Text generation method and device, equipment, medium and program product

Abstract

The embodiment of the invention provides a text generation method and device, equipment, a medium and a program product. The method comprises the following steps: displaying an original text and a first control in a first page; in response to a trigger operation of the first control, displaying a second page, the second page comprising at least one candidate title corresponding to the original text; in response to a trigger operation of a target title in the at least one candidate title, displaying content key points of at least one hierarchy of the target title, the content key points of the at least one hierarchy representing nodes of different depths of a hierarchical stacking structure corresponding to the target title; and in response to a selection operation of the candidate titles and the content key points, generating a target text based on the selected candidate titles and the selected content key points. According to the embodiment of the invention, the text meeting the expectation of the user can be efficiently and accurately generated, and the problem that the text meeting the expectation is difficult to accurately generate based on creative inspiration is solved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to computer technology, and in particular to a text generation method, apparatus, device, medium, and program product. Background Art

[0002] With the advancement of computer technology, more and more users are using generative applications to create content. For example, these applications can expand user-entered story settings into complete story text. However, when users only have creative inspiration, these applications struggle to accurately generate text that meets expectations. Summary of the Invention

[0003] The embodiments of the present disclosure provide a text generation method, apparatus, device, medium, and program product, which can optimize a text generation scheme and generate a target text that meets expectations.

[0004] In a first aspect, an embodiment of the present disclosure provides a text generation method, comprising:

[0005] Display the original text and the first control on the first page;

[0006] In response to a triggering operation of the first control, displaying a second page, wherein the second page includes at least one candidate title corresponding to the original text;

[0007] In response to a triggering operation of a target title among the at least one candidate title, displaying at least one level of content highlights of the target title, wherein the at least one level of content highlights represents nodes at different depths of a hierarchical stacking structure corresponding to the target title;

[0008] In response to the selection operation of the candidate title and content main point, a target text is generated based on the selected candidate title and content main point.

[0009] In a second aspect, the present disclosure also provides a text generation device, including:

[0010] A first display module, configured to display the original text and the first control on the first page;

[0011] a second display module, configured to display a second page in response to a triggering operation of the first control, wherein the second page includes at least one candidate title corresponding to the original text;

[0012] A third display module is configured to display, in response to a triggering operation of a target title among the at least one candidate title, at least one level of content highlights of the target title, wherein the at least one level of content highlights represents nodes at different depths of a hierarchical stacking structure corresponding to the target title;

[0013] The text generation module is used to generate a target text based on the selected candidate title and content main point in response to the selection operation of the candidate title and content main point.

[0014] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0015] one or more processors;

[0016] a storage device for storing one or more programs,

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the text generation method as described in any embodiment of the present disclosure.

[0018] In a fourth aspect, an embodiment of the present disclosure further provides a storage medium comprising computer-executable instructions, which, when executed by a computer processor, are used to execute the text generation method as described in any embodiment of the present disclosure.

[0019] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the text generation method as described in any embodiment of the present disclosure.

[0020] The embodiment of the present disclosure provides a text generation method, which displays original text and a first control on a first page, displays a second page in response to a triggering operation of the first control, and displays at least one level of content highlights extending from the target title by triggering a target title from at least one candidate title, so as to realize displaying the candidate titles and content highlights in a hierarchical stacking structure on the second page, thereby achieving a visualization effect of the divergent results of the original text, and facilitating the user to select content that meets expectations from the candidate titles and content highlights. In response to the selection operation of the candidate titles and content highlights, a target text is generated based on the selected candidate titles and content highlights. The embodiment of the present disclosure generates at least one candidate title corresponding to the original text, selects a target title from at least one candidate title, diverges at least one level of content highlights based on the target title, and then generates a target text based on the selected candidate title and content highlights. This can efficiently and accurately generate text that meets user expectations, thereby solving the problem that it is difficult to accurately generate text that meets expectations based on creative inspiration. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0022] Figure 1 A flowchart of a text generation method provided by an embodiment of the present disclosure;

[0023] Figure 2 A schematic diagram of a second page provided by an embodiment of the present disclosure;

[0024] Figure 3 A schematic diagram of another second page provided by an embodiment of the present disclosure;

[0025] Figure 4 A flowchart of another text generation method provided by an embodiment of the present disclosure;

[0026] Figure 5 A schematic diagram of another second page provided by an embodiment of the present disclosure;

[0027] Figure 6 A tree structure diagram from target title to content points provided by an embodiment of the present disclosure;

[0028] Figure 7 A flowchart of another text generation method provided by an embodiment of the present disclosure;

[0029] Figure 8 A schematic diagram of another second page provided by an embodiment of the present disclosure;

[0030] Figure 9 A schematic diagram of the structure of a text generation device provided by an embodiment of the present disclosure;

[0031] Figure 10 A schematic structural diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0033] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0034] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0035] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0036] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0037] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0038] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0039] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0040] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0041] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0042] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0043] Figure 1 This is a flow chart of a text generation method provided in an embodiment of the present disclosure. The embodiment of the present disclosure is applicable to situations where a target text is generated based on a user's creative inspiration. The method can be executed by a text generation device, which can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a PC or a server, etc.

[0044] like Figure 1 As shown, the method includes:

[0045] S110: Display the original text and the first control on the first page.

[0046] The first page may be an interactive page of a generation-type application. For example, the first page may be a first-level page corresponding to a preset tag item of the generation-type application. The generation-type application may be a client application, a web application, or a mini-program.

[0047] The first control is used to trigger a title generation event in the first page. For example, in response to the triggering operation of the first control, a title generation event in the first page is triggered to generate at least one candidate title based on the original text. The original text represents the user's creative inspiration. The original text can be input through the text input control, and the original text is displayed on the first page. Alternatively, the voice information of the original text can be input through the voice input control, the original text is obtained through voice-to-text processing, and the original text is displayed on the first page. Alternatively, recommended information can be displayed on the first page for the user to select the recommended information as the original text. The candidate title is a title that meets the user's creative inspiration.

[0048] Exemplarily, displaying the original text and the first control on the first page includes: displaying a text input box and the first control on the first page, and displaying the original text in the text input box in response to a text input operation in the text input box.

[0049] For example, a text input box and a first control are displayed on a first page, and original text is input through the text input box. The original text may include a topic and / or an opinion, etc. Clicking the first control triggers a title generation event for generating at least one candidate title based on the original text.

[0050] S120: In response to a triggering operation of the first control, display a second page, where the second page includes at least one candidate title corresponding to the original text.

[0051] The second page may be a secondary page corresponding to a preset tag item. In response to a triggering operation of a first control in the first page, the page jumps from the first page to the second page. Optionally, the second page includes a first area and a second area. The first area is used to display a tree structure of original text, candidate titles, and content highlights. The second area is used to display selected candidate titles and selected content highlights. The second area may also include a generation control. The generation control is used to trigger a text generation event.

[0052] Exemplarily, in response to the triggering operation of the first control, at least one candidate title corresponding to the original text is generated, and the original text and at least one candidate title are displayed in the second page, wherein the original text is a root node and the at least one candidate title is a child node.

[0053] Optionally, generating at least one candidate title corresponding to the original text includes: generating a first search term based on the original text, and determining a first search result based on the first search term; obtaining a reference title from a preset title library based on the original text; obtaining video titles of historically posted videos corresponding to the account; generating first prompt information based on the first search result, the reference title, the video title, and a first prompt template; inputting the first prompt information into a preset natural language processing model, and obtaining at least one candidate title output by the preset natural language processing model.

[0054] The first search term is used to retrieve webpage content related to the original text. Search term prompt information can be generated based on the original text and a preset prompt template. The preset prompt template includes predefined information related to search term rewriting. The search term prompt information is input into a preset natural language processing model to obtain a first search term output by the preset natural language processing model. A preset search interface is invoked based on the first search term to send the first search term to a search engine corresponding to the preset search interface, and a first search result is returned by the search engine. The first search result represents webpage content related to the original text. A preset title library is a library of video titles that meet preset criteria. Based on the original text, n relevant titles can be searched from the preset title library as reference titles, where n is a positive integer. Video titles of previously posted videos are obtained from the user's account. A first prompt template is obtained, and the first search result, n reference titles, and video title are entered into the first prompt template to obtain first prompt information. The first prompt information is input into the preset natural language processing model to guide the preset natural language processing model to generate candidate titles that are more in line with user expectations and more comprehensive, and at least one candidate title output by the preset natural language processing model is obtained.

[0055] Figure 2 This is a schematic diagram of a second page provided by an embodiment of the present disclosure. Figure 2 As shown, the original text 220 and the first control 230 are displayed on the first page 210. In response to the triggering operation of the first control 230, the second page 240 is displayed. The second page 240 includes a first area 241 and a second area 242. The first area 241 includes the original text 220 and a display control 250 corresponding to at least one candidate title. The second control 260 and the third control 270 are displayed in the position corresponding to each candidate title in the display control 250. The second control 260 is used to trigger a content generation event. The third control 270 is used to trigger a content selection event. The bottom of the display control 250 also includes a fourth control 280, which is used to trigger the generation event of the candidate title or content key point at the same level. The display controls 250 are connected by line segments. The second area 242 includes the selected candidate title, the selected candidate content key point and the generation control 290.

[0056] Optionally, a fourth control is displayed at the bottom of the display area corresponding to the candidate title. The fourth control is used to trigger the generation of a candidate title at the same level. For example, in response to a triggering operation of the fourth control within the second display control corresponding to at least one candidate title, a candidate title at the same level as the at least one candidate title is generated based on the original text. The second display control is expanded, and the newly generated candidate title is added to the expanded second display control.

[0057] Figure 3 This is a schematic diagram of another second page provided by an embodiment of the present disclosure. Figure 3 As shown, a second display control 320 displaying at least one candidate title is displayed on a second page 310, and a fourth control 330 is displayed at the bottom of the second display control 320. In response to a triggering operation of the fourth control 330, at least one candidate title at the same level as the original candidate title is generated based on the original text. The second display control 320 is expanded, and the newly generated candidate title is displayed within the expanded second display control 320.

[0058] S130: In response to a triggering operation of a target title among the at least one candidate title, display content highlights of at least one level of the target title.

[0059] The target title is the candidate title that is triggered among the at least one candidate title. The at least one level of content points represents nodes at different depths of the hierarchical stacking structure corresponding to the target title. For example, in response to the triggering operation of the target title, at least one content point is extended from the target title. Alternatively, in response to the triggering operation of the target content point among the at least one content point, at least one content point is extended from the target content point. Similarly, by extending layer by layer, at least one level of content points of the target title can be obtained.

[0060] Exemplarily, in response to a triggering operation on any candidate title among at least one candidate title, the triggered candidate title is determined as the target title. For example, in response to a triggering operation on a second control corresponding to any candidate title among at least one candidate title, the candidate title corresponding to the triggered second control is determined as the target title. Optionally, a content key point generation button corresponding to at least one candidate title is displayed on the second page. In response to selecting at least one candidate title and clicking the content key point generation button, the selected at least one candidate title is used as the target title, and content key points extending from the target title are generated.

[0061] A preset search engine is queried based on the target title to obtain search results. Preset prompt information is generated based on the target title, search results, target title hierarchy, and a preset prompt template. The preset prompt information is input into a preset natural language processing model, which is then guided by the preset prompt information to generate rich content highlights.

[0062] Optionally, new content points can be further generated based on the content points. For example, in response to a triggering operation on any of the at least one content point, the triggered content point is determined as the target content point. A preset search engine is queried based on the target content point and the target title to obtain retrieval results. Preset prompt information is generated based on the target content point, the target title, the retrieval results, the path from the target title to the target content point, the hierarchy of the target content point, and a preset prompt template. The preset prompt information is input into a preset natural language processing model, which is then guided by the preset prompt information to generate content points at the next level of the target content point, thereby enriching and optimizing the content points.

[0063] It should be noted that the embodiment of the present disclosure does not specifically limit the method for determining the target title and target content highlights.

[0064] Optionally, a fourth control is displayed at the bottom of the display area corresponding to the content key point. The fourth control is used to trigger the generation event of a content key point at the same level. For example, in response to the triggering operation of the fourth control, a content key point at the same level as the content key point corresponding to the triggered fourth control is generated. The display area corresponding to the content key point is expanded, and the newly generated content key point is added to the expanded display area.

[0065] S140: In response to the selection operation of the candidate title and content main point, generate a target text based on the selected candidate title and content main point.

[0066] The target text is generated based on the candidate titles and key points of the original text. For example, the target text can be a video script, product copy, or speech. Optionally, the target text can be exported or copied. Optionally, subtitles can be generated for the video by intelligently segmenting the video script. Based on the subtitles, a video description and dubbing can be generated. Based on the description, video frames can be generated. Then, a video is generated based on the video frames, subtitles, dubbing, transitions, special effects, and filters.

[0067] Exemplarily, in response to a click operation on a third control corresponding to a candidate title and content key point, the candidate title and content key point corresponding to the clicked third control are determined as the selected candidate title and content key point. Alternatively, a confirmation button corresponding to at least one candidate title is displayed on the second page. The second page also displays confirmation buttons corresponding to content key points at each level. In response to selecting at least one candidate title and clicking the confirmation button, the at least one candidate title corresponding to the selection operation is determined as the selected candidate title. For content key points at any level, in response to selecting a content key point at the current level and clicking the confirmation button corresponding to the content key point at the current level, the content key point at the current level corresponding to the selection operation is determined as the selected content key point.

[0068] In some embodiments, for accounts with no video creation history, a video script is generated based on selected candidate titles, content highlights, and preset configuration information. Thus, a target video can be generated based on the video script. The preset configuration information may include requirements such as style and / or duration.

[0069] Optionally, for accounts with a video creation record, m historically released videos related to the selected title are obtained, and reference texts are determined based on the m historically released videos. For example, text information of the m historically released videos can be extracted to obtain reference texts. Alternatively, the audio data of the m historically released videos can be converted into text, etc. A video script is generated based on the selected candidate title, content highlights, reference texts, and preset configuration information. The disclosed embodiment realizes the recognition of text style through the reference text corresponding to the historically released videos, thereby imitating the target text that conforms to the user's text style.

[0070] The technical solution of the embodiment of the present disclosure is to display the original text and the first control on the first page, and display the second page in response to the triggering operation of the first control, and display the target title from at least one candidate title, and display at least one level of content points extending from the target title, so as to realize the display of the candidate titles and content points in a hierarchical stacking structure on the second page, thereby achieving a visualization effect of the divergent results of the original text, and facilitating the user to select the content that meets the expectations from the candidate titles and content points. In response to the selection operation of the candidate titles and content points, the target text is generated based on the selected candidate titles and content points. The embodiment of the present disclosure generates at least one candidate title corresponding to the original text, and then selects the target title from at least one candidate title, diverges at least one level of content points based on the target title, and then generates the target text based on the selected candidate title and content points. It can efficiently and accurately generate text that meets the user's expectations, and solve the problem that it is difficult to accurately generate text that meets expectations based on creative inspiration.

[0071] Figure 4 A flow chart of another text generation method provided in an embodiment of the present disclosure. Based on the above embodiments, the embodiment of the present disclosure specifically defines displaying the content highlights of at least one level of the target title in response to a triggering operation of the target title in the at least one candidate title.

[0072] like Figure 4 As shown, the method includes:

[0073] S410: Display the original text and the first control on the first page.

[0074] S420: In response to the triggering operation of the first control, display a second page, where the second page includes at least one candidate title corresponding to the original text.

[0075] S430: In response to a triggering operation of a second control corresponding to the target title, generate a content main point corresponding to the target title, and display the second control at a position corresponding to the content main point.

[0076] The content point corresponding to the target title is a child node of the target title. A second control is displayed at a position corresponding to each candidate title, and the second control is used to trigger a generation event of the content point. The candidate title corresponding to the triggered second control is determined as the target title.

[0077] Figure 5 This is a schematic diagram of another second page provided by an embodiment of the present disclosure. Figure 5As shown, the original text and at least one candidate title are displayed through a display control 510. A second control 520 is displayed at a position corresponding to each candidate title. In response to a triggering operation of the second control 520 for a target title (e.g., zzzzz), a new display control 510 is extended from the target title. At least one content point corresponding to the target title is displayed in the new display control 510. The second control 520 is displayed at a position corresponding to each content point within the display control 510. In response to a triggering operation of the second control 520 for a target content point (e.g., bbbb) among the at least one content point, a new display control 510 is extended from the target content point. At least one content point corresponding to the target content point is displayed in the new display control 510.

[0078] In the embodiment of the present disclosure, multiple levels of content highlights can be extended from the target title. The tree structure corresponding to the target title is taken as an example to illustrate the process of generating content highlights. Figure 6 This is a tree structure diagram from target title to content points provided by the embodiment of the present disclosure. Figure 6 As shown, the target title is a node with a depth of 1, and three levels of content points extend from the target title, represented as nodes with depths of 2, 3, and 4.

[0079] Exemplarily, generating the key points corresponding to the target title includes: generating a second search term based on the target title, determining a second search result based on the second search term; generating second prompt information based on the target title, the second search result, a hierarchy of the target title, and a second prompt information template; inputting the second prompt information into a preset natural language processing model to obtain the key points output by the preset natural language processing model.

[0080] The second search term is used to retrieve web page content that is directly and indirectly related to the target title. The second search results are web page content that is directly and indirectly related to the target title. The web page content retrieved by the second search term generated based on the target title is directly related to the target title. The web page content retrieved by the second search term generated based on the content highlights corresponding to the target title is indirectly related to the target title. The hierarchy of the target title represents the depth of the target title in the tree structure. The second prompt information template includes definition information and thinking direction related to the data drill-down task. The second prompt information template includes placeholder information corresponding to information such as the target content highlights, target title, the path from the target title to the target content highlights, the second search results, and the hierarchy. The target content highlights, target title, the path from the target title to the target content highlights, the second search results, and the hierarchy are filled into the second prompt information template to obtain the second prompt information. The second prompt information template is used to guide the preset natural language generation model to generate content highlights that are relevant to the target title and have information gain.

[0081] For example, search term prompt information can be generated based on the target title and a preset prompt template. The preset prompt template includes, among other things, predefined information related to rewriting the search term. Based on the preset prompt template, the target title is rewritten into a natural language description to obtain the search term prompt information. The search term prompt information is input into a preset natural language processing model to obtain a second search term output by the preset natural language processing model. A preset search interface is called based on the second search term to send the second search term to the search engine corresponding to the preset search result, thereby obtaining a second search result returned by the search engine.

[0082] If a content key point corresponding to a target title needs to be generated, the current content key point is empty, and the path from the target title to the target content key point is empty. The target title, the second search result, and the depth of the target title are entered into a second prompt information template to generate second prompt information. The second prompt information is input into a preset natural language processing model to obtain at least one content key point output by the preset natural language processing model. The at least one content key point derived from the target title is displayed on the second page.

[0083] As the drill-down depth increases, the granularity of content highlights gradually decreases. To allow the pre-set natural language processing model to perceive this change in granularity, target examples are needed to control the granularity of the content highlights generated by the model. Using target examples of corresponding depths at different drill-down depths can significantly enhance the model's granular control over content highlights. A pre-set example library can be pre-built. This library includes prompt information examples at different levels. High-quality video scripts can be manually annotated to break down prompt information examples at different levels, and online searches can be used to supplement reference information for the prompt information examples. Reference information includes online search results.

[0084] Optionally, a candidate sample set in a preset sample library is determined based on the hierarchy of the target title. The target sample corresponding to the target title in the candidate sample set is obtained. For example, prompt information samples with a depth of 1 are selected from the preset sample library to form a candidate sample set. Then, based on the semantics of the target title, a target sample with similar semantics is searched from the candidate sample set. The second prompt information is generated based on the target title, the hierarchy of the target body, the second retrieval result, the target sample and the second prompt information template. The second prompt information is input into a preset natural language processing model, and the preset natural language processing model is guided by the second prompt information to generate content points related to the target title with information gain, and the content points output by the preset natural language processing model are obtained. The content points extended from the target title are displayed on the second page, and the second control is displayed at the position corresponding to the content points.

[0085] S440: In response to a triggering operation of a second control corresponding to a target content point in content points of a current level, generate content points of a next level to the target content point, and display the second control at a position corresponding to the content points of the next level.

[0086] Among them, the content points of the next level are child nodes of the target content points. In response to the triggering operation of the second control corresponding to any content point in the content points of the current level, the content point corresponding to the triggered second control is used as the target content point. The content points of the next level of the target content point are generated, and the content points of the next level extending from the target content point are displayed on the second page. The second control is displayed at the position corresponding to the content points of the next level. It can be understood that in response to the triggering operation of the second control corresponding to the content points of the next level, the content points corresponding to the triggered second control are used as the new target content point, and the content points of the next level are generated in a similar manner. By analogy, content points of different levels of the target title can be obtained.

[0087] Exemplarily, generating a content point at a next-level level below the target content point includes: generating a second search term based on the target title and content points on the path from the target title to the target content point; and determining a second search result based on the second search term. Generating second prompt information based on the target content point, the target title, the current level, the path from the target title to the target content point, the second search result, and a second prompt information template. Inputting the second prompt information into a preset natural language processing model to obtain the content point at the next level output by the preset natural language processing model.

[0088] The path from the target title to the target content main point represents the path between the node corresponding to the target title and the node corresponding to the target content main point. Figure 6 The target title → content point A → content point K in the data can represent the path from the target title to the content point B. In the data drill-down task, as the drill-down depth increases, the finer the granularity of the content points, the stronger the dependence on online retrieval. However, as the drill-down depth increases, the branches become more numerous, and the necessary context or subject may be lacking during retrieval, resulting in the inability to retrieve accurate retrieval results. In order to solve this problem, it is necessary to include the progressive information from the target title to the target content points in the second search term. For example, based on the target title, all content points and preset prompt template on the path from the target title to the target content points, generate search term prompt information, input the search term prompt information into the preset natural language processing model, and obtain the second search term output by the preset natural language processing model. Among them, the preset prompt template includes placeholder information for the target title and content points, and the search term prompt information is obtained by filling the target title and content points into the preset prompt template.

[0089] A preset search interface is called to send the second search term to the preset search engine, and a second search result corresponding to the second search term is obtained from the preset search engine. The target content key point, target title, depth of the target content key point, path from the target title to the target content key point, and the second search result are populated into a second prompt information template to obtain second prompt information. The second prompt information is input into a preset natural language processing model, and the preset natural language processing model is guided by the second prompt information to generate a next-level content key point associated with the target title and having information gain, and the next-level content key point output by the preset natural language processing model is obtained.

[0090] Optionally, generating the second prompt information based on the target content point, target title, current level, path from the target title to the target content point, second search results, and second prompt information template includes: determining a candidate sample set in a preset sample library based on the level of the target content point, wherein the preset sample library includes prompt information samples at different levels; obtaining a target sample from the candidate sample set corresponding to the target content point; and generating the second prompt information based on the target content point, target title, current level, path from the target title to the target content point, second search results, target sample, and second prompt information template.

[0091] S450: In response to the selection operation of the candidate title and content main point, generate a target text based on the selected candidate title and content main point.

[0092] The technical solution of the disclosed embodiment generates a second search term based on the target title and content key points along the path from the target title to the target content key points in response to a triggering operation of a second control corresponding to the target content key points, and determines a second search result based on the second search term. This generates progressive information from the target title to the target content key points, thereby avoiding the problem of inaccurate search results caused by the loss of necessary information as the drill-down depth increases, thereby improving the accuracy of the search results. By obtaining a target example from a preset example library based on the hierarchy and semantics of the target content key points, generating a second prompt information based on the target example, and inputting the second prompt information into a preset natural language processing model, the granularity of the content key points generated by the preset natural language processing model can be controlled, thereby avoiding the problem of non-convergence of the model generation results.

[0093] Figure 7 This is a flow chart of another text generation method provided by an embodiment of the present disclosure. Based on the above embodiments, the embodiment of the present disclosure specifically defines generating a target text based on the selected candidate title and content main points in response to the selection operation of the candidate title and content main points.

[0094] like Figure 7As shown, the method includes:

[0095] S710: Display the original text and the first control on the first page.

[0096] S720: In response to the triggering operation of the first control, display a second page, where the second page includes at least one candidate title corresponding to the original text.

[0097] S730. In response to a triggering operation of a target title among the at least one candidate title, display at least one level of content highlights of the target title, wherein the at least one level of content highlights represents nodes of different depths of a hierarchical stacking structure corresponding to the target title.

[0098] S740: Display the generated control and the third control corresponding to the candidate title and content highlights on the second page.

[0099] S750: In response to a triggering operation of a third control corresponding to the candidate title and content main point, display the selected candidate title and content main point.

[0100] Figure 8 This is a schematic diagram of another second page provided by an embodiment of the present disclosure. Figure 8 As shown, on the second page 810, original text 820, at least one candidate title 830, at least one level of content highlights 840, and a generation control 850 are displayed. A third control 860 is displayed in a location corresponding to the candidate title. A third control 860 is displayed in a location corresponding to the content highlights. In response to a triggering operation on the third control 860 corresponding to the candidate title 830, a selected candidate title is determined. In response to a triggering operation on the third control 860 corresponding to the content highlights 840, a selected content highlight is determined. The selected candidate title and content highlights are displayed on the second page 810.

[0101] S760: In response to the triggering operation of the generation control, generate the target text based on the selected candidate title and content highlights.

[0102] Exemplarily, in response to a triggering operation of a generation control, a third prompt message is generated based on the selected candidate title, the selected content key points, the configuration information, and the third prompt template, and the third prompt message is input into a preset natural language processing model to obtain a target text output by the natural language processing model.

[0103] The third prompt information includes predefined information related to text generation. For example, the third prompt information includes a title, key points, configuration information, and placeholder information for reference text. The selected candidate title, key points, and configuration information are input into the third prompt template to generate the third prompt information. The third prompt information is then input into a preset natural language processing model to obtain the target text output by the preset natural language processing model.

[0104] Optionally, generating the third prompt information based on the selected candidate title, the selected content highlights, the configuration information, and the third prompt template includes: determining a reference text based on historically published videos corresponding to the account. Generating the third prompt information based on the selected candidate title, the selected content highlights, the configuration information, the reference text, and the third prompt template.

[0105] If the user has previously published a video work, reference text can also be generated based on the historically published videos to facilitate the generation of target text by imitating the text style. For example, in response to the triggering operation of the generation control, the historically published videos corresponding to the account are obtained. Reference videos related to the selected candidate title in the historically published videos are obtained, and the text information in the reference videos is extracted to obtain the reference text. The third prompt information is generated based on the selected candidate title, the selected content points, the configuration information, the reference text, and the third prompt template. The third prompt information is input into the preset natural language processing model to obtain the target text output by the preset natural language processing model.

[0106] The technical solution of the disclosed embodiment achieves content point recommendation based on the original text by generating candidate titles based on the original text and then generating at least one level of content points based on the target title among the candidate titles, thereby facilitating user selection of candidate titles and content points to generate the target text. Before generating the target text, configuration information input by the user can also be obtained, and under the guidance of the configuration information, a target text that better meets the expectations can be generated. Reference text can also be generated based on the historically published videos associated with the account, facilitating the generation of target text by imitating the text style of the reference text.

[0107] Figure 9 This is a structural diagram of a text generation device provided in an embodiment of the present disclosure. The device can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, PC or server, etc.

[0108] like Figure 9 As shown, the apparatus includes: a first display module 910 , a second display module 920 , a third display module 930 and a text generation module 940 .

[0109] A first display module 910, configured to display the original text and the first control on the first page;

[0110] A second display module 920 is configured to display a second page in response to a triggering operation of the first control, where the second page includes at least one candidate title corresponding to the original text;

[0111] A third display module 930 is configured to display, in response to a triggering operation of a target title among the at least one candidate title, at least one level of content highlights of the target title, wherein the at least one level of content highlights represents nodes at different depths of a hierarchical stacking structure corresponding to the target title;

[0112] The text generation module 940 is configured to generate a target text based on the selected candidate title and content main point in response to the selection operation of the candidate title and content main point.

[0113] Optionally, the first display module 910 is specifically configured to:

[0114] Displaying a text input box and the first control on the first page;

[0115] In response to a text input operation in the text input box, the original text is displayed in the text input box.

[0116] Optionally, the second display module 920 is specifically configured to:

[0117] In response to the triggering operation of the first control, at least one candidate title corresponding to the original text is generated, and the original text and at least one candidate title are displayed in the second page, wherein the original text is a root node and the at least one candidate title is a child node.

[0118] Optionally, generating at least one candidate title corresponding to the original text includes:

[0119] generating a first search term according to the original text, and determining a first search result based on the first search term;

[0120] Obtaining a reference title from a preset title library according to the original text;

[0121] Get the video titles of the historically released videos corresponding to the account;

[0122] generating first prompt information based on the first search result, the reference title, the video title, and the first prompt template;

[0123] The first prompt information is input into a preset natural language processing model to obtain at least one candidate title output by the preset natural language processing model.

[0124] Optionally, a second control is displayed at a position corresponding to each candidate title, and the second control is used to trigger a generation event of a content key point;

[0125] The third display module 930 is specifically used for:

[0126] In response to a triggering operation of a second control corresponding to the target title, generating a content key point corresponding to the target title, and displaying the second control at a position corresponding to the content key point, wherein the content key point corresponding to the target title is a child node of the target title;

[0127] In response to the triggering operation of the second control corresponding to the target content point in the content points of the current level, the content points of the next level are generated for the target content point, and the second control is displayed at the position corresponding to the content points of the next level, wherein the content points of the next level are child nodes of the target content point.

[0128] Optionally, generating the content highlights corresponding to the target title includes:

[0129] generating a second search term according to the target title, and determining a second search result based on the second search term;

[0130] generating second prompt information based on the target title, the second search result, the level of the target title, and the second prompt information template;

[0131] The second prompt information is input into a preset natural language processing model to obtain the content key points output by the preset natural language processing model.

[0132] Optionally, generating the next-level content points of the target content points includes:

[0133] generating a second search term based on the target title and the content key points on the path from the target title to the target content key points, and determining a second search result based on the second search term;

[0134] generating second prompt information based on the target content main point, the target title, the current level, the path from the target title to the target content main point, the second search result, and the second prompt information template;

[0135] The second prompt information is input into a preset natural language processing model to obtain the next level of content highlights output by the preset natural language processing model.

[0136] Optionally, generating the second prompt information based on the target content main point, the target title, the current level, the path from the target title to the target content main point, the second search result, and the second prompt information template includes:

[0137] Determining a candidate sample set in a preset sample library based on the hierarchy of the target content key points, wherein the preset sample library includes prompt information samples of different hierarchies;

[0138] Obtain a target example corresponding to the target content key point from the candidate example set;

[0139] The second prompt information is generated based on the target content main point, the target title, the current level, the path from the target title to the target content main point, the second search result, the target example and the second prompt information template.

[0140] Optionally, it also includes:

[0141] Displaying a generation control and a third control corresponding to the candidate title and content highlights on the second page;

[0142] The text generation module 940 is specifically used for:

[0143] In response to a triggering operation of a third control corresponding to the candidate title and content main point, displaying the selected candidate title and content main point;

[0144] In response to the triggering operation of the generation control, the target text is generated based on the selected candidate title and content highlights.

[0145] Optionally, generating the target text based on the selected candidate titles and content highlights includes:

[0146] generating third prompt information based on the selected candidate title, the selected content key points, the configuration information, and the third prompt template;

[0147] The third prompt information is input into a preset natural language processing model to obtain a target text output by the natural language processing model.

[0148] Optionally, generating the third prompt information based on the selected candidate title, the selected content key points, the configuration information, and the third prompt template includes:

[0149] Determine the reference text based on the historical videos published by the account;

[0150] The third prompt information is generated based on the selected candidate title, the selected content main point, the configuration information, the reference text and the third prompt template.

[0151] Optionally, it also includes:

[0152] A fourth control is displayed at the bottom of the display area corresponding to the candidate title or content key point, wherein the fourth control is used to trigger a generation event of the candidate title or content key point at the same level.

[0153] Optionally, the target text includes a video script.

[0154] The text generation device provided in the embodiments of the present disclosure can execute the text generation method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0155] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0156] Figure 10 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 10 , which shows an electronic device (eg Figure 10 The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 10 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0157] like Figure 10 As shown, the electronic device 1000 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1008 into a random access memory (RAM) 1003. Various programs and data required for the operation of the electronic device 1000 are also stored in the RAM 1003. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An edit / output (I / O) interface 1005 is also connected to the bus 1004.

[0158] Typically, the following devices may be connected to the I / O interface 1005: an input device 1006 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1008 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the electronic device 1000 to communicate with other devices wirelessly or by wire to exchange data. Figure 10 The electronic device 1000 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0159] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 1009, or installed from the storage device 1008, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0160] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0161] The electronic device provided by the embodiment of the present disclosure and the text generation method provided by the above embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0162] An embodiment of the present disclosure provides a computer storage medium having a computer program stored thereon. When the program is executed by a processor, the text generation method provided in the above embodiment is implemented.

[0163] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0164] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0165] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0166] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0167] Display the original text and the first control on the first page;

[0168] In response to a triggering operation of the first control, displaying a second page, wherein the second page includes at least one candidate title corresponding to the original text;

[0169] In response to a triggering operation of a target title among the at least one candidate title, displaying at least one level of content highlights of the target title, wherein the at least one level of content highlights represents nodes at different depths of a hierarchical stacking structure corresponding to the target title;

[0170] In response to the selection operation of the candidate title and content main point, a target text is generated based on the selected candidate title and content main point.

[0171] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0172] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0173] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

[0174] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0175] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0176] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0177] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0178] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A text generation method, characterized in that: include: Display the original text and the first control on the first page; In response to a triggering operation of the first control, displaying a second page, wherein the second page includes at least one candidate title corresponding to the original text; In response to a triggering operation of a target title among the at least one candidate title, displaying at least one level of content highlights of the target title, wherein the at least one level of content highlights represents nodes at different depths of a hierarchical stacking structure corresponding to the target title; In response to the selection operation of the candidate title and content main point, a target text is generated based on the selected candidate title and content main point.

2. The method according to claim 1, characterized in that The displaying of the original text and the first control on the first page includes: Displaying a text input box and the first control on the first page; In response to a text input operation in the text input box, the original text is displayed in the text input box.

3. The method according to claim 1, characterized in that The displaying of the second page in response to the triggering operation of the first control includes: In response to the triggering operation of the first control, at least one candidate title corresponding to the original text is generated, and the original text and at least one candidate title are displayed in the second page, wherein the original text is a root node and the at least one candidate title is a child node.

4. The method according to claim 3, characterized in that Generating at least one candidate title corresponding to the original text includes: generating a first search term according to the original text, and determining a first search result based on the first search term; Obtaining a reference title from a preset title library according to the original text; Get the video titles of the historically released videos corresponding to the account; generating first prompt information based on the first search result, the reference title, the video title, and the first prompt template; The first prompt information is input into a preset natural language processing model to obtain at least one candidate title output by the preset natural language processing model.

5. The method according to claim 1, characterized in that Display a second control at a position corresponding to each candidate title, wherein the second control is used to trigger a generation event of a content key point; The step of displaying at least one level of content highlights of the target title in response to a triggering operation of the target title among the at least one candidate title includes: In response to a triggering operation of a second control corresponding to the target title, generating a content key point corresponding to the target title, and displaying the second control at a position corresponding to the content key point, wherein the content key point corresponding to the target title is a child node of the target title; In response to the triggering operation of the second control corresponding to the target content point in the content points of the current level, the content points of the next level are generated for the target content point, and the second control is displayed at the position corresponding to the content points of the next level, wherein the content points of the next level are child nodes of the target content point.

6. The method according to claim 5, characterized in that Generating the content points corresponding to the target title includes: generating a second search term according to the target title, and determining a second search result based on the second search term; generating second prompt information based on the target title, the second search result, the level of the target title, and the second prompt information template; The second prompt information is input into a preset natural language processing model to obtain the content key points output by the preset natural language processing model.

7. The method according to claim 5, characterized in that Generating the next level of content points of the target content points includes: generating a second search term based on the target title and the content key points on the path from the target title to the target content key points, and determining a second search result based on the second search term; generating second prompt information based on the target content main point, the target title, the current level, the path from the target title to the target content main point, the second search result, and the second prompt information template; The second prompt information is input into a preset natural language processing model to obtain the next level of content highlights output by the preset natural language processing model.

8. The method according to claim 7, characterized in that The generating of the second prompt information based on the target content main point, the target title, the current level, the path from the target title to the target content main point, the second search result and the second prompt information template includes: Determining a candidate sample set in a preset sample library based on the hierarchy of the target content key points, wherein the preset sample library includes prompt information samples of different hierarchies; Obtain a target example corresponding to the target content key point from the candidate example set; The second prompt information is generated based on the target content main point, the target title, the current level, the path from the target title to the target content main point, the second search result, the target example and the second prompt information template.

9. The method according to claim 1, characterized in that Also includes: Displaying a generation control and a third control corresponding to the candidate title and content highlights on the second page; In response to the selection operation of the candidate title and content main point, generating a target text based on the selected candidate title and content main point includes: In response to a triggering operation of a third control corresponding to the candidate title and content main point, displaying the selected candidate title and content main point; In response to the triggering operation of the generation control, the target text is generated based on the selected candidate title and content highlights.

10. The method according to claim 9, characterized in that Generating the target text based on the selected candidate titles and content highlights includes: generating third prompt information based on the selected candidate title, the selected content key points, the configuration information, and the third prompt template; The third prompt information is input into a preset natural language processing model to obtain a target text output by the natural language processing model.

11. The method according to claim 10, characterized in that The generating of the third prompt information based on the selected candidate title, the selected content key points, the configuration information and the third prompt template includes: Determine the reference text based on the historical videos published by the account; The third prompt information is generated based on the selected candidate title, the selected content main point, the configuration information, the reference text and the third prompt template.

12. The method according to claim 1, characterized in that Also includes: A fourth control is displayed at the bottom of the display area corresponding to the candidate title or content key point, wherein the fourth control is used to trigger a generation event of the candidate title or content key point at the same level.

13. The method according to any one of claims 1 to 12, characterized in that The target text includes a video script.

14. A text generation device, characterized in that include: A first display module, configured to display the original text and the first control on the first page; a second display module, configured to display a second page in response to a triggering operation of the first control, wherein the second page includes at least one candidate title corresponding to the original text; A third display module is configured to display, in response to a triggering operation of a target title among the at least one candidate title, at least one level of content highlights of the target title, wherein the at least one level of content highlights represents nodes at different depths of a hierarchical stacking structure corresponding to the target title; The text generation module is used to generate a target text based on the selected candidate title and content main point in response to the selection operation of the candidate title and content main point.

15. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the text generation method according to any one of claims 1 to 13.

16. A storage medium containing computer-executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to perform the text generation method according to any one of claims 1 to 13.

17. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the text generation method according to any one of claims 1 to 13.

Images