Media content generation method and apparatus, device, medium, and program product

Abstract

Embodiments of the present disclosure provide a media content generation method and apparatus, a device, a medium, and a program product. The method comprises: displaying an input box and a first control in a first page; in response to a recommendation trigger event in the first page, displaying in the first page a recommended term generated by at least one round of recommendation operations, and on the basis of a recommended term generated by the N-th round of recommendation operations, determining a prompt corresponding to the N-th round of recommendation operations in the input box, wherein the recommended term generated by the N-th round of recommendation operations is determined on the basis of a preset recommendation policy or a prompt corresponding to the (N-1)-th round of recommendation operations; and in response to a trigger operation of the first control, generating media content on the basis of a prompt corresponding to the current round of recommendation operations.

Description

A method, apparatus, equipment, medium, and program product for generating media content.

[0001] Cross-references to related applications

[0002] This application claims priority to Chinese Patent Application No. 202510389647.6, filed on March 28, 2025, entitled "A method, apparatus, device, medium and program product for generating media content", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to computer technology, and more particularly to a method, apparatus, device, medium, and program product for generating media content. Background Technology

[0004] With the development of computer technology, generative applications can help users generate media content that meets their expectations. For example, users can use generative applications to generate images or videos. Summary of the Invention

[0005] This disclosure provides a method, apparatus, device, medium, and program product for generating media content.

[0006] In a first aspect, embodiments of this disclosure provide a media content generation method, including:

[0007] The input box and the first control are displayed on the first page;

[0008] In response to a recommendation trigger event on the first page, recommended words generated by at least one round of recommendation operations are displayed on the first page. Based on the recommended words generated by the Nth round of recommendation operations, the prompt words corresponding to the Nth round of recommendation operations in the input box are determined, wherein the recommended words generated by the Nth round of recommendation operations are determined based on a preset recommendation strategy or the prompt words corresponding to the N-1th round of recommendation operations.

[0009] In response to the triggering operation of the first control, the media content is generated based on the prompt words corresponding to the current round of recommendation operations.

[0010] Secondly, embodiments of this disclosure also provide a media content generation apparatus, the apparatus comprising:

[0011] The first display module is used to display the input box and the first control on the first page;

[0012] The second display module is used to respond to a recommendation trigger event on the first page, display recommended words generated by at least one round of recommendation operations on the first page, and determine the prompt word corresponding to the Nth round of recommendation operations in the input box based on the recommended words generated by the Nth round of recommendation operations, wherein the recommended words generated by the Nth round of recommendation operations are determined based on a preset recommendation strategy or the prompt word corresponding to the N-1th round of recommendation operations;

[0013] The generation module is used to generate the media content in response to the triggering operation of the first control, based on the prompt words corresponding to the current round of recommendation operations.

[0014] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0015] One or more processors;

[0016] 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 media content generation method as described in any embodiment of this disclosure.

[0018] Fourthly, embodiments of this disclosure also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the media content generation method as described in any embodiment of this disclosure.

[0019] Fifthly, embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements the media content generation method as described in any embodiment of this disclosure. Attached Figure Description

[0020] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0021] Figure 1 is a schematic flowchart of a media content generation method provided in an embodiment of this disclosure;

[0022] Figure 2 is a schematic diagram of a first page provided in an embodiment of this disclosure;

[0023] Figure 3 is a flowchart illustrating another media content generation method provided in this embodiment of the present disclosure;

[0024] Figure 4 is a schematic diagram of another first page provided in an embodiment of this disclosure;

[0025] Figure 5 is a schematic diagram of yet another first page provided in an embodiment of this disclosure;

[0026] Figure 6 is a schematic diagram of a recommended word switching display process provided in an embodiment of this disclosure;

[0027] Figure 7 is a flowchart illustrating another media content generation method provided in this embodiment of the present disclosure;

[0028] Figure 8 is a schematic diagram of yet another first page provided in an embodiment of this disclosure;

[0029] Figure 9 is a schematic diagram of the structure of a media content generation device provided in an embodiment of this disclosure;

[0030] Figure 10 is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0031] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0032] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0033] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0034] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0035] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0036] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0037] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0038] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation 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 software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0039] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0040] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0041] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0042] As mentioned above, with the development of computer technology, generative applications can help users generate media content that meets their expectations. For example, users can generate images or videos using generative applications. Current generative applications require users to input prompts to generate images or videos based on those prompts. The more accurate the prompts, the easier it is to generate images or videos that meet expectations; inaccurate prompts will lead to poor image or video generation results.

[0043] To address this, this disclosure provides a media content generation method, apparatus, device, medium, and program product that can assist users in determining accurate prompt words and improve generation effectiveness. Embodiments of this disclosure provide a media content generation method that, by displaying an input box and a first control on a first page, responding to a recommendation trigger event on the first page, displays recommended words generated from at least one round of recommendation operations on the first page, determines the prompt word corresponding to the Nth round of recommendation operations within the input box based on the recommended words generated from the Nth round of recommendation operations, and, responding to a trigger operation of the first control, generates media content based on the prompt word corresponding to the current round of recommendation operations. This achieves automatic generation and recommendation of recommended words, and then determines prompt words based on the recommended words, solving the problem in related technologies where it is difficult to accurately determine prompt words, thus affecting generation effectiveness. Embodiments of this disclosure can provide users with a rich selection of recommended words, and based on these recommended words, can accurately determine prompt words that meet user expectations, improving the generation effectiveness of media content.

[0044] Figure 1 is a schematic flowchart of a media content generation method provided in an embodiment of this disclosure. This embodiment is applicable to the generation of images or videos. The method can be executed by a media content generation device, which can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, such as a mobile terminal, a PC, or a server.

[0045] As shown in Figure 1, the method includes:

[0046] S110. Display the input box and the first control on the first page.

[0047] The first page can be the media content generation page of a generative application. Generative applications include client programs, mini-programs, or web clients used to generate media content. The first control is used to trigger a media content generation event. In response to the triggering operation of the first control, the prompt words in the input box are input into a pre-trained generative model, which then generates media content. The generative model can include a diffusion model, etc. The diffusion model uses the prompt words as conditions to ensure that the generated result is highly semantically consistent with the text. It uses a noise prediction network including an upsampling module, a downsampling module, and an attention mechanism module to progressively predict and remove noise, generating high-quality images or videos.

[0048] S120. In response to the recommendation trigger event on the first page, display recommended words generated by at least one round of recommendation operation on the first page, and determine the prompt word corresponding to the Nth round of recommendation operation in the input box based on the recommended words generated by the Nth round of recommendation operation.

[0049] The recommendation trigger event represents the event that triggers the generation and display of recommended words. Recommended words can be displayed using bubble controls or dropdown list controls, etc. For example, triggering the recommendation trigger event on the first page includes: triggering the recommendation trigger event in response to an input pause operation within the input box; or, triggering the recommendation trigger event in response to a trigger operation of a target recommended word among at least one recommended word generated in the Nth round of recommendation operations. Here, N can be a positive integer. In this embodiment of the disclosure, by triggering the recommendation trigger event when input is paused, candidate creative inspiration is provided by generating and displaying recommended words, thus improving creative efficiency. Furthermore, by triggering the recommendation trigger event of the next round of recommendation operations through the trigger operation of a target recommended word among at least one recommended word in the current round of recommendation operations, the continuous generation and display of recommended words is achieved, simplifying the creative process and improving the user experience while providing creative inspiration.

[0050] In this embodiment of the disclosure, the input pause operation includes the cursor pausing in the input box for a duration exceeding a preset duration threshold. For example, the input pause operation includes pausing for a duration exceeding the preset duration threshold after entering text information into the input box. Alternatively, the input pause operation includes not entering information into the input box, but the cursor pausing in the input box for a duration exceeding the preset duration threshold.

[0051] The recommended words generated in the Nth round of recommendation are determined based on a preset recommendation strategy or the prompt words corresponding to the (N-1)th round of recommendation. A target recommended word represents the selected recommended word from at least one set of recommended words. A target recommended word can be selected by clicking, circling, long-pressing, or swiping. Alternatively, it can be selected by voice.

[0052] In this embodiment, the preset recommendation strategy can be a recommendation strategy associated with at least one of the following: preset news, historical prompts associated with the current account, and input text in the input box. The prompt corresponding to the (N-1)th round of recommendation operation corresponds to the target recommendation word corresponding to the (N-1)th round of recommendation operation. For example, the prompt corresponding to the (N-1)th round of recommendation operation can be the descriptive text corresponding to the target recommendation word of the (N-1)th round of recommendation operation. Alternatively, the prompt corresponding to the (N-1)th round of recommendation operation can be the concatenation result of the target recommendation words of the previous (N-1)th rounds of recommendation operation, etc. It should be noted that there is a one-to-one correspondence between the recommendation word and the descriptive text. The recommendation word can be the semantic summary result of the descriptive text, and the recommendation word and the descriptive text corresponding to the recommendation word can be determined by a pre-trained recommendation model. The recommendation model can be a deep learning model used to generate the recommendation word and the descriptive text. For example, the recommendation model can generate the recommendation word and the descriptive text corresponding to the Nth round of recommendation operation based on the preset recommendation strategy or the prompt word corresponding to the (N-1)th round of recommendation operation.

[0053] For example, in response to a pause operation in the input box of the first page, a recommendation trigger event is triggered on the first page. In response to the recommendation trigger event on the first page, a first round of recommendation operations is performed based on a preset recommendation strategy, generating at least one recommended word and its corresponding descriptive text. In response to a trigger operation of a target recommended word among the at least one recommended word in the first round of recommendation operations, a recommendation trigger event for a second round of recommendation operations is triggered, and the descriptive text corresponding to the current target recommended word is displayed in the input box of the first page as a prompt word for the first round of recommendation operations. At least one recommended word corresponding to the second round of recommendation operations is determined based on the prompt word of the first round of recommendation operations. In response to a trigger operation of a target recommended word among the at least one recommended word in the second round of recommendation operations, a recommendation trigger event for a third round of recommendation operations is triggered, and the prompt word corresponding to the current target recommended word is displayed in the input box of the first page. In this embodiment of the disclosure, determining at least one recommended word corresponding to the Nth round of recommendation operations based on the prompt word corresponding to the (N-1)th round of recommendation operations enables continuous recommendation of recommended words. The target recommended words generated in the Nth round of recommendation operations are used to determine the prompt words corresponding to the Nth round of recommendation operations. Since the target recommended words are selected from at least one recommended word that better matches the user's creative expectations, determining the current prompt words based on the current target recommended words can improve the accuracy of the prompt words.

[0054] Figure 2 is a schematic diagram of a first page provided in an embodiment of this disclosure. As shown in Figure 2, the first page 210 includes an input box 220 and a first control 230. The input box 220 of the first page 210 includes input text, which is a kitten. If the user enters "kitten" into the input box 220 and pauses for t milliseconds, a recommendation trigger event in the first page is triggered, generating at least one recommendation word and corresponding descriptive text based on the kitten. For example, one recommendation word could be a kitten with a bow, and the corresponding descriptive text could be a cute kitten with a bow. Another recommendation word could be a kitten with a bell, and the corresponding descriptive text could be a kitten with a bell around its neck. Multiple bubble controls 240 are displayed on the first page 210, and recommendation words are displayed on the bubble controls 240. In response to a click operation on a bubble control 240, the descriptive text corresponding to the recommendation word on the clicked bubble control 240 is filled into the input box 220 as a prompt word, and at least one recommendation word and corresponding descriptive text for the next round of recommendation operations are generated based on the descriptive text. The recommended words for the next round of recommendation operations include: recommended word a, recommended word c, ..., recommended word x. For example, in response to the triggering operation of the bubble control 240 corresponding to the kitten with a bow, a cute kitten with a bow is filled into the input box 220, thus changing the information in the input box 220 from a kitten to a cute kitten with a bow. Based on the cute kitten with a bow, at least one recommended word and its corresponding descriptive text for the next round of recommendation operations are generated.

[0055] Since recommended words are semantic summaries of descriptive text, they are more concise than the descriptive text itself. By displaying recommended words on the first page, more recommended words can be displayed on the first page while providing candidate creative inspiration, thus avoiding excessive page space usage. In this embodiment, by continuously generating and displaying recommended words, and by continuously refining and adjusting the prompts based on the descriptive text corresponding to the target recommended words in multiple rounds of recommendation operations, the accuracy of the prompts can be improved, thereby enhancing the accuracy of media content generation.

[0056] S130. In response to the triggering operation of the first control, generate the media content according to the prompt word corresponding to the current round of recommendation operation.

[0057] Among these, media content representation generation applications generate results based on prompts. For example, media content includes images or videos.

[0058] For example, in response to the triggering operation of the first control, the media content is generated based on the prompt words of the current round of recommendation operations within the input box. For instance, in response to the triggering operation of the first control, the prompt words in the input box are input into a pre-trained generative model, and the generative model generates media content based on the prompt words. The prompt words may include text prompt information. Optionally, image features such as images and / or videos may also be input into the input box, using the text prompt information and image features as prompt words. After generating the media content, the media content can be displayed. Optionally, a preview image and prompt words of the media content may be displayed.

[0059] Optionally, the descriptive text corresponding to the recommended word can be a complete prompt word determined based on a preset recommendation strategy. In response to a recommendation trigger event on the first page, at least one recommended word is displayed on the first page. In response to a trigger operation of a target recommended word among the at least one recommended word, the descriptive text corresponding to the target recommended word is displayed in the input box. Furthermore, in response to a trigger operation of the first control, media content is generated based on the descriptive text in the input box.

[0060] Optionally, in response to a triggering operation of a second control on the first page, a second page is displayed, the second page including a third control. When the third control is in a closed state, triggering the recommended trigger event is disabled. When the third control is in an open state, triggering the recommended trigger event is enabled.

[0061] The second control represents the on / off state of the recommendation function. For example, the second control can be a toggle switch, with states including off and on. Responding to a trigger operation on the second control, the recommendation function can be turned on or off. If the current state of the second control is off, the recommendation trigger event is disabled, i.e., the recommendation function is off. Responding to a trigger operation on the second control, the state of the second control is changed to on, allowing the recommendation trigger event to be triggered, i.e., the recommendation function is on.

[0062] In other embodiments, after displaying at least one recommended word on the first page, in response to user input in the input box, the input text is displayed in the input box, and at least one recommended word for the next round of recommendation is generated based on the input text. This recommended word is then displayed on the first page. Alternatively, in response to user input in the input box, the input text is displayed in the input box, and at least one recommended word for the next round of recommendation is generated again based on the input text. This recommended word is then displayed on the first page. If the user does not click on any of the recommended words corresponding to n rounds of recommendation operations, the recommendation function is automatically disabled.

[0063] In other embodiments, the recommendation function is automatically turned off in response to the number of characters in the prompt words in the input box exceeding a preset character threshold.

[0064] The technical solution of this disclosure, by displaying an input box and a first control on a first page, responding to a recommendation trigger event on the first page, displays recommended words generated by at least one round of recommendation operations on the first page, determines the prompt word corresponding to the Nth round of recommendation operations in the input box based on the recommended words generated by the Nth round of recommendation operations, and generates media content based on the prompt word corresponding to the current round of recommendation operations in response to the trigger operation of the first control. This achieves automatic generation and recommendation of recommended words, and then determines prompt words based on the recommended words. This solves the problem in related technologies where it is difficult to accurately determine prompt words, thus affecting the generation effect. It can provide users with rich recommended words, and based on the recommended words, it can accurately determine prompt words that meet the user's expectations, thereby improving the generation effect of media content.

[0065] Figure 3 is a flowchart illustrating another media content generation method provided by an embodiment of this disclosure. Based on the above embodiments, this disclosure specifically defines the steps for generating and displaying recommended words.

[0066] S310. Display the input box and the first control on the first page.

[0067] S320. In response to the recommendation trigger event of the Nth round of recommendation operation on the first page, determine at least one recommended word corresponding to the Nth round of recommendation operation.

[0068] For example, in response to the recommendation trigger event of the first round of recommendation operations on the first page, at least one recommended word corresponding to the first round of recommendation operations is determined according to the preset recommendation strategy, wherein the preset recommendation strategy is associated with at least one of preset news, historical prompt words associated with the current account, and input text in the input box. In response to the recommendation trigger event of a recommendation operation after the first round of recommendation operations, at least one recommended word corresponding to the Nth round of recommendation operations is determined based on the prompt words corresponding to the (N-1)th round of recommendation operations.

[0069] If triggering a recommendation event is allowed, the event is triggered when the input field is empty and the cursor pauses within the input field for more than a preset duration threshold. The first round of recommendation operations is performed to determine at least one recommended word based on preset news items and historical suggestion words associated with the current account. For example, trending news is summarized into short recommended words and stored in a preset content library. The preset content library is then queried based on news popularity and historical suggestion words associated with the current account to obtain at least one recommended word corresponding to the first round of recommendation operations.

[0070] Figure 4 is a schematic diagram of another first page provided in an embodiment of this disclosure. As shown in Figure 4, the first page 410 includes an input box 420 and a first control 430, for example, the first control 430 includes a generate button. Preset text is displayed in the input box 420. The preset text is used to prompt the user for information to enter in the input box 420, and after detecting the input text, the preset text is switched to the input text. Two bubble controls 440 are displayed in the area outside the input box 420 in the first page 410. Recommended words are displayed on the bubble controls 440.

[0071] Optionally, if triggering a recommendation trigger event is allowed, in response to the input box including input text and the input pause duration exceeding a preset duration threshold, the recommendation trigger event is triggered to perform a first round of recommendation operations to determine at least one recommended word for the first round of recommendation operations based on the input text.

[0072] Figure 5 is a schematic diagram of another first page provided in an embodiment of this disclosure. As shown in Figure 5, the first page 510 includes an input box 520 and a first control 530, for example, the first control 530 includes a generate button. Input text is displayed within the input box 520, for example, the input text includes "A fluffy little orange cat looks at the camera...". Two speech bubble controls 540 are displayed in the area outside the input box 520 in the first page 510. Recommended words are displayed on the speech bubble controls 540.

[0073] In response to the recommendation trigger event of the recommendation operation following the first round of recommendation operation, at least one recommended word corresponding to the current round of recommendation operation is determined based on the prompt word corresponding to the previous round of recommendation operation in the input box.

[0074] For example, determining at least one recommended word corresponding to the Nth round of recommendation operation based on the prompt word corresponding to the (N-1)th round of recommendation operation includes: obtaining the descriptive text corresponding to the target recommended word of the (N-1)th round of recommendation operation; and generating at least one recommended word and the descriptive text corresponding to the recommended word based on the descriptive text corresponding to the N-1th round of recommendation operation.

[0075] For example, in response to a click on a target recommended word among at least one recommended word in the (N-1)th round of recommendation operations, the content of the input box is updated based on the descriptive text corresponding to the target recommended word, so that the descriptive text corresponding to the target recommended word in the (N-1)th round of recommendation operations is displayed in the input box. The descriptive text corresponding to the target recommended word in the (N-1)th round of recommendation operations is input into the recommendation model, and the recommendation model generates at least one recommended word for the Nth round of recommendation operations and the descriptive text corresponding to the recommended word.

[0076] S330. Display at least one recommended word corresponding to the Nth round of recommendation operation in the area outside the input box on the first page.

[0077] In this embodiment of the disclosure, recommended words are displayed in the area outside the input box on the first page.

[0078] For example, at least one recommended word generated by the (N-1)th round of recommendation is hidden. At least one recommended word corresponding to the Nth round of recommendation is displayed in the area outside the input box on the first page.

[0079] For example, to hide at least one recommended word generated in the (N-1)th round of recommendation, the method includes: adjusting the position and transparency of the recommended word corresponding to the (N-1)th round of recommendation in the area outside the input box on the first page, to demonstrate the process of hiding the recommended word. In response to the recommended word corresponding to the (N-1)th round of recommendation being transparent, at least one recommended word corresponding to the Nth round of recommendation is displayed in the area outside the input box on the first page.

[0080] Figure 6 is a schematic diagram of a recommendation word switching display process provided in an embodiment of this disclosure. As shown in Figure 6, an input box 620 and a first control 630 are displayed in the first page 610. At least one bubble control 640 is displayed in the area outside the input box 620 in the first page 610. The recommendation words corresponding to the N-1th round of recommendation operation are displayed through the bubble control 640. For example, the recommendation words corresponding to the N-1th round of recommendation operation include: recommendation word s, recommendation word r, ..., recommendation word e. In response to the triggering operation of the target recommendation word in the at least one recommendation word corresponding to the N-1th round of recommendation operation, the descriptive text corresponding to the target recommendation word is displayed in the input box 620, and the position and transparency of the bubble control 640 corresponding to the recommendation word in the N-1th round of recommendation operation are adjusted. In response to the bubble control 640 carrying the recommendation word in the area outside the input box 620 in the first page 610 being in a transparent state, the bubble control 640 corresponding to the at least one recommendation word in the N-1th round of recommendation operation is displayed in the area outside the input box 620 in the first page 610. For example, the recommended words for the (N-1)th round of recommendation operation include recommended word h, recommended word n, ..., recommended word f.

[0081] S340. In response to the triggering operation of the target recommended word among the at least one recommended word generated by the Nth round of recommendation operation, determine the prompt word corresponding to the Nth round of recommendation operation based on the description text corresponding to the target recommended word of the Nth round of recommendation operation.

[0082] For example, in response to the triggering operation of the target recommended word in at least one recommended word corresponding to the Nth round of recommendation operation, the descriptive text corresponding to the target recommended word of the Nth round of recommendation operation is used as the prompt word corresponding to the Nth round of recommendation operation.

[0083] S350. Display the prompt words corresponding to the N rounds of recommendation operations in the input box.

[0084] For example, in response to an empty input field, the descriptive text corresponding to the target recommended word in the first round of recommendation is displayed within the input field. In response to the input field including input text, the content of the input field is switched to the descriptive text corresponding to the target recommended word in the first round of recommendation. For recommendation operations after the first round of recommendation, the content of the input field is switched to the descriptive text corresponding to the target recommended word in the current round of recommendation. For example, the descriptive text corresponding to the target recommended word in the second round of recommendation is used to replace the prompt word corresponding to the first round of recommendation in the input field.

[0085] S360. In response to the triggering operation of the first control, generate the media content according to the prompt word corresponding to the current round of recommendation operation.

[0086] The technical solution of this disclosure embodiment, in response to an empty input box, generates at least one recommended word and its corresponding descriptive text based on preset news and historical prompts associated with the current account. In response to an open input box, at least one recommended word is generated based on the input box content. In response to the triggering operation of at least one recommended word generated in the Nth round of recommendation operation, the N+1th round of recommendation operation is triggered to generate at least one recommended word and its corresponding descriptive text corresponding to the N+1th round of recommendation operation. The at least one recommended word corresponding to the N+1th round of recommendation operation is displayed on the first page, realizing the cyclic generation and display of recommended words. During the cyclic recommendation process, the prompts can be continuously refined and adjusted based on the selected recommended words, thereby obtaining prompts that meet user expectations and improving the accuracy and richness of the prompts.

[0087] Figure 7 is a flowchart illustrating another media content generation method provided in this disclosure. Based on the above embodiments, this disclosure specifies a method for optimizing prompt words. As shown in Figure 7, the method includes:

[0088] S710. An input box and a first control are displayed on the first page, wherein the input box includes input text.

[0089] S720. The input text in the input box is processed to obtain optimized prompt words, and the optimized prompt words are displayed in the area outside the input box on the first page.

[0090] The prompt word optimization process includes proposing optimization suggestions based on semantic understanding of the input text. This process can correct the input text. For example, a large language model can be used to perform semantic understanding of the input text within the input box, and then predict and optimize the prompt words based on that understanding. A large language model is a deep learning model trained on massive amounts of data (e.g., billions to hundreds of billions of text data points) for understanding and generating natural language text.

[0091] Display at least one optimization suggestion in the area outside the input box on the first page. For example, this could be done using a speech bubble control or a dropdown list control.

[0092] S730. In response to the triggering operation of the optimized suggestion word, the recommendation triggering event is triggered, and the input text in the input box is updated based on the optimized suggestion word.

[0093] For example, in response to a triggering action of at least one target optimization suggestion word in the optimization suggestions, a recommendation triggering event is triggered, and the input text in the input box is updated according to the target optimization suggestion word. For example, the target optimization suggestion word is displayed in the input box. Alternatively, preset words from the target optimization suggestion word are displayed in the input box. The preset words can be words following preset characters. For example, preset characters can be symbols such as colons or dashes.

[0094] S740. In response to a recommendation trigger event on the first page, display recommended words generated by at least one round of recommendation operations on the first page, and determine the prompt word corresponding to the Nth round of recommendation operations in the input box based on the recommended words generated by the Nth round of recommendation operations, wherein the recommended words generated by the Nth round of recommendation operations are determined based on a preset recommendation strategy or the prompt word corresponding to the N-1th round of recommendation operations.

[0095] For example, in response to a recommendation trigger event on the first page, at least one recommended word and its corresponding descriptive text are generated based on the updated input text in the input box. The at least one recommended word corresponding to the first round of recommendation is displayed in the area outside the input box on the first page. In response to a trigger event for a target recommended word among the at least one recommended word, the descriptive text corresponding to the target recommended word is displayed in the input box, and at least one recommended word corresponding to the second round of recommendation is displayed in the area outside the input box on the first page. Specifically, at least one recommended word and its corresponding descriptive text for the second round of recommendation are generated based on the descriptive text corresponding to the target recommended word in the first round of recommendation. Similarly, in response to a recommendation trigger event for the Nth round of recommendation, at least one recommended word and its corresponding descriptive text for the Nth round of recommendation are generated based on the descriptive text corresponding to the target recommended word in the (N-1)th round of recommendation. This embodiment of the disclosure improves the accuracy and richness of prompt words through prompt word optimization and prompt word recommendation.

[0096] Figure 8 is a schematic diagram of another first page provided in an embodiment of this disclosure. As shown in Figure 8, the first page 810 displays an input box 820 and a first control 830. Input text is displayed in the input box 820 of the first page 810, for example, "Draw a Spring Festival poster". At least one optimization suggestion is displayed in the area 840 outside the input box 820 of the first page 810, for example, "You might want to change: Draw a 'Spring Festival' poster". "You might want to change: Draw 'a' 'Spring Festival' poster", etc. In response to the triggering operation of the target optimization suggestion in at least one optimization suggestion, the input text in the input box 820 is updated based on the target optimization suggestion. That is, the content of the input box 820 is updated to "Draw a 'Spring Festival' poster". The position and transparency of the optimization suggestion in the area 840 outside the input box 820 of the first page 810 are adjusted. In response to the optimization suggestion being in a transparent state, recommended words generated by the first round of recommendation operation are displayed in the area 840 outside the input box 820 of the first page 810. For example, the recommended keywords for the first round of recommendations included adding firecracker elements and adding red lantern elements.

[0097] S550, In response to the triggering operation of the first control, generate the media content according to the prompt word corresponding to the current round of recommendation operation.

[0098] The technical solution of this disclosure embodiment displays an input box and a first control on a first page. The input box includes input text. Optimized prompt words are obtained by optimizing the input text in the input box, and these optimized prompt words are displayed in the area outside the input box on the first page. In response to the triggering operation of the optimized prompt words, a recommendation triggering event is triggered, and the input text in the input box is updated based on the optimized prompt words. In response to the recommendation triggering event on the first page, recommended words generated from at least one round of recommendation operations are displayed on the first page, and the prompt word corresponding to the Nth round of recommendation operations in the input box is determined based on the recommended words generated from the Nth round of recommendation operations. In response to the triggering operation of the first control, media content is generated according to the prompt words corresponding to the current round of recommendation operations. Through the technical solution of this disclosure embodiment, prompt word optimization and prompt word recommendation are combined, improving the accuracy and richness of prompt words.

[0099] Figure 9 is a schematic diagram of a media content generation device provided in an embodiment of this disclosure. The device can be implemented in the form of software and / or hardware, and optionally, it can be implemented in the form of an electronic device, such as a mobile terminal, a PC, or a server.

[0100] As shown in Figure 9, the device includes: a first display module 910, a second display module 920, and a generation module 930.

[0101] The first display module 910 is used to display the input box and the first control on the first page;

[0102] The second display module 920 is used to respond to a recommendation trigger event on the first page, display recommended words generated by at least one round of recommendation operations on the first page, and determine the prompt word corresponding to the Nth round of recommendation operations in the input box based on the recommended words generated by the Nth round of recommendation operations, wherein the recommended words generated by the Nth round of recommendation operations are determined based on a preset recommendation strategy or the prompt word corresponding to the N-1th round of recommendation operations;

[0103] The generation module 930 is used to generate the media content in response to the triggering operation of the first control, based on the prompt words corresponding to the current round of recommendation operations.

[0104] Optionally, triggering the recommendation trigger event on the first page includes:

[0105] In response to a pause operation in the input field, the recommended trigger event is triggered.

[0106] or,

[0107] The recommendation trigger event is triggered in response to the triggering operation of the target recommended word among at least one recommended word generated by the Nth round of recommendation operation.

[0108] Optionally, the second display module 920 is specifically used for:

[0109] In response to the recommendation trigger event of the Nth round of recommendation operation on the first page, at least one recommended word corresponding to the Nth round of recommendation operation is determined;

[0110] At least one recommended word corresponding to the Nth round of recommendation operation is displayed in the area outside the input box on the first page.

[0111] Optionally, the recommendation trigger event in response to the Nth round of recommendation operation on the first page, determining at least one recommended word corresponding to the Nth round of recommendation operation, includes:

[0112] In response to the recommendation trigger event of the first round of recommendation operation on the first page, at least one recommended word corresponding to the first round of recommendation operation is determined according to the preset recommendation strategy, wherein the preset recommendation strategy is associated with at least one of preset news, historical prompt words associated with the current account, and input text in the input box;

[0113] In response to the recommendation trigger event following the first round of recommendation operations, at least one recommended word corresponding to the Nth round of recommendation operations is determined based on the prompt word corresponding to the (N-1)th round of recommendation operations.

[0114] Optionally, determining at least one recommended word corresponding to the Nth round of recommendation operation based on the prompt word corresponding to the (N-1)th round of recommendation operation includes:

[0115] Obtain the description text corresponding to the target recommended word in the (N-1)th round of recommendation operation;

[0116] Based on the description text corresponding to the (N-1)th round of recommendation operation, generate at least one recommended word corresponding to the Nth round of recommendation operation and the description text corresponding to the recommended word.

[0117] Optionally, the second display module 920 is also specifically used for:

[0118] In response to the triggering operation of the target recommended word in at least one recommended word generated by the Nth round of recommendation operation, the prompt word corresponding to the Nth round of recommendation operation is determined according to the description text corresponding to the target recommended word of the Nth round of recommendation operation;

[0119] The prompt words corresponding to the N rounds of recommendation operations are displayed in the input box.

[0120] Optionally, displaying at least one recommended word corresponding to the Nth round of recommendation operation in the area outside the input box on the first page includes:

[0121] Convert at least one recommended word generated in the (N-1)th round of recommendation operation into a hidden state;

[0122] At least one recommended word corresponding to the Nth round of recommendation operation is displayed in the area outside the input box on the first page.

[0123] Optionally, the input box includes input text, and the device further includes:

[0124] The optimization module is used to perform prompt word optimization processing on the input text in the input box after the input box and the first control are displayed on the first page, and to display the optimized prompt word in the area outside the input box on the first page;

[0125] The update module is used to respond to the triggering operation of the optimized suggestion word, trigger the recommendation triggering event, and update the input text in the input box based on the optimized suggestion word.

[0126] Optionally, the generation module 930 is specifically used for:

[0127] In response to the triggering operation of the first control, the media content is generated based on the prompt words of the current round of recommendation operation in the input box.

[0128] Optionally, the device further includes:

[0129] The third display module is used to display the second page in response to the triggering operation of the second control in the first page, and the second page includes the third control;

[0130] The event disabling module is used to prevent the recommended triggering event from being triggered when the third control is in a closed state.

[0131] The event enabling module is used to enable the recommended triggering event in response to the third control being in the enabled state.

[0132] The media content generation apparatus provided in this disclosure can execute the media content generation method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of executing the method.

[0133] 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 division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0134] Figure 10 is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Referring now to Figure 10, a schematic diagram of the structure of an electronic device (e.g., the terminal device or server in Figure 10) 1000 suitable for implementing embodiments of this disclosure is shown. The terminal device in embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. The electronic device shown in Figure 10 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of this disclosure.

[0135] As shown in Figure 10, the electronic device 1000 may include a processing unit (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. The RAM 1003 also stores various programs and data required for the operation of the electronic device 1000. The processing unit 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An edit / output (I / O) interface 1005 is also connected to the bus 1004.

[0136] Typically, the following devices can be connected to the I / O interface 1005: input devices 1006 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 1007 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1008 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows electronic device 1000 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 10 shows an electronic device 1000 with various devices, 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 alternatively.

[0137] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 1009, or installed from storage device 1008, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of embodiments of this disclosure.

[0138] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0139] The electronic device provided in this embodiment and the media content generation method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0140] This disclosure provides a computer storage medium storing a computer program that, when executed by a processor, implements the media content generation method provided in the above embodiments.

[0141] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0142] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0143] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0144] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:

[0145] The input box and the first control are displayed on the first page;

[0146] In response to a recommendation trigger event on the first page, recommended words generated by at least one round of recommendation operations are displayed on the first page. Based on the recommended words generated by the Nth round of recommendation operations, the prompt words corresponding to the Nth round of recommendation operations in the input box are determined, wherein the recommended words generated by the Nth round of recommendation operations are determined based on a preset recommendation strategy or the prompt words corresponding to the N-1th round of recommendation operations.

[0147] In response to the triggering operation of the first control, the media content is generated based on the prompt words corresponding to the current round of recommendation operations.

[0148] Computer program code for performing the operations of this disclosure can 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, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0149] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0150] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0151] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0152] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0153] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0154] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0155] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for generating media content, comprising: The input box and the first control are displayed on the first page; In response to a recommendation trigger event on the first page, recommended words generated by at least one round of recommendation operations are displayed on the first page. Based on the recommended words generated by the Nth round of recommendation operations, the prompt words corresponding to the Nth round of recommendation operations in the input box are determined, wherein the recommended words generated by the Nth round of recommendation operations are determined based on a preset recommendation strategy or the prompt words corresponding to the N-1th round of recommendation operations. In response to the triggering operation of the first control, the media content is generated based on the prompt words corresponding to the current round of recommendation operations.

2. The method according to claim 1, wherein, Triggering the recommended trigger events on the first page includes: In response to a pause operation in the input field, the recommended trigger event is triggered. or, The recommendation trigger event is triggered in response to the triggering operation of the target recommended word among at least one recommended word generated by the Nth round of recommendation operation.

3. The method according to claim 2, wherein, The response to the recommendation trigger event on the first page, displaying recommended words generated from at least one round of recommendation operations on the first page, includes: In response to the recommendation trigger event of the Nth round of recommendation operation on the first page, at least one recommended word corresponding to the Nth round of recommendation operation is determined; At least one recommended word corresponding to the Nth round of recommendation operation is displayed in the area outside the input box on the first page.

4. The method according to claim 3, wherein, The recommendation trigger event in response to the Nth round of recommendation operation on the first page, determining at least one recommended word corresponding to the Nth round of recommendation operation, includes: In response to the recommendation trigger event of the first round of recommendation operation on the first page, at least one recommended word corresponding to the first round of recommendation operation is determined according to the preset recommendation strategy, wherein the preset recommendation strategy is associated with at least one of preset news, historical prompt words associated with the current account, and input text in the input box; In response to the recommendation trigger event following the first round of recommendation operations, at least one recommendation word corresponding to the Nth round of recommendation operations is determined based on the prompt word corresponding to the (N-1)th round of recommendation operations.

5. The method according to claim 4, wherein, The step of determining at least one recommended word corresponding to the Nth round of recommendation operation based on the prompt word corresponding to the (N-1)th round of recommendation operation includes: Obtain the description text corresponding to the target recommended word in the (N-1)th round of recommendation operation; Based on the description text corresponding to the (N-1)th round of recommendation operation, generate at least one recommended word corresponding to the Nth round of recommendation operation and the description text corresponding to the recommended word.

6. The method according to claim 5, wherein, The step of determining the prompt word corresponding to the Nth round of recommendation operation within the input box based on the recommendation words generated by the Nth round of recommendation operation includes: In response to the triggering operation of the target recommended word in at least one recommended word generated by the Nth round of recommendation operation, the prompt word corresponding to the Nth round of recommendation operation is determined according to the description text corresponding to the target recommended word of the Nth round of recommendation operation; The prompt words corresponding to the N rounds of recommendation operations are displayed in the input box.

7. The method according to claim 3, wherein, Displaying at least one recommended word corresponding to the Nth round of recommendation operation in the area outside the input box on the first page includes: Convert at least one recommended word generated in the (N-1)th round of recommendation operation into a hidden state; At least one recommended word corresponding to the Nth round of recommendation operation is displayed in the area outside the input box on the first page.

8. The method according to claim 1, wherein, The input box includes input text, and after the input box and the first control are displayed on the first page, it also includes: The input text in the input box is processed to obtain optimized prompts, and the optimized prompts are displayed in the area outside the input box on the first page. In response to the triggering operation of the optimized suggestion word, the recommendation triggering event is triggered, and the input text in the input box is updated based on the optimized suggestion word.

9. The method according to claim 1, wherein, The step of generating the media content based on the prompt word corresponding to the current round of recommendation operations in response to the trigger operation of the first control includes: In response to the triggering operation of the first control, the media content is generated based on the prompt words of the current round of recommendation operation in the input box.

10. The method according to claim 1, further comprising: In response to a triggering operation of a second control on the first page, a second page is displayed, the second page including a third control; In response to the third control being in a closed state, the recommended triggering event is prevented from being triggered; In response to the third control being enabled, the recommended trigger event is allowed to be triggered.

11. A media content generation device, comprising: The first display module is used to display the input box and the first control on the first page; The second display module is used to respond to a recommendation trigger event on the first page, display recommended words generated by at least one round of recommendation operations on the first page, and determine the prompt word corresponding to the Nth round of recommendation operations in the input box based on the recommended words generated by the Nth round of recommendation operations, wherein the recommended words generated by the Nth round of recommendation operations are determined based on a preset recommendation strategy or the prompt word corresponding to the N-1th round of recommendation operations; The generation module is used to generate the media content in response to the triggering operation of the first control, based on the prompt words corresponding to the current round of recommendation operations.

12. An electronic device, the electronic device comprising: One or more processors; 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 media content generation method as described in any one of claims 1-10.

13. A storage medium comprising computer-executable instructions, which, when executed by a computer processor, are used to perform the media content generation method as described in any one of claims 1-10.

14. A computer program product comprising a computer program that, when executed by a processor, implements the media content generation method as described in any one of claims 1-10.

Images