Content creation method and device based on AI large model, terminal and medium

Abstract

The invention provides a content creation method and device based on an AI large model, a terminal and a medium, and the method is applied to a generative AI large model, and comprises the steps: receiving a creation instruction, and obtaining a creation source related to the creation instruction; obtaining original creation elements related to the creation instruction based on the creation source, and performing creation element integrating degree analysis on the creation source based on a standard creation element structure corresponding to the creation instruction to judge whether the original creation elements meet creation element requirements of the creation instruction; if yes, generating a creation scheme and a creation element set corresponding to the creation scheme based on the original creation elements and the creation instruction; and performing creation based on the creation scheme and the corresponding creation element set to obtain creation content. The interactive content creation based on the AI large model is realized by generating the AI large model and combining the interactive scene of the user, so that richer AI products can be provided for the user, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of AI big model technology, and in particular to a content creation method, device, terminal and medium based on AI big model. Background Art

[0002] With the development of technology, especially the rapid popularization and application of generative AI technology, smart TVs are increasingly dissatisfied with staying at the level of AI voice intelligent interaction. Combined with generative AI technology, major TV manufacturers have begun to gradually launch voice products and text and image products based on AI big models, but these products are still in the primary application stage of generative AI technology, that is, AI big model products do not interact with other TV applications and user scenarios, and do not provide richer generative AI products in combination with TV application scenarios and user interaction scenarios. For example, when users project photos from their mobile phones to the TV, the current generative AI products cannot call the TV's generative AI voice or AI image big model to create content based on the AI ​​big model for the pictures projected to the TV. For example, through image recognition in the TV application window, the current generative AI products cannot create content based on the AI ​​big model through user interaction, nor can they create diverse content based on the AI ​​big model by formulating creative original materials.

[0003] Therefore, how to use the capabilities of generative AI big models and combine them with user interaction scenarios to achieve interactive content creation based on AI big models is an urgent problem that current smart TV manufacturers need to solve in order to improve the competitiveness of their products. Summary of the invention

[0004] The technical problem to be solved by the present invention is that, in response to the above-mentioned defects of the prior art, a content creation method, device, terminal and medium based on AI big model are provided, which solves the technical problem of how to realize interactive content creation based on AI big model through generative AI big model and combined with user interaction scenarios, thereby providing users with richer AI products and improving user experience.

[0005] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0006] A content creation method based on an AI big model is applied to a generative AI big model, wherein the method comprises:

[0007] Receiving a creation instruction and obtaining a creation source related to the creation instruction;

[0008] Based on the creation source, obtaining original creation elements related to the creation instruction;

[0009] Based on the standard creative element structure corresponding to the creative instruction, performing a creative element fit analysis on the creative source to determine whether the original creative element meets the creative element requirements of the creative instruction;

[0010] When the original creative elements meet the creative element requirements, a creative scheme and a corresponding creative element set are generated based on the original creative elements and the creative instructions;

[0011] The creation is performed based on the creation scheme and the corresponding creation element set to obtain the creation content.

[0012] In one implementation, the obtaining of a creation source related to the creation instruction includes:

[0013] Determine whether there is a creation source related to the creation instruction in the current application scenario;

[0014] When the creation source related to the creation instruction exists in the current application scenario, obtaining the creation source related to the creation instruction specified by the user in the current application scenario;

[0015] Or, when the creation source related to the creation instruction does not exist in the current application scenario, the corresponding target application scenario is constructed by inference, and the creation source related to the creation instruction specified by the user is obtained in the target application scenario.

[0016] In one implementation, the performing of a creative element fit analysis on the creative source based on the standard creative element structure corresponding to the creative instruction to determine whether the original creative element meets the creative element requirements of the creative instruction includes:

[0017] Determining the degree of fit between the original creative element and the standard creative element structure corresponding to the creative instruction;

[0018] Determining whether the degree of fit reaches a preset degree of fit range to obtain a corresponding degree of fit analysis result;

[0019] Based on the fit analysis result, determine whether the original creative element meets the creative element requirements corresponding to the creative instruction.

[0020] In one implementation, judging whether the original creative element meets the creative element requirement of the creative instruction based on the fit analysis result includes:

[0021] When the fit analysis result shows that the fit reaches the preset fit range, it is determined that the original creative element meets the creative element requirement of the creative instruction;

[0022] When the fit analysis result indicates that the fit does not reach the preset fit range, it is determined that the original creative element does not meet the creative element requirement of the creative instruction.

[0023] In one implementation, after determining whether the original creation element meets the creation element requirement of the creation instruction, the method further includes:

[0024] When the original creative elements do not meet the creative element requirements, based on the original creative elements and the missing of the original creative elements, and in accordance with the creative element requirements corresponding to the creative instructions, the missing creative elements are inferred to complete the original creative elements.

[0025] In one implementation, after obtaining the creation content through creation based on the creation scheme and the corresponding creation element set, the process further includes:

[0026] Outputting the created content to a display device for display;

[0027] Receiving an interactive instruction issued by a user when viewing the creative content through the display device, and adjusting the creative scheme and the corresponding creative element set according to the interactive instruction to obtain an adjusted creative scheme and an adjusted creative element set;

[0028] New creative content is obtained by re-creation based on the adjusted creative plan and the adjusted creative element set.

[0029] In one implementation, outputting the created content to a display device for display includes:

[0030] When the creative content is a plurality of creative contents, the plurality of creative contents are output to a display device, and each of the creative contents is displayed respectively on a plurality of display windows of the display device.

[0031] The present invention also discloses a content creation device based on an AI big model, which is applied to a generative AI big model, wherein the device comprises:

[0032] A creation instruction receiving module, used for receiving a creation instruction;

[0033] A creation source acquisition module, used to acquire a creation source related to the creation instruction;

[0034] A creation element acquisition module, used for acquiring original creation elements related to the creation instruction based on the creation source;

[0035] A creation requirement judgment module, configured to perform a creation element fit analysis on the creation source based on the standard creation element structure corresponding to the creation instruction, so as to judge whether the original creation element meets the creation element requirement of the creation instruction;

[0036] A scheme and element set generation module, used to generate a creation scheme and its corresponding creation element set based on the original creation element and the creation instruction when the original creation element meets the creation element requirement;

[0037] The content creation module is used to create content based on the creation scheme and its corresponding creation element set to obtain the creation content.

[0038] The present invention also discloses a terminal, which includes: a memory, a processor, and a content creation program based on an AI big model stored in the memory and executable on the processor. When the content creation program based on the AI ​​big model is executed by the processor, the steps of the content creation method based on the AI ​​big model as described above are implemented.

[0039] The present invention also discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program can be executed to implement the steps of the content creation method based on the AI ​​big model as described above.

[0040] The present invention provides a content creation method, device, terminal and medium based on AI big model. The content creation method based on AI big model is applied to generative AI big model, including: receiving creation instructions, and obtaining creation sources related to the creation instructions; based on the creation sources, obtaining original creation elements related to the creation instructions; based on the standard creation element structure corresponding to the creation instructions, performing creation element fit analysis on the creation source to determine whether the original creation elements meet the creation element requirements of the creation instructions; when the original creation elements meet the creation element requirements, generating a creation plan and its corresponding creation element set based on the original creation elements and the creation instructions; performing creation based on the creation plan and its corresponding creation element set to obtain creation content. It can be seen from this that the present invention uses a generative AI big model to perform a creative element fit analysis on the creative source based on the standard creative element structure corresponding to the received creative instructions, so as to determine whether the original creative elements of the creative source meet the creative element requirements, and if they do, generate a creative plan and its corresponding creative element set based on the original creative elements and the creative instructions, and then perform content creation based on the creative plan and its corresponding creative element set, so as to complete the user's creative instruction interaction according to the creative requirements. That is, the technical solution of the present application uses a generative AI big model and combines it with the user's interactive scenario to realize interactive content creation based on the AI ​​big model, so as to provide users with richer AI products and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flowchart of a preferred embodiment of the content creation method based on the AI ​​big model in the present invention;

[0042] Figure 2 It is a flow chart of obtaining a creative source in a screen projection scenario disclosed in the present invention;

[0043] Figure 3 It is a flow chart of a specific content creation method based on AI big model disclosed in the present invention;

[0044] Figure 4 It is a specific logic link reasoning flow chart disclosed by the present invention;

[0045] Figure 5 It is a flow chart of a specific content creation method based on AI big model disclosed in the present invention;

[0046] Figure 6 It is a specific creative source acquisition flow chart disclosed in the present invention;

[0047] Figure 7 It is a flow chart of a specific content creation method based on AI big model disclosed in the present invention;

[0048] Figure 8 It is a flow chart of a specific content creation method based on AI big model disclosed in the present invention;

[0049] Fig. 9 It is a flow chart of a specific content creation method based on AI big model disclosed in the present invention;

[0050] Fig.10 It is a functional principle block diagram of a preferred embodiment of a content creation device based on an AI big model in the present invention;

[0051] Fig.11 It is a functional principle block diagram of a preferred embodiment of the terminal in the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0053] See also Figure 1 , Figure 1 Flowchart of the content creation method based on AI big model in the present invention. Figure 1 As shown, the content creation method based on the AI ​​big model described in the embodiment of the present invention is applied to the generative AI big model, including:

[0054] Step S11, receiving a creation instruction, and obtaining a creation source related to the creation instruction.

[0055] In this embodiment, the user can issue AI content creation instructions according to the creation needs, and the generative AI big model receives the creation instructions issued by the user. The creation instructions may include but are not limited to picture creation instructions, text creation instructions, video creation instructions, comic creation instructions or other types of creation instructions.

[0056] In this embodiment, the generative AI big model can perform inference analysis on the creative needs based on the creative instructions, and then obtain corresponding creative materials in the current application scenario based on the inferred creative needs, such as obtaining the creative source related to the creative instructions, that is, the generative AI big model obtains the creative source related to the creative instructions in the application scenario specified by the user, that is, the user's specified usage scenario can be the source of material for the AI ​​big model creation.

[0057] For example, in the current usage scenario of the smart TV, the user issues a creation instruction to tell a story based on a specified picture. After receiving the creation instruction, the generative AI big model obtains the picture related to the creation instruction specified by the user in the current usage scenario; for another example, the user issues a creation instruction to generate a comic work containing a video content story based on a specified video content. After receiving the creation instruction, the generative AI big model obtains the video content related to the creation instruction specified by the user in the current usage scenario; for another example, the user issues a creation instruction to generate a video story or a graphic story based on the logical relationship of photos in a certain album. After receiving the creation instruction, the generative AI big model obtains the photos in the album specified by the user in the current usage scenario.

[0058] It should be pointed out that when the present application is specifically applied to a smart TV, the user can issue creation instructions through voice, gestures, remote control, mobile phone remote control or other command transmission methods that can reach the smart TV system, and the user can specify the creation source according to the current usage scenario of the smart TV, and the TV usage scenario may include but is not limited to the live broadcast scene of the smart TV, such as set-top boxes, TV signals, etc.; screen projection scenes, such as wireless screen projection, single or multi-channel, etc.; media asset scenes, such as USB or TV stored locally video, audio, pictures, etc.; TV windows, such as system desktop, application windows, etc.; video on demand, such as Tencent, iQiyi video on demand windows, etc., that is to say, the material of the creation source can come from local video, audio, images, smart TV live programs, video on demand, screen projection data streams, etc., and the generative AI large model can obtain material from creation sources of different dimensions according to the creation instructions issued by the user, such as video recording, image screenshots, sound recording, sound to text, text recognition, image recognition and other means to obtain the material of the creation source.

[0059] For example, in the scenario of Tencent video on demand, the user gives the command "help me make a comic based on this clip", that is, to make a comic based on the video content of the video on demand. The AI ​​big model infers that the user wants to "generate a comic work related to the specified video clip being played". Then the AI ​​big model obtains the currently playing clip through the smart TV video recording function, and controls the playback progress bar through the TV system control function to accurately infer the video clip specified by the user, and then locks the video clip and saves it as the creation source.

[0060] In this embodiment, after the creative source is determined by inference, the creative source can be opened in the smart TV window. If there are multiple creative sources, they can be opened and presented simultaneously in multiple windows, and the user can select the desired creative source through interactive confirmation.

[0061] Step S12: Based on the creation source, obtain original creation elements related to the creation instruction.

[0062] In this embodiment, after obtaining the creative source related to the creative instruction, the original creative elements related to the creative instruction can be obtained based on the creative source. It can be understood that the AI ​​big model identifies, analyzes, and infers the correlation between the creative elements of the creative source according to the creative needs of the user's creative instructions, thereby determining the original creative elements of the creative source. For example, the AI ​​creative big model identifies, analyzes, and infers the correlation between the creative elements of the creative source according to the creative needs of the user's creative instruction "to produce comic works related to video content".

[0063] It should be pointed out that creative element identification may include but is not limited to: content identification, such as what this clip is about; event identification, such as drinking, banquets, outings, etc.; character identification, such as character 1 (character name, actor, gender, clothing, etc.), character 2, character N; environment identification, such as time, place, venue, venue style, etc.; emotion identification, such as the corresponding emotions of the characters (excited, happy, sad, etc.); character relationships, such as the relationship between groups, the relationship between individuals, etc.; scene association, such as the association between certain characters at a certain time and place, such as at a certain point in time, character 1 and character 2 are happily drinking; and other elements that can be used for creative analysis.

[0064] Step S13: Based on the standard creative element structure corresponding to the creative instruction, the creative element compatibility analysis is performed on the creative source to determine whether the original creative element meets the creative element requirements of the creative instruction.

[0065] In this embodiment, the AI ​​big model performs a creative element fit analysis on the creative source based on the standard creative element structure corresponding to the creative instruction, so as to determine whether the original creative elements of the creative source meet the creative element requirements corresponding to the creative instruction. Specifically, the fit between the original creative elements of the creative source and the standard creative element structure corresponding to the creative instruction is determined; whether the fit reaches a preset fit range to obtain a corresponding fit analysis result is determined; and whether the original creative elements meet the creative element requirements corresponding to the creative instruction is determined based on the fit analysis result.

[0066] Step S13: When the original creative elements meet the creative element requirements, a creative plan and its corresponding creative element set are generated based on the original creative elements and the creative instructions.

[0067] In this embodiment, based on the fit analysis result, it is determined whether the original creative elements meet the creative element requirements corresponding to the creative instructions, and when the fit analysis result shows that the fit reaches the preset fit range, it is determined that the original creative elements meet the creative element requirements corresponding to the creative instructions, and then based on the original creative elements and the creative instructions, a creative scheme and its corresponding creative element set are generated, that is, based on the original creative elements, and according to the creative instructions, the creative logic link is inferred to generate a corresponding creative scheme and its corresponding creative element set. It can be understood that the AI ​​big model performs a creative element fit analysis on the creative source according to the standard creative element structure corresponding to the creative instruction, and when the original creative elements of the creative source meet the creative element requirements, it is based on the original creative elements and according to the creative instructions to infer the AI ​​creative logic link to generate a corresponding creative scheme and its corresponding creative element set.

[0068] For example, in the TV use scenario of screen projection, the AI ​​big model obtains the creative source, see Figure 2 As shown, the creation instruction issued by the user is received, and then the creation needs are inferred according to the creation instruction, the TV usage scenario is identified, the creation source is dynamically obtained according to the user's screen projection data, and the corresponding creation plan is constructed by dynamic reasoning, and then the creation source is locked at the end of the screen projection operation. For example, if the user issues the creation instruction "Create a video based on the content of the screen projection, which requires dubbing and text", the AI ​​big model infers that the user needs to create a video according to the storyline of the screen projection content of the current window, and configure the dubbing and text that conforms to the style and elements of the video, and then perform a creative element fit analysis, and complete the creation plan and its creation element set reasoning to achieve the corresponding content creation when the screen projection content meets the creation element requirements. Among them, in the screen projection scene, it is necessary to dynamically lock the creation source and identify, analyze, and reason the creation elements in the creation source according to the user's screen projection interaction, so as to dynamically reason the creation plan and its corresponding creation element set.

[0069] It should be pointed out that multiple users can have multiple screen projections, or one screen projection can be displayed through multiple windows, and then according to the number of pictures or videos projected by the user, multiple corresponding windows can be opened for display. In other words, the desktop of the TV system can have multiple windows displaying the content of the user's multi-channel projection.

[0070] Step S14: Create based on the creation plan and its corresponding creation element set to obtain creation content.

[0071] In this embodiment, based on the original creative elements and after inferring the AI ​​creative logic link according to the creative instructions to generate a corresponding creative plan and its corresponding creative element set, the corresponding creative content is obtained based on the creative plan and its corresponding creative element set, that is, the content creation is completed according to the creative elements in the creative element set.

[0072] For example, logical reasoning is performed on the creative elements required for "comic creation", such as story logic, scene logic, character logic, emotional logic, etc., and comic output is performed according to the requirements of comic creation.

[0073] It can be seen that in the embodiment of the present invention, through the generative AI big model, the creative element fit analysis is performed on the creative source based on the standard creative element structure corresponding to the received creative instruction, so as to determine whether the original creative elements of the creative source meet the creative element requirements, and if they meet, the corresponding creative scheme and its corresponding creative element set are generated based on the original creative elements and the creative instruction, and then content creation is performed based on the creative scheme and its corresponding creative element set, so as to complete the user's creative instruction interaction according to the creative requirements. That is, the technical solution of the present application realizes interactive content creation based on the AI ​​big model through the generative AI big model and in combination with the user's interactive scenario, so as to provide users with richer AI products and improve user experience.

[0074] See also Figure 3 As shown, the embodiment of the present invention discloses a specific content creation method based on the AI ​​big model. Compared with the previous embodiment, this embodiment further explains and optimizes the technical solution.

[0075] Step S21, receiving a creation instruction, and obtaining a creation source related to the creation instruction.

[0076] Step S22: Based on the creation source, obtain original creation elements related to the creation instruction.

[0077] Step S23: Based on the standard creative element structure corresponding to the creative instruction, the creative element compatibility analysis is performed on the creative source to determine whether the original creative element meets the creative element requirements of the creative instruction.

[0078] Step S24: When the original creative element does not meet the creative element requirement, based on the original creative element and the missing of the original creative element, and in accordance with the creative element requirement corresponding to the creative instruction, the missing creative element is inferred to complete the original creative element.

[0079] In this embodiment, it is determined whether the original creative elements meet the creative element requirements corresponding to the creative instruction based on the fit analysis results, and when the fit analysis results show that the fit does not reach the preset fit range, it is determined that the original creative elements do not meet the creative element requirements corresponding to the creative instruction, and then based on the original creative elements and the missing of the original creative elements, and in accordance with the creative element requirements corresponding to the creative instruction, the missing creative elements are inferred to complete the original creative elements. It can be understood that if the creative source selected by the user does not meet the creative element requirements through the creative element structure analysis of the AI ​​big model, the AI ​​big model automatically infers and completes the missing creative elements in the original creative elements based on the missing of the original creative elements of the creative source and the original creative elements known in the creative source, according to the creative element requirements corresponding to the creative instruction, until the original creative elements meet the creative element requirements.

[0080] For example, the user specifies multiple photos and asks the AI ​​big model to create a text story. However, the scene elements and event elements cannot be identified from these multiple photos. The AI ​​big model automatically infers and constructs scene elements and event elements based on the characters and their relationships to complete the missing creative elements in the creative source, so as to subsequently output the creative content according to the logic of the text story.

[0081] Step S25: Generate a creation plan and its corresponding creation element set based on the original creation elements and the creation instructions.

[0082] Step S26: Create based on the creation plan and its corresponding creation element set to obtain the creation content.

[0083] For the specific contents of the above steps S21 to S23 and steps S25 to S26, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0084] It can be seen that in the embodiment of the present invention, through the generative AI big model, based on the standard creative element structure corresponding to the received creative instruction, the creative element fit analysis is performed on the creative source to determine whether the original creative elements of the creative source meet the creative element requirements, and if not, the original creative elements are inferred and completed, and then based on the completed original creative elements and creative instructions, a creative scheme and its corresponding creative element set are generated, and then content creation is performed based on the creative scheme and its corresponding creative element set, so that the user's creative instruction interaction can be completed according to the creative requirements. That is, the technical solution of the present application realizes interactive content creation based on the AI ​​big model through the generative AI big model and in combination with the user's interactive scenario, so as to provide users with richer AI products and improve user experience.

[0085] See also Figure 4As shown, in the process of creative element fit analysis, the AI ​​big model can determine the standard creative element structure corresponding to the creative instruction by obtaining the creative elements required by its locally pre-defined creative instructions. For example, the AI ​​big model obtains the creative element structure corresponding to the locally pre-defined "comic creation" creative instruction, wherein the AI ​​big model pre-defines that the elements that need to be included in "comic creation" are: content recognition elements, event recognition elements, character recognition elements, emotion recognition elements, and character relationship elements, so that the standard creative element structure corresponding to the "comic creation" creative instruction can be known. Then, the AI ​​big model identifies, analyzes, and infers the correlation between the creative elements of the creative source according to the creative needs corresponding to the user's creative instructions, thereby determining the original creative elements of the creative source. Finally, the AI ​​big model compares the original creative elements identified, analyzed, and inferred from the creative source with the The creative elements contained in the creative element structure corresponding to the pre-defined creative instructions are analyzed for creative fit, that is, the fit between the original creative elements and the creative elements contained in the standard creative element structure corresponding to the creative instructions is determined, and it is judged whether the fit reaches the preset fit range to obtain the corresponding fit analysis results, so as to judge whether the original creative elements meet the creative element requirements corresponding to the creative instructions based on the fit analysis results. If so, the AI ​​big model directly performs reasoning of the creative logic chain and content creation according to the creative instructions; if not, the AI ​​big model must first reason and complete the original creative elements, and after completion, it can continue to determine whether the completed original creative elements meet the creative element requirements, until the completed original creative elements meet the creative element requirements, and then execute the reasoning of the creative logic chain to generate the corresponding creative plan and its corresponding creative element set, and then perform content creation.

[0086] It should be pointed out that the same creative instruction may infer multiple creative logics, that is, multiple creative logic links, and then generate multiple creative plans and corresponding creative element sets for each creative plan, such as creative logic 1-creative plan 1-creative element set 1; creative logic 2-creative plan 2-creative element set 2; creative logic 3-creative plan 3-creative element set 3. That is to say, after the user specifies the creative source, the AI ​​big model may generate multiple creative plans and their corresponding creative element sets based on the results of element recognition and the reasoning results of the creative logic after performing creative logic inference. That is, after an instruction is issued, the same creative source will generate different creative works from different creative logic links. Users can require the AI ​​big model to open multiple windows at the same time or one by one for users to select and confirm.

[0087] See also Figure 5 As shown, the embodiment of the present invention discloses a specific content creation method based on the AI ​​big model. Compared with the previous embodiment, this embodiment further explains and optimizes the technical solution.

[0088] Step S31, receiving a creation instruction, and determining whether there is a creation source related to the creation instruction in the current application scenario.

[0089] In this embodiment, after receiving the creation instructions issued by the user, the creation requirements can be inferred based on the received creation instructions, and then the current application scenario can be identified to determine whether the current application scenario meets the creation requirements of the creation instructions issued by the user, that is, to determine whether the current application scenario has a creation source related to the creation instructions. If the current application scenario has a creation source related to the creation instructions, then it is determined that the current application scenario meets the creation requirements of the creation instructions issued by the user. If the current application scenario does not have a creation source related to the creation instructions, then it is determined that the current application scenario does not meet the creation requirements of the creation instructions issued by the user.

[0090] Step S32: When the creation source related to the creation instruction exists in the current application scenario, the creation source related to the creation instruction specified by the user is obtained in the current application scenario.

[0091] In this embodiment, it is determined whether there is a creation source related to the creation instruction in the current application scenario, and when there is a creation source related to the creation instruction in the current application scenario, the creation source related to the creation instruction specified by the user can be directly obtained in the current application scenario. For example, a user issues a creation instruction "create 1 thrilling video of star A's concert in 2024" on the smart TV desktop. If there is corresponding video content playing in the current application scenario (current usage scenario) of the smart TV, the relevant creation source is obtained from the video content played in the application scenario of the smart TV.

[0092] For example, see Figure 6 As shown, in the process of the AI ​​big model acquiring the creative source, the AI ​​big model infers the creative requirements based on the received creative instructions, and then identifies the TV application scenario to determine whether the current TV application scenario meets the creative requirements of the creative instructions issued by the user, that is, to determine whether the current application scenario has a creative source related to the creative instruction. If so, the creative source is directly acquired, such as related audio, video, pictures, text, etc.

[0093] Step S33: Based on the creation source, obtain original creation elements related to the creation instruction.

[0094] Step S34: Based on the standard creative element structure corresponding to the creative instruction, the creative element compatibility analysis is performed on the creative source to determine whether the original creative element meets the creative element requirements of the creative instruction.

[0095] Step S35: When the original creative elements meet the creative element requirements, a creative plan and its corresponding creative element set are generated based on the original creative elements and the creative instructions.

[0096] Step S36: Create based on the creation plan and its corresponding creation element set to obtain the creation content.

[0097] For the specific contents of the above steps S33 to S36, reference may be made to the corresponding contents disclosed in the above embodiments, which will not be repeated here.

[0098] It can be seen that in the embodiment of the present invention, through the generative AI big model, based on the standard creative element structure corresponding to the received creative instruction, the creative element fit analysis is performed on the creative source to determine whether the original creative elements of the creative source meet the creative element requirements, and if they do, based on the original creative elements and the creative instructions, a creative scheme and its corresponding creative element set are generated, and then content creation is performed based on the creative scheme and its corresponding creative element set, so that the user's creative instruction interaction can be completed according to the creative requirements. That is, the technical solution of the present application realizes interactive content creation based on the AI ​​big model through the generative AI big model and in combination with the user's interactive scenario, so as to provide users with richer AI products and improve user experience.

[0099] See also Figure 7 As shown, the embodiment of the present invention discloses a specific content creation method based on the AI ​​big model. Compared with the previous embodiment, this embodiment further explains and optimizes the technical solution.

[0100] Step S41, receiving a creation instruction, and determining whether there is a creation source related to the creation instruction in the current application scenario.

[0101] Step S42: When the creation source related to the creation instruction does not exist in the current application scenario, the corresponding target application scenario is constructed by inference, and the creation source related to the creation instruction specified by the user is obtained under the target application scenario.

[0102] In this embodiment, it is determined whether there is a creation source related to the creation instruction in the current application scenario. If there is no creation source related to the creation instruction in the current application scenario, it is necessary to infer and construct the corresponding target application scenario, and obtain the creation source related to the creation instruction specified by the user in the target application scenario. It is understandable that if the creation instruction issued by the user requires the AI ​​big model to build an application scenario, the AI ​​big model will build the relevant application scenario.

[0103] For example, if a user issues a creation instruction on the smart TV desktop to "create a thrilling video of star A's concert in 2024", if there is no corresponding video content to play in the current application scenario of the smart TV, the AI ​​big model and the media data knowledge base of the smart TV can be used to infer which videos or materials in which applications need to be used to obtain the creation source related to the creation instruction specified by the user. For example, the videos of star A having two concerts with the risk of falling in 2024 can be found in A video application-access link 1 and B video application-access link 2 respectively. Then, open the A video application-access link 1 window and the B video application-access link 2 window on the smart TV, locate the thrilling clip for playback, and then after the user confirms the creation source, continue to execute the subsequent content creation steps.

[0104] For example, see above Figure 6 As shown, in the process of the AI ​​big model acquiring the creative source, the AI ​​big model infers the creative requirements based on the received creative instructions, and then identifies the TV application scenario to determine whether the current TV application scenario meets the creative requirements of the creative instructions issued by the user, that is, to determine whether the current application scenario has a creative source related to the creative instruction. If not, a user creative scenario is created, such as inferring which applications need to be opened and which application scenarios need to be built.

[0105] Step S43: Based on the creation source, obtain original creation elements related to the creation instruction.

[0106] Step S44: Based on the standard creative element structure corresponding to the creative instruction, a creative element compatibility analysis is performed on the creative source to determine whether the original creative element meets the creative element requirements corresponding to the creative instruction.

[0107] Step S45: When the original creative elements meet the creative element requirements, a creative plan and its corresponding creative element set are generated based on the original creative elements and the creative instructions.

[0108] Step S46: Create based on the creation plan and its corresponding creation element set to obtain creation content.

[0109] For the specific contents of the above steps S43 to S46, reference may be made to the corresponding contents disclosed in the above embodiments, which will not be repeated here.

[0110] It can be seen that in the embodiment of the present invention, through the generative AI big model, based on the standard creative element structure corresponding to the received creative instruction, the creative element fit analysis is performed on the creative source to determine whether the original creative elements of the creative source meet the creative element requirements, and if they do, based on the original creative elements and the creative instructions, a creative scheme and its corresponding creative element set are generated, and then content creation is performed based on the creative scheme and its corresponding creative element set, so that the user's creative instruction interaction can be completed according to the creative requirements. That is, the technical solution of the present application realizes interactive content creation based on the AI ​​big model through the generative AI big model and in combination with the user's interactive scenario, so as to provide users with richer AI products and improve user experience.

[0111] See also Figure 8 As shown, the embodiment of the present invention discloses a specific content creation method based on the AI ​​big model. Compared with the previous embodiment, this embodiment further explains and optimizes the technical solution.

[0112] Step S51, receiving a creation instruction, and obtaining a creation source related to the creation instruction.

[0113] Step S52: Based on the creation source, obtain original creation elements related to the creation instruction.

[0114] Step S53: Based on the standard creative element structure corresponding to the creative instruction, the creative element compatibility analysis is performed on the creative source to determine whether the original creative element meets the creative element requirements of the creative instruction.

[0115] Step S54: When the original creative elements meet the creative element requirements, a creative plan and its corresponding creative element set are generated based on the original creative elements and the creative instructions.

[0116] Step S55: Create based on the creation plan and its corresponding creation element set to obtain the creation content.

[0117] Step S56: output the created content to a display device for display.

[0118] In this embodiment, the AI ​​big model creates content based on the creation scheme and its corresponding creation element set to obtain corresponding creation content, and can output the creation content to the corresponding display device for display, such as outputting it to a smart TV window. In addition, when the creation content is multiple creation contents, the multiple creation contents are output to the corresponding display device, and each creation content is displayed on multiple display windows of the display device. It should be pointed out that when outputting the creation content, the creation scheme and the corresponding creation element set corresponding to the creation logic can also be displayed in the window at the same time.

[0119] Step S57, receiving an interactive instruction issued by a user when viewing the creative content through the display device, and adjusting the creative scheme and the corresponding creative element set according to the interactive instruction to obtain an adjusted creative scheme and an adjusted creative element set.

[0120] In this embodiment, the AI ​​big model creates content according to the creation scheme and its corresponding creation element set, and outputs the creation content to the display device, and the user interacts with the command according to the content output to the TV window. It is understandable that the user can adjust the content creation ideas of the AI ​​big model through command interaction, that is, the user issues the corresponding interactive command, and the AI ​​big model adjusts the creation scheme and its corresponding creation element set according to the interactive command to obtain the adjusted creation scheme and the adjusted creation element set. For example, the user can request to replace or delete one or more creation elements, or add non-existent creation elements, and when the user issues such instructions, the AI ​​big model fine-tunes the creation element set according to the creation needs.

[0121] For example, in the local media scenario of a smart TV, when a user accesses the AI ​​album of the smart TV, there are many photos in the album. The user can specify a certain person and generate a subtitled video with the photos of this person according to the timeline and storyline. After generating a group of videos, the user can also specify a certain video and continue to send interactive instructions, requiring that the video does not require event A and add character B, etc. Then the AI ​​big model infers the creation requirements of the instruction based on the interactive instruction, fine-tunes the creation plan, and continues to output the creative content.

[0122] Step S58: re-create new creative content based on the adjusted creative plan and the adjusted creative element set.

[0123] In this embodiment, new creative content is obtained by re-creation based on the adjusted creative scheme and the adjusted creative element set. It can be understood that the AI ​​big model adjusts the creative scheme according to the user's interactive instructions, completes the relevant creative logic reasoning and creative element set reconstruction, and re-completes the content creation according to the user's interactive instructions.

[0124] For example, after creating a thrilling video of Star A's concert in 2024, it is also necessary to add text and voice broadcasts introducing Star A in the video, and adjust the creative content according to the user's instructions. For example, the user can use a voice remote control to output descriptive text and voice, and perform corresponding special effects processing on the thrilling time period. The adjustment of the creative content may include replacing the creative source, replacing elements, changing the relationship between elements, etc.

[0125] For the specific contents of the above steps S51 to S55, reference may be made to the corresponding contents disclosed in the above embodiments, which will not be elaborated here.

[0126] It can be seen that in the embodiment of the present invention, through the generative AI big model, based on the standard creative element structure corresponding to the received creative instruction, the creative element fit analysis is performed on the creative source to determine whether the original creative elements of the creative source meet the creative element requirements, and if they do, based on the original creative elements and the creative instructions, a creative scheme and its corresponding creative element set are generated, and then content creation is performed based on the creative scheme and its corresponding creative element set, so that the user's creative instruction interaction can be completed according to the creative requirements. That is, the technical solution of the present application realizes interactive content creation based on the AI ​​big model through the generative AI big model and in combination with the user's interactive scenario, so as to provide users with richer AI products and improve user experience.

[0127] For example, see Fig. 9 As shown, the smart TV is turned on and the AI ​​large model is loaded. The user can specify the creation source according to the current smart TV application scenario. The source of the creation source may include but is not limited to smart TV live broadcast, screen projection data, local media resources, TV window, video on demand, etc. Then the user issues AI content creation instructions according to demand, where the creation instructions may include but are not limited to picture creation instructions, text creation instructions, video creation instructions, comic creation instructions and other types of creation instructions. Next, the AI ​​big model analyzes the creative element fit of the creative source according to the standard creative element structure corresponding to the creative instruction to determine whether the original creative elements of the creative source meet the creative element requirements of the creative instruction. If not, the AI ​​big model must first infer and complete the original creative elements, and then perform the subsequent creative logic link reasoning and content creation after completion. If it is in line with the AI ​​big model, the creative logic link is directly inferred according to the creative instruction, and the corresponding creative scheme and its corresponding creative element set are generated according to the creative logic link of the creative instruction. Finally, the content is created based on the creative scheme and its corresponding creative element set, and the creative content is output. The user checks the currently output creative content by watching and checking whether the creative content meets his creative needs. If it is in line with the requirements, the user will proceed to the next step of processing the creative content; if it is not in line with the requirements, the user adjusts the content creation ideas of the AI ​​big model, that is, adjusts the creative scheme and its corresponding creative element set. It can be seen from this that the technical solution of interactive content creation based on the application scenario of smart TVs in this application can improve the AI ​​efficiency of smart TVs, expand the application boundaries of traditional smart TVs, bring better AI intelligent applications and services to users, and greatly improve the user experience of smart TVs.

[0128] In one embodiment, if Fig.10 As shown, based on the above-mentioned content creation method based on the AI ​​big model, the present invention also provides a content creation device based on the AI ​​big model, which is applied to the generative AI big model, including:

[0129] The creation instruction receiving module 100 is used to receive the creation instruction;

[0130] A creation source acquisition module 200, used to acquire a creation source related to the creation instruction;

[0131] A creation element acquisition module 300, used to acquire original creation elements related to the creation instruction based on the creation source;

[0132] A creation requirement judgment module 400 is used to perform a creation element fit analysis on the creation source based on the standard creation element structure corresponding to the creation instruction, so as to judge whether the original creation element meets the creation element requirement corresponding to the creation instruction;

[0133] A scheme and element set generation module 500, configured to generate a creation scheme and a corresponding creation element set based on the original creation element and the creation instruction when the original creation element meets the creation element requirement;

[0134] The content creation module 600 is used to create content based on the creation scheme and its corresponding creation element set to obtain the creation content.

[0135] Fig.11 A schematic diagram of the structure of a terminal provided in an embodiment of the present application. The terminal may include:

[0136] A memory 501 , a processor 502 , and a computer program stored in the memory 501 and executable on the processor 502 .

[0137] When the processor 502 executes the program, the content creation method based on the AI ​​big model provided in the above embodiment is implemented.

[0138] Furthermore, the terminal further includes:

[0139] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0140] The memory 501 is used to store computer programs that can be executed on the processor 502 .

[0141] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0142] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0143] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0144] The processor 502 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0145] This embodiment also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned content creation method based on the AI ​​big model is implemented.

[0146] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0147] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0148] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes additional implementations, in which the order shown or discussed may not be followed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0149] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can read instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary and then storing it in a computer memory.

[0150] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0151] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0152] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0153] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

[0154] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A content creation method based on AI big model, characterized in that: Applied to a generative AI large model, the method includes: Receiving a creation instruction and obtaining a creation source related to the creation instruction; Based on the creation source, obtaining original creation elements related to the creation instruction; Based on the standard creative element structure corresponding to the creative instruction, performing a creative element fit analysis on the creative source to determine whether the original creative element meets the creative element requirements of the creative instruction; When the original creative elements meet the creative element requirements, a creative scheme and a corresponding creative element set are generated based on the original creative elements and the creative instructions; The creation is performed based on the creation scheme and the corresponding creation element set to obtain the creation content.

2. The content creation method based on AI big model according to claim 1 is characterized in that: The obtaining of the creation source related to the creation instruction includes: Determine whether there is a creation source related to the creation instruction in the current application scenario; When the creation source related to the creation instruction exists in the current application scenario, obtaining the creation source related to the creation instruction specified by the user in the current application scenario; Or, when the creation source related to the creation instruction does not exist in the current application scenario, the corresponding target application scenario is constructed by inference, and the creation source related to the creation instruction specified by the user is obtained in the target application scenario.

3. The content creation method based on AI big model according to claim 1 is characterized in that: The performing of a creative element fit analysis on the creative source based on the standard creative element structure corresponding to the creative instruction to determine whether the original creative element meets the creative element requirements of the creative instruction includes: Determining the degree of fit between the original creative element and the standard creative element structure corresponding to the creative instruction; Determining whether the degree of fit reaches a preset degree of fit range to obtain a corresponding degree of fit analysis result; Based on the fit analysis result, determine whether the original creative element meets the creative element requirements of the creative instruction.

4. The content creation method based on AI big model according to claim 3 is characterized in that: The determining, based on the fit analysis result, whether the original creative element meets the creative element requirement of the creative instruction includes: When the fit analysis result shows that the fit reaches the preset fit range, it is determined that the original creative element meets the creative element requirement of the creative instruction; When the fit analysis result indicates that the fit does not reach the preset fit range, it is determined that the original creative element does not meet the creative element requirement of the creative instruction.

5. The content creation method based on AI big model according to claim 1 is characterized in that: After determining whether the original creation element meets the creation element requirement of the creation instruction, the method further includes: When the original creative elements do not meet the creative element requirements, the missing creative elements are inferred based on the original creative elements and the missing of the original creative elements and in accordance with the creative element requirements of the creation instructions to complete the original creative elements.

6. The content creation method based on AI big model according to any one of claims 1 to 5, characterized in that: After obtaining the creation content through creation based on the creation scheme and the corresponding creation element set, the method further includes: Outputting the created content to a display device for display; Receiving an interactive instruction issued by a user when viewing the creative content through the display device, and adjusting the creative scheme and the corresponding creative element set according to the interactive instruction to obtain an adjusted creative scheme and an adjusted creative element set; New creative content is obtained by re-creation based on the adjusted creative plan and the adjusted creative element set.

7. The content creation method based on AI big model according to claim 6 is characterized in that: Outputting the created content to a display device for display includes: When the creative content is a plurality of creative contents, the plurality of creative contents are output to a display device, and each of the creative contents is displayed respectively on a plurality of display windows of the display device.

8. A content creation device based on an AI big model, characterized in that: Applied to a generative AI large model, the device comprises: A creation instruction receiving module, used for receiving a creation instruction; A creation source acquisition module, used to acquire a creation source related to the creation instruction; A creation element acquisition module, used for acquiring original creation elements related to the creation instruction based on the creation source; A creation requirement judgment module, configured to perform a creation element fit analysis on the creation source based on the standard creation element structure corresponding to the creation instruction, so as to judge whether the original creation element meets the creation element requirement of the creation instruction; A scheme and element set generation module, used to generate a creation scheme and its corresponding creation element set based on the original creation element and the creation instruction when the original creation element meets the creation element requirement; The content creation module is used to create content based on the creation scheme and its corresponding creation element set to obtain the creation content.

9. A terminal, characterized in that: include: A memory, a processor, and a content creation program based on an AI big model stored in the memory and executable on the processor, wherein the content creation program based on the AI ​​big model, when executed by the processor, implements the steps of the content creation method based on the AI ​​big model as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which can be executed to implement the steps of the content creation method based on the AI ​​big model as described in any one of claims 1 to 7.

Images