Content generation method and device, electronic equipment and storage medium

By generating and optimizing live copywriting, the problem of low efficiency of live broadcast anchors manually editing copywriting is solved, efficient and high-quality live content creation is achieved, and the live broadcast effect is improved.

CN119089871APending Publication Date: 2024-12-06BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411274968.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-11
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The live broadcast anchor manually edits copywriting during the live broadcast process inefficient and prone to errors, resulting in low creative efficiency and quality.

Method used

Provide a content generation method, generate text content by receiving input information, associate target materials with preset positions, and display relevant materials during broadcasting, and use large models to generate, edit and optimize text content, and improve copywriting quality and creative efficiency. .

Benefits of technology

It realizes automatic generation of live copywriting, improves the efficiency and quality of copywriting editing, enriches live content, enhances creative effects, and reduces manual editing errors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089871A_ABST
    Figure CN119089871A_ABST
Patent Text Reader

Abstract

The invention provides a content generation method, relates to the technical field of artificial intelligence, in particular to the technical field of deep learning, natural language processing, large models and model generation, and can be used for application scenes such as generative search, document intelligent editing, intelligent assistants, virtual assistants and intelligent e-commerce. According to the specific implementation scheme, in response to received input information, text content is generated; in response to a received association operation for a preset position in the text content, associating a target material at the preset position; in response to the received broadcasting operation for the text content, broadcasting the text content; and in response to broadcasting to the preset position, displaying the target material associated with the preset position. The invention further provides a content generation device, electronic equipment and a storage medium.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the field of deep learning, natural language processing, large models, and generative model technology, and can be used in application scenarios such as generative search, intelligent document editing, intelligent assistants, virtual assistants, and intelligent e-commerce. More specifically, the present disclosure provides a content generation method, device, electronic device, storage medium, and computer program product. Background Art

[0002] With the rapid development of artificial intelligence, content creation based on large models is becoming more and more abundant. Live broadcast is currently a popular media communication method. The anchor needs to manually edit the live broadcast copy for reference and expression during the live broadcast. Manual editing of copy is inefficient and prone to errors. Summary of the invention

[0003] The present disclosure provides a content generation method, an apparatus, an electronic device, a storage medium, and a computer program product.

[0004] According to a first aspect, a content generation method is provided, the method comprising: in response to receiving input information, generating text content; in response to receiving an association operation for a preset position in the text content, associating a target material at the preset position; in response to receiving a broadcast operation for the text content, broadcasting the text content; and in response to broadcasting to the preset position, displaying the target material associated with the preset position.

[0005] According to a second aspect, a content generation device is provided, which includes: a generation module for generating text content in response to receiving input information; an association module for associating a target material at a preset position in the text content in response to receiving an association operation for the text content; a broadcast module for broadcasting the text content in response to receiving a broadcast operation for the text content; and a display module for displaying the target material associated with the preset position in response to broadcasting to the preset position.

[0006] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method provided according to the present disclosure.

[0007] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the method provided according to the present disclosure.

[0008] According to a fifth aspect, a computer program product is provided, comprising a computer program, wherein the computer program is stored on at least one of a readable storage medium and an electronic device, and wherein the computer program implements the method provided according to the present disclosure when executed by a processor.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 is a schematic diagram of an exemplary system architecture to which a content generation method and apparatus can be applied according to an embodiment of the present disclosure;

[0012] Figure 2 is a flowchart of a content generation method according to an embodiment of the present disclosure;

[0013] Figure 3 is a flowchart of a text content generation method according to an embodiment of the present disclosure;

[0014] Figure 4A is a schematic diagram of a page display of a content generation method according to an embodiment of the present disclosure;

[0015] Figure 4B is a page display schematic diagram of a content generation method according to another embodiment of the present disclosure;

[0016] Figure 5 is a block diagram of a content generating device according to an embodiment of the present disclosure;

[0017] Figure 6 is a block diagram of an electronic device according to a content generating method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0019] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0020] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0021] Figure 1 is a schematic diagram of an exemplary system architecture to which a content generation method and apparatus can be applied according to an embodiment of the present disclosure. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0022] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0023] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be various electronic devices, including but not limited to smart phones, tablet computers, laptops, etc.

[0024] The content generation method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the content generation device provided in the embodiment of the present disclosure can generally be set in the server 105. The content generation method provided in the embodiment of the present disclosure can also be executed by a server or a server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the content generation device provided in the embodiment of the present disclosure can also be set in a server or a server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0025] Figure 2 is a flowchart of a content generation method according to an embodiment of the present disclosure.

[0026] like Figure 2 As shown, the content generating method 200 includes operations S210 to S240.

[0027] In operation S210, in response to receiving input information, text content is generated.

[0028] The embodiments of the present disclosure can be applied to live broadcasting scenarios, for example, live broadcasting of objects, live broadcasting of course explanations, live broadcasting of picture book stories, etc. It can also be applied to content creation scenarios, such as course content production, etc.

[0029] The input information may include the subject input by the user, the object information to be introduced, or part of the text content that has been written. Based on the subject and object information, text content containing the corresponding subject or object information can be generated. Based on the part of the text content, it can be continued to obtain the complete text content.

[0030] The input information may also be files such as videos, audios, documents or pictures uploaded by users. Texts may be parsed from the files and sorted to obtain text content.

[0031] The input information can also be the user's real-time voice input, which can be automatically converted into text. It can also support multi-language input, and can be converted into text content for multiple languages.

[0032] The text content generated based on the above input information may be various copywritings, such as copywritings for introducing items, copywritings for explaining courses, and copywritings for describing stories.

[0033] In operation S220, in response to receiving an association operation for a preset position in the text content, a target material is associated with the preset position.

[0034] After generating the text content, the user may choose to perform an association operation at a preset position of the text content. The association operation may include associating the corresponding target material at the preset position. The target material may include pictures, slides, emoticons, stickers, pendants, object connections, etc.

[0035] Associated materials can be set at multiple locations in the text content, and the text content at each location can match the associated material. For example, if the text content at a preset location is an explanation of a certain exercise, the preset location can be associated with a legend of the exercise.

[0036] In operation S230 , in response to receiving a reporting operation for the text content, the text content is reported.

[0037] After obtaining the text content, the user can select the broadcast operation, which is used to audition, preview, broadcast or live broadcast in the form of digital human broadcasting. In the scenario of audition, preview, broadcast or live broadcast, the text content can be converted into voice and the digital human can be driven to perform voice broadcast.

[0038] In operation S240 , in response to the broadcasting to the preset position, a target material associated with the preset position is displayed.

[0039] When the digital human broadcasts to a preset position associated with a target material, the target material can be displayed on the page. The displayed target material can cover the entire live page, or only be displayed in a part of the page. For example, when the exercise explanation is live, the exercise legend can cover the entire page. When an item is live, the item link can be displayed only in a fixed position area of ​​the live page.

[0040] The embodiments of the present disclosure generate text content according to input information, and by setting associated target materials at a preset position of the text content, the associated materials are displayed when the broadcast reaches the preset position, which can make the created content more vivid and improve the creation effect.

[0041] In a live broadcast scenario, the embodiments of the present disclosure can automatically generate live broadcast text, improve the efficiency and quality of text editing, enrich the live broadcast content, and improve the live broadcast effect.

[0042] Figure 3 It is a flowchart of a text content generation method according to the present disclosure.

[0043] like Figure 3 As shown, this embodiment includes operation S310, operation S321~operation S322, and operation S330~operation S360.

[0044] In operation S310, input information is received.

[0045] The input information may include the topic input by the user, the attributes of the item to be introduced, or part of the copy that has been written, or the voice input by the user in real time, or files such as video, audio, and documents. In the live broadcast scenario, the input information may also include the anchor information.

[0046] In operation S321, a target text template is determined according to input information.

[0047] In operation S322, text is parsed from the video / audio / document / picture.

[0048] In operation S330, text content is generated.

[0049] Operation S321 to Operation S330 are steps of generating text content based on the document library.

[0050] The copy library can include commonly used copy templates in multiple scenarios. Each copy template can include welcome words, interactive words, common introductions, etc. Multiple scenarios can include various live broadcast scenarios and content creation scenarios.

[0051] According to an embodiment of the present disclosure, a target copy template may be determined from a copy library according to at least one of subject information and resource information included in input information.

[0052] For example, the subject information may include item recommendations, course explanations, etc., and the resources may include item links, course content, etc. Based on the subject information and resource information, a copywriting template that matches the item to be introduced or the course to be explained can be automatically recommended. In addition, based on the anchor information, the anchor's historical live broadcast information can also be obtained, and a more suitable copywriting template can be recommended to the anchor based on the anchor's historical live broadcast style and historically selected templates.

[0053] In addition, users can select and edit copy templates as needed.

[0054] This embodiment can automatically generate text content based on the copy template, and can also automatically continue writing on the basis of a partial copy to obtain a complete text content.

[0055] Operation S322 to Operation S330 are steps of generating text content by parsing the file.

[0056] According to an embodiment of the present disclosure, text may be parsed from at least one of video, audio, document, and image; and text content may be generated based on the parsed text.

[0057] For example, for a video, text corresponding to the video voice can be parsed from the video, and an image can be extracted from the video and parsed to obtain image description text. The text corresponding to the video voice and the image description text can both be used as text parsed from the video.

[0058] For example, for audio files, you can convert audio into text. For documents, you can extract text from documents. For images, you can generate image description text.

[0059] After obtaining the text parsed from the file, the large model can be called to organize and polish the parsed text to generate text content.

[0060] It should be noted that the above-mentioned images and images extracted from the video can be saved as materials, and after the text content is generated, the text content can be associated with the saved images. For example, the image is associated at a position in the text content corresponding to the description text of the image, so that the image can be displayed when the subsequent broadcast reaches the position.

[0061] In operation S340, the text content is edited, quality analyzed, and checked for illegal words.

[0062] After obtaining the text content, the user can edit and modify the text content. For example, a visual text editing interface can be provided, and the user can adjust the text, font, color, size, etc. in the text.

[0063] For text content, you can also use the quality evaluation model to evaluate the quality of the copy, obtain the quality level of the text content and optimization suggestions for the text content.

[0064] The above-mentioned quality evaluation model can be obtained by fine-tuning the large model, and can score or evaluate the text content, and can also give modification suggestions. For example, the evaluation level can include low, medium, high, etc., and the modification suggestions can include expanding, simplifying, adding modal particles, etc. to the text content.

[0065] You can also use the preset illegal word library to conduct risk checks on the text content to determine whether the text content contains sensitive words, banned words, etc. In addition, it can also provide audit reports and modification suggestions to ensure that the text content meets the compliance requirements of the platform.

[0066] In operation S350, quality prompt information and illegal word prompt information are displayed.

[0067] The quality level of the evaluated text content can be displayed to prompt the user whether the current text content is high-quality copywriting.

[0068] Prompts can also be given for the detected illegal words, for example, the number of illegal words can be displayed, and the location of the illegal words can be displayed by clicking the prompt information.

[0069] In operation S360, the text content is optimized to obtain an optimized copy.

[0070] For example, you can use the big model to rewrite, expand, simplify, polish, add modal particles, etc. to optimize the text content. Users can also rewrite, expand, and optimize a certain part or section of the text content.

[0071] The embodiments of the present disclosure can improve the efficiency of text content generation by using a template library to recommend a target copy template to generate text content, or by generating text content based on text parsed from a file, and can improve the quality of text content through quality analysis, illegal word checking and large model optimization.

[0072] Figure 4A It is a schematic diagram of page display of a content generation method according to an embodiment of the present disclosure.

[0073] like Figure 4AAs shown, page 410 may be an editor page for editing text content, and page 420 may be a display page for preview, broadcast, audition, or live broadcast.

[0074] The text content displayed on the editor page 410 may be a copy generated based on the user's input information. After the copy is generated, it can be published to the editor page 410 with one click.

[0075] According to an embodiment of the present disclosure, in response to receiving an editing operation on text content by a target user in a group, the editing position and editing content of the target user in the text content are determined; based on the editing position, the editing content is synchronized to the text content of other users in the group except the target user.

[0076] The editor of this embodiment can support multi-user collaborative editing. The above group can be a group that supports multi-user collaborative editing. The editing operations of any user in the group can be synchronized to other users in the group.

[0077] For example, the generated copy has a copy identifier. For the copy with the same identifier, the server determines the editing position and editing content in response to any user in the multi-person collaboration group editing the copy, and synchronizes the user's editing content to other users in the multi-person collaboration group based on the editing position.

[0078] This embodiment supports multi-user collaborative editing, facilitates teamwork, and further improves the efficiency of copywriting generation.

[0079] The editor of this embodiment can also save the editing history of the copy, and the user can view and restore the previous version at any time. For example, the previous operation can be undone to return to the version before the operation, and the operation can be restored after the undo operation to restore the version after the operation.

[0080] When editing a document, users can save the text content at preset time intervals to obtain multiple historical versions of the text content. For example, a version can be saved every 5 minutes, which is convenient for users to manage and compare different versions of the document.

[0081] The editor of this embodiment can provide a manual editing function for the user, and can also provide an optimization function based on a large model. For example, the large model can be called to expand, simplify, rewrite, polish, and add modal particles to the text content.

[0082] For example, multiple optimization controls such as rewrite, expand, simplify, polish, and tone are provided in the editor page 410. When the user selects the optimization control, the large model can be called to perform the corresponding optimization function. For example, if the user selects rewrite, the copy can be regenerated. If the user selects tone, modal particles can be added to the copy to make the copy more colloquial. The user can also select a certain paragraph for optimization. For example, after selecting a certain paragraph, the user can select optimization functions such as expansion and simplification. For the optimized content, the user can also choose to replace the copy of the current paragraph, insert it below the copy of the current paragraph, regenerate, and other operations.

[0083] The embodiment of the present disclosure provides a large model-based auxiliary writing function, where the user can input part of the copy and the system automatically completes the rest. It also supports the large model modification function, where the user can make modification requests for the generated copy and the system automatically optimizes and adjusts it, which can improve the copy quality.

[0084] The embodiments of the present disclosure also provide function controls such as timbre, preview, audition, report, and live broadcast. The user selects the timbre control to select a target timbre from a variety of timbres to enable the digital human to report the content of the copy based on the target timbre. The user selects preview to view the screen broadcast by the digital human and audition the content broadcast by the digital human. The user selects audition to audition the timbre of the digital human, the content of the broadcast, etc. The user selects broadcast to drive the digital human to broadcast the complete copy. The user selects live broadcast to drive the digital human to broadcast the copy in a live broadcast scene, and display the corresponding material during the copy broadcast process. The effects displayed by the above preview / audit / broadcast / live broadcast can be consistent.

[0085] The embodiment of the present disclosure provides preview / audit / broadcast functions, and users can view the copywriting broadcast effect in real time. It also provides a live broadcast function, which can display the content created by users in a live broadcast form, thereby improving the publishing efficiency of content creation.

[0086] Figure 4B It is a schematic diagram of page display of a content generation method according to another embodiment of the present disclosure.

[0087] According to an embodiment of the present disclosure, the broadcast operation includes a broadcast interaction operation; in response to receiving a broadcast interaction operation for text content from at least one user, the text content is broadcast using at least one broadcast object.

[0088] like Figure 4BAs shown, page 410 may be an editor page, displaying a generated copy, which may include a first text content 411, a second text content 412, etc. The first text content 411 and the second text content 412 may be text contents of different paragraphs, or may be dialogue contents of different characters in the copy, etc. In this editor page, a broadcast interactive operation may be set for the copy. The broadcast interactive operation may refer to the user setting different broadcast operations for different text contents of the copy, so that different text contents are broadcasted by different digital people, thereby achieving the effect of broadcast interaction.

[0089] Page 420 may be a preview, broadcast, audition, or live broadcast display page, which may display one or more digital people broadcasting the text according to the user's broadcast interaction operation. For example, digital people 421 and 422 may be displayed for broadcasting.

[0090] According to an embodiment of the present disclosure, a first broadcast interaction operation is received from a first user, wherein the first broadcast interaction operation includes the first user setting up multiple corresponding broadcast objects for multiple partial contents of the text content respectively; in response to broadcasting to each partial content, displaying the broadcast object corresponding to the partial content to broadcast the partial content.

[0091] In one example, the first user may set corresponding digital humans for different text contents of the copy. For example, the first user sets digital human 421 for the first text content 411 and sets digital human 422 for the second text content 412. Thus, in the process of broadcasting the copy, when the first text content 411 is broadcasted, digital human 421 is displayed for broadcasting, and when the second text content 412 is broadcasted, digital human 422 is displayed for broadcasting.

[0092] According to an embodiment of the present disclosure, in response to receiving a second editing operation on text content from a second user in the group, a second editing position and a second editing content of the second user in the text content are determined; in response to receiving a second broadcast interaction operation on the second editing position from the second user, the editing content and the second broadcast interaction operation are synchronized to the text content of other users in the group except the second user according to the second editing position, wherein the second broadcast interaction operation includes the second user setting a corresponding broadcast object for the second editing position; in response to broadcasting to the second editing position, the second editing content is broadcast using the broadcast object corresponding to the second editing position.

[0093] In another example, when multiple users are collaboratively editing, multiple users can set multiple broadcast objects to broadcast the content they edited. For example, the second user and the third user are users in the collaborative editing group. The second user edits the first text content 411 and sets the broadcast interaction operation of the digital human 421 associated with the first text content 411. The first text content 411 edited by the second user and the set broadcast interaction operation are synchronized to the third user in the collaborative editing group. The third user edits the second text content 412 and sets the broadcast interaction operation of the digital human 422 associated with the second text content 412. The second text content 412 edited by the third user and the set broadcast interaction operation are synchronized to the second user in the collaborative editing group.

[0094] During the text broadcasting process, when the first text content 411 is broadcasted, it is displayed that the digital person 421 is broadcasting. When the second text content 412 is broadcasted, it is displayed that the digital person 422 is broadcasting.

[0095] In the embodiments of the present disclosure, one user sets multiple broadcast objects to broadcast different contents of a copy, or multiple users set multiple broadcast objects respectively to broadcast contents edited by multiple users, which can enhance the interactivity of the broadcast and improve the fun of the live broadcast.

[0096] According to an embodiment of the present disclosure, the present disclosure also provides a content generating device.

[0097] Figure 5 is a block diagram of a content generating apparatus according to an embodiment of the present disclosure.

[0098] like Figure 5 As shown, the content generating device 500 includes a generating module 510 , an associating module 520 , a broadcasting module 530 and a displaying module 540 .

[0099] The generating module 510 is used to generate text content in response to receiving input information.

[0100] The association module 520 is configured to associate a target material at a preset position in response to receiving an association operation for a preset position in the text content.

[0101] The broadcast module 530 is used for broadcasting the text content in response to receiving a broadcast operation for the text content.

[0102] The display module 540 is used for displaying the target material associated with the preset position in response to the broadcast to the preset position.

[0103] The generating module 510 includes a template determining unit and a first generating unit.

[0104] The template determination unit is used for determining a target document template from a document library according to the input information in response to receiving the input information.

[0105] The first generating unit is used to generate text content according to the target copy template.

[0106] The input information includes at least one of subject information and resource information. The template determination unit is used to determine a target text template from a text library according to at least one of subject information and resource information.

[0107] The generating module 510 includes a parsing unit and a second generating unit.

[0108] The parsing unit is used for parsing text from at least one of the video, audio, document and image in response to receiving at least one of the video, audio, document and image.

[0109] The second generating unit is used to generate text content based on the parsed text.

[0110] The content generating device 500 further includes a processing module.

[0111] The processing module is used to perform at least one of editing, quality evaluation, illegal word checking and optimization on the text content.

[0112] The processing module includes a first editing unit and a first synchronization unit.

[0113] The first editing unit is used for determining the editing position and editing content of the target user in the text content in response to receiving an editing operation on the text content by the target user in the group.

[0114] The first synchronization unit is used to synchronize the edited content to the text content of other users in the group except the target user according to the edit position.

[0115] The broadcasting operation includes a broadcasting interactive operation. The broadcasting module 530 is used to respond to receiving a broadcasting interactive operation for text content from at least one user and use at least one broadcasting object to broadcast the text content.

[0116] The broadcast module 530 includes a receiving unit and a first broadcast unit.

[0117] The receiving unit is used to receive a first broadcast interaction operation from a first user, wherein the first broadcast interaction operation includes the first user setting a plurality of broadcast objects corresponding to respective parts of the text content.

[0118] The first broadcasting unit is used for displaying a broadcasting object corresponding to the partial content to broadcast the partial content in response to the broadcasting to each partial content.

[0119] The broadcast module 530 includes a second editing unit, a second synchronization unit and a second broadcast unit.

[0120] The second editing unit is used for determining a second editing position and a second editing content of the second user in the text content in response to receiving a second editing operation on the text content by the second user in the group.

[0121] The second synchronization unit is used for synchronizing the editing content and the second broadcast interaction operation to the text content of other users in the group except the second user in response to receiving a second broadcast interaction operation from the second user for the second editing position according to the second editing position, wherein the second broadcast interaction operation includes the second user setting a corresponding broadcast object for the second editing position.

[0122] The second broadcasting unit is used for broadcasting the second editing content using the broadcasting object corresponding to the second editing position in response to broadcasting to the second editing position.

[0123] The processing module includes an evaluation unit and a first prompting unit.

[0124] The evaluation unit is used to evaluate the quality of text content and obtain quality grades and optimization suggestions.

[0125] The first prompt unit is used to display quality prompt information, wherein the quality prompt information includes at least one of a quality level and an optimization suggestion.

[0126] The processing module includes a checking unit and a second prompting unit.

[0127] The checking unit is used to check the illegal words contained in the text content using a preset illegal word library.

[0128] The second prompt unit is used to display the illegal word prompt information, wherein the illegal word prompt information includes at least one of the position and the number of the illegal words.

[0129] The processing module includes an optimization unit.

[0130] The optimization unit is used to perform at least one of expansion, simplification, rewriting, polishing and adding modal particles to the text content.

[0131] The content generating device 500 further includes a storage module.

[0132] The saving module is used to save the text content at preset time intervals during the editing process of the text content to obtain multiple historical versions of the text content.

[0133] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0134] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0135] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0136] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0137] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as the content generation method. For example, in some embodiments, the content generation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the content generation method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the content generation method in any other appropriate manner (e.g., by means of firmware).

[0138] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0139] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0140] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. 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, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may 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.

[0141] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0142] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by 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), and the Internet.

[0143] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0144] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0145] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A content generation method, comprising: In response to receiving the input information, generating text content; In response to receiving an association operation for a preset position in the text content, associating a target material at the preset position; In response to receiving a broadcasting operation for the text content, broadcasting the text content; as well as In response to the broadcast to the preset position, the target material associated with the preset position is displayed.

2. The method according to claim 1, wherein: In response to receiving the input information, generating text content includes: In response to receiving the input information, determining a target copy template from a copy library according to the input information; and The text content is generated according to the target copy template.

3. The method according to claim 2, wherein: The input information includes at least one of subject information and resource information; in response to receiving the input information, determining a target copy template from a copy library according to the input information includes: According to at least one of the subject information and the resource information, a target copy template is determined from the copy library.

4. The method according to claim 1, wherein: In response to receiving the input information, generating text content includes: In response to receiving at least one of video, audio, document, and image, parsing text from at least one of the video, audio, document, and image; and The text content is generated based on the parsed characters.

5. The method according to claim 1, further comprising: The text content is at least one of edited, quality evaluated, checked for illegal words, and optimized.

6. The method according to claim 5, wherein: At least one of editing, quality evaluation, illegal word checking, and optimization of the text content includes: In response to receiving a first editing operation on the text content by a target user in the group, determining a first editing position and a first editing content of the target user in the text content; The first edited content is synchronized to text contents of other users in the group except the target user according to the first edited position.

7. The method according to claim 1, wherein: The reporting operation includes reporting an interactive operation; in response to receiving the reporting operation for the text content, reporting the text content includes: In response to receiving a broadcasting interactive operation for the text content from at least one user, the text content is broadcasted using at least one broadcasting object.

8. The method according to claim 7, wherein: In response to receiving a broadcast interaction operation for the text content from at least one user, broadcasting the text content using at least one broadcast object includes: Receiving a first broadcast interaction operation from a first user, wherein the first broadcast interaction operation includes the first user setting a plurality of broadcast objects corresponding to respective portions of the text content; In response to the broadcast to each partial content, a broadcast object corresponding to the partial content is displayed to broadcast the partial content.

9. The method according to claim 7, wherein: In response to receiving a broadcast interaction operation for the text content from at least one user, broadcasting the text content using at least one broadcast object includes: In response to receiving a second editing operation on the text content by a second user in the group, determining a second editing position and a second editing content of the second user in the text content; In response to receiving a second broadcast interaction operation from the second user for the second editing position, synchronizing the edited content and the second broadcast interaction operation to text content of other users in the group except the second user according to the second editing position, wherein the second broadcast interaction operation includes the second user setting a corresponding broadcast object for the second editing position; In response to the broadcast reaching the second editing position, the second editing content is broadcast using a broadcast object corresponding to the second editing position.

10. The method according to claim 5, wherein: At least one of editing, quality evaluation, illegal word checking, and optimization of the text content includes: Evaluate the quality of the text content to obtain a quality grade and optimization suggestions; and Quality prompt information is displayed, wherein the quality prompt information includes at least one of the quality level and optimization suggestions.

11. The method according to claim 5, wherein: At least one of editing, quality evaluation, illegal word checking, and optimization of the text content includes: Using a preset illegal word library to check illegal words contained in the text content; and Displaying the illegal word prompt information, wherein the illegal word prompt information includes at least one of the position and the number of the illegal words.

12. The method according to claim 5, wherein: At least one of editing, quality evaluation, illegal word checking, and optimization of the text content includes: The text content is at least one of expanded, simplified, rewritten, polished and modal particles are added.

13. The method according to claim 5, further comprising: In the process of editing the text content, the text content is saved at preset time intervals to obtain multiple historical versions of the text content.

14. A content generating device, comprising: A generating module, for generating text content in response to receiving input information; an associating module, configured to, in response to receiving an associating operation for a preset position in the text content, associate a target material at the preset position; A broadcasting module, configured to broadcast the text content in response to receiving a broadcasting operation for the text content; as well as The display module is used for displaying the target material associated with the preset position in response to the broadcast to the preset position.

15. The device according to claim 14, wherein: The generation module comprises: a template determination unit, configured to determine a target document template from a document library according to the input information in response to receiving the input information; and The first generating unit is used to generate the text content according to the target copy template.

16. The device according to claim 15, wherein: The input information includes at least one of subject information and resource information; the template determination unit is used to determine a target copy template from the copy library according to at least one of the subject information and resource information.

17. The device according to claim 14, wherein: The generation module comprises: a parsing unit, configured to parse text from at least one of the video, audio, document and image in response to receiving at least one of the video, audio, document and image; and The second generating unit is used to generate the text content based on the parsed characters.

18. The apparatus according to claim 14, further comprising: A processing module is used to perform at least one of editing, quality evaluation, illegal word checking and optimization on the text content.

19. The device according to claim 18, wherein: The processing module comprises: A first editing unit, configured to determine an editing position and editing content of the target user in the text content in response to receiving an editing operation of the target user in the group on the text content; The first synchronization unit is used to synchronize the edited content to text contents of other users in the group except the target user according to the edit position.

20. The device according to claim 14, wherein: The broadcast operation includes a broadcast interaction operation; the broadcast module is used to broadcast the text content using at least one broadcast object in response to receiving a broadcast interaction operation for the text content from at least one user.

21. The device according to claim 20, wherein: The broadcast module comprises: A receiving unit, configured to receive a first broadcast interaction operation from a first user, wherein the first broadcast interaction operation includes the first user setting a plurality of broadcast objects corresponding to respective parts of the text content; The first broadcasting unit is used for displaying a broadcasting object corresponding to each partial content to broadcast the partial content in response to the broadcasting to the partial content.

22. The device according to claim 20, wherein: The broadcast module comprises: A second editing unit, configured to determine a second editing position and a second editing content of the second user in the text content in response to receiving a second editing operation on the text content by the second user in the group; A second synchronization unit is configured to, in response to receiving a second broadcast interaction operation from the second user for the second editing position, synchronize the editing content and the second broadcast interaction operation to text content of other users in the group except the second user according to the second editing position, wherein the second broadcast interaction operation includes the second user setting a corresponding broadcast object for the second editing position; The second broadcasting unit is configured to broadcast the second editing content using a broadcasting object corresponding to the second editing position in response to broadcasting to the second editing position.

23. The device according to claim 18, wherein The processing module comprises: An evaluation unit, configured to evaluate the quality of the text content to obtain a quality grade and optimization suggestions; and The first prompt unit is used to display quality prompt information, wherein the quality prompt information includes at least one of the quality level and optimization suggestions.

24. The device according to claim 18, wherein The processing module comprises: A checking unit, configured to check illegal words contained in the text content using a preset illegal word library; and The second prompt unit is used to display the illegal word prompt information, wherein the illegal word prompt information includes at least one of the position and the number of the illegal words.

25. The apparatus of claim 18, wherein: The processing module comprises: The optimization unit is used to perform at least one of expansion, simplification, rewriting, polishing and adding modal particles to the text content.

26. The apparatus of claim 18, further comprising: The saving module is used to save the text content at preset time intervals during the editing process of the text content to obtain multiple historical versions of the text content.

27. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 13.

28. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 13.

29. A computer program product, comprising a computer program, wherein the computer program is stored on at least one of a readable storage medium and an electronic device, and when the computer program is executed by a processor, the method according to any one of claims 1 to 13 is implemented.

Citation Information

Cited By

  • Live broadcast method and device, electronic equipment, storage medium and program product

    CN119946340A