is not limited to, mobile devices such as Android devices (PADs), portable media players (PMPs), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. The electronic devices shown in Figure 13 are merely examples and do not limit the functions and scope of use of the embodiments of the present invention.

[0073] As shown in Figure 13, the electronic device 1300 is a read-only memory (Read Only Memory (ROM) 1302 contains programs or random access memory (Random Access Memory) from storage device 1308. The system may include a processing unit (e.g., a central processing unit, a graphical processor, etc.) 1301 capable of performing various appropriate operations and processes based on the program loaded into the Access Memory (RAM) 1303. The RAM 1303 further stores various programs and data necessary for the operation of the electronic device 1300. Processing unit 1301, ROM 1302, and RAM The 1303s are connected to each other via bus 1304. The input / output (I / O) interface 1305 is also connected to bus 1304.

[0074] Typically, input devices 1306 including touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc., and liquid crystal displays (Liquid Devices such as output devices 1307 including a crystal display (LCD), speaker, vibrator, etc., storage devices 1308 including magnetic tape, hard disk, etc., and communication devices 1309 may be connected to the I / O interface 1305. The communication device 1309 can enable the electronic device 1300 to communicate wirelessly or via wired connection to exchange data with other devices. Although the drawings show the electronic device 1300 with various devices, it should be understood that it is not necessary to implement or have all of the shown devices. More or fewer devices may be implemented or have been implemented instead.

[0075] In particular, according to embodiments of the present invention, the process described with reference to the flowchart above may be implemented as a computer software program. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for performing the method shown in the flowchart. In such embodiments, the computer program may be downloaded and installed from a network via a communication device 1309, or installed from a storage device 1308 or ROM 1302. When the computer program is executed by the processing unit 1301, the above-described functions, limited to the methods of embodiments of the present invention, are performed.

[0076] It should be noted that the computer-readable medium described above in the present invention may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the above. The computer-readable storage medium may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media include electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), and erasable programmable read-only memory. Memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (Compact Disc Read-Only) This may include, but is not limited to, memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination described above. In the present invention, a computer-readable storage medium may be a tangible medium containing or storing a program that can be used by the program, instruction execution system, apparatus, or device in combination with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium may also contain data signals propagated in the baseband or as part of a carrier carrying computer-readable program code. Such propagated data signals can take various forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination described above. The computer-readable signal medium may further be any computer-readable medium other than a computer-readable storage medium that transmits, propagates, or transmits a program for use by, or in combination with, an instruction execution system, apparatus, or device. The program code contained in the computer-readable medium can be transmitted using any suitable medium, including, but not limited to, wired, fiber optic cables, RF (radio frequency), or any suitable combination described above.

[0077] The computer-readable medium described above may be included in the electronic device described above, or it may exist separately and not be assembled into the electronic device.

[0078] The computer-readable medium described above contains one or more programs, and when one or more of these programs are executed by the electronic device, the electronic device is made to perform the method shown in the embodiment described above.

[0079] Computer program code for performing the operations of the present invention can be written in one or more programming languages ​​or a combination thereof, and the programming languages ​​mentioned above include object-oriented programming languages ​​such as Java, Smalltalk, and C++, and further include conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code may run entirely on the user's computer, partially on the user's computer, run as a standalone software package, run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or server. In the case of a remote computer, the remote computer may be on a local area network. Network, LAN) or Wide Area Network (Wide The user computer may be connected via any type of network, including an Area Network (WAN), or it may be connected to an external computer (for example, via the Internet using an Internet service provider).

[0080] The flowcharts and block diagrams in the drawings illustrate implementable architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. From this perspective, each box in a flowchart or block diagram may contain one or more executable instructions for implementing a specified logical function and may represent a module, program segment, or part of code. It should also be noted that in some alternative implementations, the functions shown within a box may occur in a different order than shown in the drawings. For example, two boxes shown consecutively may actually be executed substantially in parallel, or, depending on the functions involved, in reverse order. It should also be noted that each box in a block diagram and / or flowchart, and combinations of boxes in a block diagram and / or flowchart, may be implemented in a dedicated hardware-based system that performs the specified function or operation, or in a combination of dedicated hardware and computer instructions.

[0081] The units described as being involved in embodiments of the present invention may be implemented by software or by hardware. In this context, the names of the units do not constitute a limitation of the unit itself in any particular case. For example, the first acquisition unit may be described as "a unit that acquires at least two Internet Protocol addresses."

[0082] The functions described herein may be performed, at least in part, by one or more hardware logic components. For example, non-limiting exemplary types of hardware logic components that may be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standards (ASSPs), systems-on-a-chip (SOCs), and composite programmable logic devices (CPLDs).

[0083] In the context of the present invention, a machine-readable medium may be a tangible medium that contains or can store a program that can be used by an instruction execution system, apparatus, or device in combination with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0084] In a first embodiment, according to one or more embodiments of the present invention, a method for generating text video is provided, the method is: Displaying a text editing page, the text editing page including a text input area; displaying target text in the text input area in response to a first input command to the text editing page, the target text having a first font state within the text input area, the first font state characterizing the font size and / or line spacing of the target text, the first font state being determined by the length of the target text; and generating a target video for displaying the target text within the text input area.

[0085] According to one or more embodiments of the present invention, displaying target text in the text input area in response to a first input command for the text editing page includes generating target text and obtaining the total number of characters in the target text in response to the first input command, determining the first font state based on the total number of characters and the area size of the text input area, and displaying the target text in the text input area based on the first font state.

[0086] According to one or more embodiments of the present invention, the area size includes the horizontal area size and the vertical area size, and determining the first font state based on the total number of characters and the area size of the text input area includes determining the number of characters per line based on the font width corresponding to the base font size and the horizontal area size, wherein the number of characters per line is characterized by the number of characters that can be displayed in one line of the text input area, determining the first vertical size based on the number of characters per line and the total number of characters, and determining the first font state based on the first vertical size and the vertical area size.

[0087] According to one or more embodiments of the present invention, determining the first font state based on the first vertical size and the area vertical size includes obtaining a proportional value between the first vertical size and the area vertical size; determining the first font state based on the base font size and / or base line spacing if the proportional value is smaller than a first proportional threshold; and obtaining the first font state by reducing the base font size and / or base line spacing based on the proportional value if the proportional value is larger than the first proportional threshold.

[0088] According to one or more embodiments of the present invention, generating a target video for displaying target text in the text input area includes generating a rendering image containing the target text having the first font state based on the target text, determining the video duration based on the length of the target text, and generating the target video based on the video duration and the rendering image.

[0089] According to one or more embodiments of the present invention, before generating a target video for displaying the target text in the text input area, a background image is displayed on the text editing page in response to a second input command to the text editing page, and generating a target video for displaying the target text in the text input area includes generating the target video based on the target text in the text input area and the background image.

[0090] According to one or more embodiments of the present invention, the target text further has a second font state, the second font state characterizes the font color of the target text, and in response to a second input command to a text editing page, displaying a background image on the text editing page includes matching the target color based on the second font state in response to the second input command, wherein the color difference between the target color and the font color is greater than a color difference threshold, and obtaining a background image whose main color is the target color based on a predetermined gallery, and displaying the background image on the text editing page.

[0091] According to one or more embodiments of the present invention, further comprising obtaining background music based on the background image, and generating a target video for displaying the target text in the text input area, comprises generating the target video based on the target text in the text input area and the background music.

[0092] In a second embodiment, according to one or more embodiments of the present invention, a text video generation apparatus is provided, the apparatus is An editing module for displaying a text editing page, wherein the text editing page includes an editing module that includes a text input area, A display module for displaying target text in a text input area in response to a first input command to a text editing page, wherein the target text has a first font state within the text input area, the first font state characterizes the font size and / or line spacing of the target text, and the first font state is determined by the length of the target text; The system includes a generation module for generating a target video to display the target text in the text input area.

[0093] According to one or more embodiments of the present invention, the display module specifically generates target text in response to the first input command, obtains the total number of characters in the target text, determines the first font state based on the total number of characters and the area size of the text input area, and displays the target text in the text input area based on the first font state.

[0094] According to one or more embodiments of the present invention, the area size includes a horizontal area size and a vertical area size, and when the display module determines the first font state based on the total number of characters and the area size of the text input area, it specifically determines the number of characters per line based on the font width corresponding to the base font size and the horizontal area size, where the number of characters per line is characterized by the number of characters that can be displayed in one line of the text input area, and also determines the first vertical size based on the number of characters per line and the total number of characters, and determines the first font state based on the first vertical size and the vertical area size.

[0095] According to one or more embodiments of the present invention, when the display module determines the first font state based on the first vertical size and the area vertical size, it specifically obtains a proportional value between the first vertical size and the area vertical size, determines the first font state based on the base font size and / or base line spacing if the proportional value is smaller than a first proportional threshold, and obtains the first font state by reducing the base font size and / or base line spacing based on the proportional value if the proportional value is larger than the first proportional threshold.

[0096] According to one or more embodiments of the present invention, the generation module specifically generates a rendering image containing the target text having the first font state based on the target text, determines the video duration based on the length of the target text, and generates the target video based on the video duration and the rendering image.

[0097] According to one or more embodiments of the present invention, before generating a target video for displaying the target text in the text input area, the display module further displays a background image on the text editing page in response to a second input command to the text editing page, and the generation module specifically generates the target video based on the target text in the text input area and the background image.

[0098] According to one or more embodiments of the present invention, the target text further has a second font state, the second font state characterizes the font color of the target text, and the display module, in response to a second input command to the text editing page, displays a background image on the text editing page, specifically matching the target color based on the second font state in response to the second input command, where the color difference between the target color and the font color is greater than a color difference threshold, and also obtains a background image whose main color is the target color based on a predetermined gallery, and displays the background image on the text editing page.

[0099] According to one or more embodiments of the present invention, the generation module further acquires background music based on the background image, and when generating a target video to display the target text in the text input area, the generation module specifically generates the target video based on the target text in the text input area and the background music.

[0100] In a third embodiment, according to one or more embodiments of the present invention, an electronic device is provided, the electronic device comprising a processor and a memory communicably connected to the processor, The aforementioned memory stores computer execution instructions, The processor implements the text-video generation method described in the first embodiment and various possible designs of the first embodiment by executing computer execution instructions stored in the memory.

[0101] In a fourth embodiment, one or more embodiments of the present invention provide a computer-readable storage medium in which computer execution instructions are stored, and when the computer execution instructions are executed by a processor, the text-video generation method described in the first embodiment and various possible designs of the first embodiment described above is realized.

[0102] In a fifth embodiment, an embodiment of the present invention provides a computer program product including a computer program, wherein the text-video generation method described in the first embodiment and various possible designs of the first embodiment is realized when the computer program is executed by a processor.

[0103] The above description represents preferred embodiments of the present invention and merely describes the applicable technical principles. Those skilled in the art should understand that the scope of the invention as described herein is not limited to technical solutions formed by specific combinations of the above technical features, but also includes other technical solutions formed by any combination of the above technical features or equivalent features without departing from the concept of the invention. For example, it should be understood that this also includes technical solutions formed by switching between the above features and similar functional technical features disclosed herein (but not limited to these).

[0104] Furthermore, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed sequentially in a specific order or sequence shown. Multitasking and parallel processing may be advantageous in certain environments. Similarly, while some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the invention. Certain features described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0105] While this subject matter has been described in terms specific to the structural features and / or the logical operation of the method, it should be understood that the subject matter limited in the attached claims is not necessarily limited to the specific features or operations described above. Conversely, the specific features and operations described above are merely illustrative forms of realizing the claims.

Claims

1. Displaying a text editing page, wherein the text editing page includes a text input area, In response to a first input command for a text editing page, a target text is displayed in the text input area, wherein the target text has a first font state within the text input area, the first font state characterizes the font size and / or line spacing of the target text, the first font state is determined by the length of the target text, and in response to the first input command, the target text is generated, the total number of characters in the target text is obtained, the first font state is determined based on the total number of characters and the area size of the text input area, the area size includes the horizontal area size and the vertical area size, and the font width corresponds to the base font size and Based on the horizontal size of the area, the number of characters per line is determined, the number of characters per line is characterized by the number of characters that can be displayed in one line of the text input area, a first vertical size is determined based on the number of characters per line and the total number of characters, a proportional value is obtained between the first vertical size and the vertical size of the area, if the proportional value is smaller than a first proportional threshold, the first font state is determined based on the base font size and / or base line spacing, if the proportional value is larger than the first proportional threshold, the base font size is reduced and / or the base line spacing is reduced based on the proportional value to obtain the first font state, and the target text is displayed in the text input area based on the first font state. To generate a target video for displaying the target text in the text input area, Based on the target text, a rendering image is generated that includes the target text having the first font state. The video length is determined based on the length of the target text, The process includes generating the target video based on the video duration and the rendered image, A method for generating text-to-video, characterized by the features described herein.

2. Before generating a target video to display the target text in the aforementioned text input area, The system further includes displaying a background image on a text editing page in response to a second input command to the text editing page, To generate a target video for displaying the target text in the aforementioned text input area, The process includes generating the target video based on the target text in the text input area and the background image. The text video generation method according to feature 1.

3. The target text further has a second font state, the second font state characterizes the font color of the target text, Displaying a background image on the text editing page in response to a second input command to the text editing page is: In response to the second input command, the target color is matched based on the second font state, wherein the color difference between the target color and the font color is greater than the color difference threshold. This includes obtaining a background image whose main color is the target color based on a predetermined gallery, and displaying the background image on the text editing page. The text video generation method according to feature 2.

4. The process further includes obtaining background music based on the aforementioned background image. To generate a target video for displaying the target text in the aforementioned text input area, The process includes generating the target video based on the target text in the text input area and the background music. The text video generation method according to feature 2.

5. An editing module for displaying a text editing page, wherein the text editing page includes an editing module that includes a text input area, A display module for displaying target text in a text input area in response to a first input command to a text editing page, wherein the target text has a first font state within the text input area, the first font state characterizes the font size and / or line spacing of the target text, the first font state is determined by the length of the target text, and in response to the first input command, generates the target text, obtains the total number of characters in the target text, determines the first font state based on the total number of characters and the area size of the text input area, the area size includes the horizontal area size and the vertical area size, and the font width corresponds to the base font size. A display module that determines the number of characters per line based on the horizontal size of the area, the number of characters per line characterizes the number of characters that can be displayed in one line of the text input area, determines a first vertical size based on the number of characters per line and the total number of characters, obtains a proportional value between the first vertical size and the vertical size of the area, determines a first font state based on the base font size and / or base line spacing if the proportional value is smaller than a first proportional threshold, reduces the base font size and / or base line spacing based on the proportional value to obtain a first font state, and displays the target text in the text input area based on the first font state, The system comprises a generation module for generating a target video for displaying the target text in the text input area, The aforementioned generation module further, Based on the target text, a rendering image is generated that includes the target text having the first font state. Based on the length of the target text, the video length is determined. This is for generating the target video based on the video duration and the rendered image. A text-to-video generation device characterized by the following features.

6. The system comprises a processor and a memory that is communicably connected to the processor, The aforementioned memory stores computer execution instructions, The processor implements the text video generation method according to any one of claims 1 to 4 by executing computer execution instructions stored in the memory. An electronic device characterized by the following features.

7. Computer execution instructions are stored, and when the computer execution instructions are executed by the processor, the text video generation method described in any one of claims 1 to 4 is realized. A computer-readable storage medium characterized by the following features.

8. A computer program wherein, when the computer program is executed by a processor, the text-video generation method described in any one of claims 1 to 4 is realized. Computer program.

Images