Interactive drama design method and device based on large language model and electronic equipment

Abstract

The invention provides an interactive drama design method and device based on a large language model and electronic equipment, and relates to the technical field of artificial intelligence. The interactive drama design method based on the large language model comprises the steps that line modification information, input by a user, of any role in a to-be-modified script is acquired; generating response information of other roles according to the line modification information, the background information of the roles and the story situation corresponding to the line modification information by using a story selection large language model; according to the response information of other roles, determining a subsequent plot in the to-be-reorganized script by using a plot scaffold system, and generating a target script; and based on the target script, generating a drama video for displaying the script content of the target script. According to the method, the artificial intelligence technology can be utilized, so that the user can go deep into the core process of drama creation, and the interactivity and efficiency of drama creation are improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an interactive drama design method, device and electronic equipment based on a large language model. Background Art

[0002] With the rapid development of artificial intelligence technology, it has shown broad application prospects and achieved remarkable results in many art fields, including music, painting and literature. AI technology has greatly promoted the innovation and development of these fields through automated creation, intelligent analysis and personalized recommendation. However, in the traditional and profound art form of drama art, the application of AI technology is still in its infancy and faces many challenges and problems.

[0003] First, the limitation of technology application is an important factor restricting the development of AI in theatrical art. Although there have been some attempts to apply AI technology to the visual and sensory aspects of stage art, such as dynamic stage design and visual enhancement, most of these technologies focus on auxiliary means of performance and fail to go deep into the core process of drama creation. The participation of ordinary users in drama creation is still limited, and there is a lack of platforms or tools that can stimulate widespread creative vitality.

[0004] Secondly, the primitiveness of creative tools is also a major obstacle to the current application of AI in drama art. Although some AI tools have been tried for the initial creation of scripts, such as generating basic plot frameworks or dialogues, the content generated by these tools often lacks artistic depth and market competitiveness, and it is difficult to meet the high standards of professional dramas. This has resulted in the actual application value of AI in drama creation being limited and unable to fully realize its potential.

[0005] Therefore, how to use artificial intelligence technology to enable users to delve into the core process of drama creation in order to improve the interactivity and efficiency of drama creation is a technical problem that needs to be solved urgently. Summary of the invention

[0006] In view of the above problems existing in the prior art, the present invention provides an interactive drama design method, device and electronic device based on a large language model, which utilizes artificial intelligence technology to enable users to deeply understand the core process of drama creation, so as to improve the interactivity and efficiency of drama creation.

[0007] The present invention provides an interactive drama design method based on a large language model, comprising the following steps.

[0008] The method comprises obtaining the dialogue modification information of any role in the script to be adapted input by the user; using the plot selection large language model, generating the response information of other roles according to the dialogue modification information, the background information of the role and the plot context corresponding to the dialogue modification information; using the plot scaffolding system to determine the subsequent plot in the script to be adapted and generate a target script according to the response information of the other roles; wherein the plot scaffolding system includes a plurality of preset plot anchor points, each plot anchor point corresponding to a key decision node in the script to be adapted; based on the target script, generating a drama video showing the script content of the target script.

[0009] According to an interactive drama design method based on a large language model provided by the present invention, the method generates a drama video showing the script content of the target script based on the target script, including: using a trained dialogue generation model to generate a dialogue dubbing for each dialogue in the target script according to the target script; generating an editing timeline according to all the dialogue dubbings; wherein the editing timeline is composed of multiple time segments, each time segment corresponds to a dialogue dubbing, and the length of each time segment is the same as the length of the corresponding dialogue dubbing; using a large language model that supports visual question answering, according to the plot text of the dialogue dubbing corresponding to each time segment, a video segment corresponding to each time segment is obtained from a pre-recorded video material library; each dialogue dubbing and each video segment are placed on the corresponding time segment of the editing timeline to synthesize the drama video.

[0010] According to an interactive drama design method based on a large language model provided by the present invention, the dialogue generation model is trained in the following manner: a training data set is generated based on the voices of the actors in the drama video; and an initial end-to-end text-to-speech model is trained using the training data set to obtain the dialogue generation model.

[0011] According to an interactive drama design method based on a large language model provided by the present invention, the subsequent plot in the script to be adapted is determined by using a plot scaffolding system according to the response information of the other characters to generate a target script, including: selecting from the plot scaffolding system a plot path with the highest matching degree with the plot corresponding to the response information of the other characters; generating the target script based on the plot path and the plot before the response information of the other characters in the script to be adapted.

[0012] According to an interactive drama design method based on a large language model provided by the present invention, the method also includes: obtaining user feedback on the drama video; generating reflection prompt words based on the feedback; and inputting the reflection prompt words into the plot selection large language model so that the plot selection large language model performs context learning based on the reflection prompt words.

[0013] The present invention also provides an interactive drama design device based on a large language model, comprising the following modules: An acquisition module is used to obtain the dialogue modification information of any role in the script to be adapted input by the user; a first generation module is used to use the plot selection large language model to generate response information of other roles according to the dialogue modification information and the background information of the role and the plot context corresponding to the dialogue modification information; a determination module is used to determine the subsequent plot in the script to be adapted according to the response information of the other roles and use the plot scaffolding system to generate a target script; wherein the plot scaffolding system includes a plurality of preset plot anchor points, each plot anchor point corresponds to a key decision node in the script to be adapted; a second generation module is used to generate a drama video showing the script content of the target script based on the target script.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, an interactive drama design method based on a large language model as described above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described interactive drama design methods based on a large language model.

[0016] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned interactive drama design methods based on a large language model.

[0017] The interactive drama design method, device and electronic device based on the large language model provided by the present invention obtain the line modification information of any role in the script to be adapted input by the user; utilize the powerful semantic understanding ability and natural language generation ability of the large language model for plot selection, and generate smooth response information of other roles that conforms to the plot coherence and logic according to the line modification information and the background information of the role and the plot context corresponding to the line modification information. According to the response information of other roles, the subsequent plot in the script to be adapted is determined by using the plot scaffolding system, and the target script is generated. The anchor point of the plot scaffolding system can guide the branch selection and generation of the subsequent plot, thereby ensuring the coherence and consistency of the story line of the target script and avoiding the plot from deviating from the preset plot trajectory. Finally, based on the target script, a drama video showing the script content of the target script is generated. Thus, artificial intelligence technology can be used to enable users to deeply understand the core process of drama creation, effectively improving the interactivity and efficiency of drama creation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a flow chart of the interactive drama design method based on the large language model provided by the present invention.

[0020] Figure 2 It is a flowchart of the method for generating a drama video based on a target script provided by the present invention.

[0021] Figure 3 It is a structural schematic diagram of the plot scaffolding system provided by the present invention.

[0022] Figure 4 It is a structural schematic diagram of an interactive drama design device based on a large language model provided by the present invention.

[0023] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Combine the following Figure 1-Figure 3 The interactive drama design method based on a large language model of the present invention is described.

[0026] Figure 1 is a flow chart of the interactive drama design method based on the large language model provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 101: Obtain the dialogue modification information of any role in the script to be adapted input by the user.

[0027] The script to be adapted is a script that needs to be adapted. Users can adapt the script according to their own interests and wishes to participate in the script creation.

[0028] In the specific implementation process, the user's line modification information can be received through a human-computer interaction interface (for example, a text or voice input box displayed on a computer screen). The line modification information can be in various forms, such as text or voice, and is not limited to the description of this specification.

[0029] As an example, the script to be adapted describes a dialogue conflict in a palace banquet. In the script to be adapted, the protagonist A challenges the supporting character B due to a misunderstanding, and the supporting character B responds with a provocative line. User C thinks that the line is too sharp, so he modifies the supporting character B's line to make it more subtle and profound, and hopes to see that this modification will lead to a happy ending for the subsequent plot development.

[0030] In the specific implementation process, the acquisition module executing this step acquires the line modification information of supporting role B input by user C: "Your words are like swords, I hope they can pierce the fog, not the human heart."

[0031] Step 102: Use the plot to select a large language model, and generate response information of other characters according to the dialogue modification information, the background information of the characters, and the plot context corresponding to the dialogue modification information.

[0032] The large language model selected by the plot may be a general large language model after pre-training, or a large language model after continuous training using a large number of plots, and is not limited by the description of this specification.

[0033] In the specific implementation process, prompt words can be generated according to the dialogue modification information, the background information of the character and the plot context corresponding to the dialogue modification information; the prompt words are input into the plot selection large language model, and the plot selection large language model uses its powerful semantic understanding ability and natural language expression ability to output the response information of other characters.

[0034] Just as an example, after receiving the line modification information in the example of step 101, the line modification information, the background information of supporting character B (such as personality, status, relationship with protagonist A, etc.) and the current plot situation (protagonist A challenges supporting character B due to misunderstanding) can be input into the plot selection large language model. The plot selection large language model generates the response information of protagonist A based on the above input information: "There is a sharp edge in your words. I hope we can convince others with reason instead of fighting."

[0035] Step 103: Based on the response information of other characters, the plot scaffolding system is used to determine the subsequent plot in the script to be adapted and generate the target script.

[0036] The plot scaffolding system includes multiple preset plot anchor points, each of which corresponds to a key decision node in the script to be adapted. The plot scaffolding system provides strong support for script adaptation by building a logically clear and well-structured plot framework.

[0037] In the specific implementation process, a plot scaffolding system can be implemented in a processor using a specific form of data structure. The data structure includes a tree, a graph, a linked list, etc., which is used to store and organize key elements such as plot anchors, character information, and scene descriptions. Through a suitable data structure, these plot elements can be effectively managed and operated, thereby achieving the adaptation, optimization, and presentation of the plot.

[0038] In the specific implementation process, we can first deeply analyze the plot and character background of the script to be adapted to ensure that we can accurately capture the personality characteristics, historical background and key role of each character in the plot. Then we can preset multiple plot anchor points and build the following according to the preset plot anchor points: Figure 3 The scaffolding system structure shown.

[0039] In some embodiments, a plot path with the highest degree of matching with the plot corresponding to the response information of other characters may be selected from the plot scaffolding system.

[0040] As an example, for the script to be adapted in step 101, the processing module executing this step can analyze and select the plot path that best matches the current situation based on the lines of the protagonist A and the supporting role B and the current plot situation. For example, the system may choose a path that resolves conflicts through intelligent dialogue and reveals a deeper plot.

[0041] In the specific implementation process, the module executing this step can analyze the response information and match it with the plot anchor points in the plot scaffolding system through a series of algorithms and technical means to determine the plot path with the highest matching degree. For example, natural language processing technology can be used to parse and understand the input response information and extract keywords, phrases or semantic features; by comparing and analyzing these features with the plot anchor points in the plot scaffolding system, the relevance or matching degree of the response information and each plot anchor point can be evaluated.

[0042] In some embodiments, a target script may be generated based on the plot path and the previous plot of the response information of other characters in the script to be adapted.

[0043] Just as an example, for the example in step 101, the target script describes how the protagonist A and the supporting character B gradually resolve misunderstandings through in-depth dialogues, while revealing the conspiracy or secret hidden behind the banquet, thereby driving the plot in a more complex and fascinating direction.

[0044] Step 104: Based on the target script, generate a drama video that displays the script content of the target script.

[0045] In the specific implementation process, a drama video showing the script content of the target script can be generated based on the target script in a variety of ways, which are not limited to the description of this specification.

[0046] For an embodiment of generating a drama video showing the script content of the target script based on the target script, see Figure 2 The relevant content in will not be repeated here.

[0047] In some embodiments, user feedback on a drama video may be obtained; based on the feedback, reflection prompt words may be generated; and the reflection prompt words may be input into a large language model for plot selection so that the large language model for plot selection performs context learning based on the reflection prompt words.

[0048] For example, if a user gives feedback that a plot twist in a drama video is too abrupt, you can construct the following reflection prompts: "The dialogue modification information of A entered by the user is: ….

[0049] The response information of other characters you generated is: ….

[0050] The plot twist is: …

[0051] Please think about this: How can we make the plot twists driven by other characters’ responses more natural and smooth, so as to enhance the audience’s viewing experience? "

[0052] Such prompt words can prompt the plot selection large language model to pay more attention to the naturalness and fluency of plot transitions when generating response information of other characters, so as to better meet the needs and expectations of users.

[0053] In the specific implementation process, after the user watches the generated drama video, the plot or lines can be further adjusted according to the user's feedback according to steps 101 to 104 to generate a drama video to obtain a creation that makes the user more satisfied.

[0054] The embodiments provided by the present invention directly affect the development of the entire script by allowing users to modify the lines of the selected characters, thus achieving a high degree of personalization and interactivity in script creation, allowing users to adjust the plot direction according to their personal preferences and create a unique drama experience. This effectively enhances the user's sense of participation and satisfaction, effectively solves the limitations of the current application of artificial intelligence in the field of drama, creates more diverse and open theatrical art creation and expression forms, and meets the market and audience's demand for new interactive drama experiences.

[0055] Figure 2 It is a flowchart of the method for generating a drama video based on a target script provided by the present invention.

[0056] like Figure 2 As shown, the method includes the following: 201. Using the trained dialogue generation model, generate the dialogue dubbing for each dialogue in the target script according to the target script.

[0057] The line generation model can be an end-to-end text-to-speech model (for example, Tacotron). An end-to-end text-to-speech model can generate speech waveforms directly from text without the need for traditional multiple independent modules (such as text analysis, acoustic model, and audio synthesis modules).

[0058] In the specific implementation process, each section of dialogue can be input into the dialogue generation model respectively, and the dialogue generation model outputs the corresponding dialogue dubbing.

[0059] In some embodiments, a training data set can be generated based on the voices of actors in drama videos (with dialogues as training data and actors' dubbing as labels); the training data set is used to train an initial end-to-end text-to-speech model to obtain a dialogue generation model.

[0060] 202. Generate an editing timeline based on the dubbing of all lines.

[0061] In the specific implementation process, video editing software can be used to generate an editing timeline, which is composed of multiple time segments, each time segment corresponds to a line dubbing, and the length of each time segment is the same as the length of the corresponding line dubbing.

[0062] 203. Using a large language model that supports visual question answering, according to the plot text of the lines dubbed corresponding to each time segment, a video segment corresponding to each time segment is obtained from a pre-recorded video material library.

[0063] In the specific implementation process, the corresponding shots can be recorded according to the script to be adapted and the visual information such as the character actions, expressions, scene changes involved in the plot in the plot scaffolding system, and stored in the video material library. Each shot in the video material library is numbered.

[0064] The plot text with the lines dubbed corresponding to each time segment is input into a large language model that supports visual question answering, and the model is instructed to filter out one or more shots associated with the plot text from the video material library; the large language model that supports visual question answering outputs the numbers of the filtered shots; and the filtered shots are sorted by number to generate video segments.

[0065] For example, for a sad plot text, the large language model that supports visual question answering can select shots that contain sad character expressions, corresponding sad background music, and dim lighting to form a video clip.

[0066] 204. Place each line dubbing and each video clip on the corresponding time segment of the editing timeline to synthesize the drama video.

[0067] In the specific implementation process, the functions provided by the video editing software can be used to place each line dubbing and each video clip on the corresponding time segment of the editing timeline to synthesize the drama video.

[0068] In some embodiments, after generating a drama video according to the above steps, in order to obtain a smoother visual effect, AI technology can be used to adjust the lip shape of each character in the drama video to match the corresponding line dubbing.

[0069] The interactive drama design device based on the large language model provided by the present invention is described below. The interactive drama design device based on the large language model described below and the interactive drama design method based on the large language model described above can refer to each other.

[0070] Figure 4 is a schematic diagram of the structure of an interactive drama design device based on a large language model provided by the present invention, such as Figure 4 As shown, the device 400 includes the following modules.

[0071] The acquisition module 410 is used to acquire the dialogue modification information of any role in the script to be adapted input by the user.

[0072] The first generating module 420 is used to select a large language model by using the plot, and generate response information of other characters according to the line modification information, the background information of the character, and the plot context corresponding to the line modification information.

[0073] The determination module 430 is used to determine the subsequent plot in the script to be adapted and generate a target script by using the plot scaffolding system according to the response information of the other characters; wherein the plot scaffolding system includes a plurality of preset plot anchor points, each plot anchor point corresponding to a key decision node in the script to be adapted.

[0074] The second generating module 440 is used to generate a drama video showing the script content of the target script based on the target script.

[0075] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute an interactive drama design method based on a large language model, the method comprising: obtaining the line modification information of any role in the script to be adapted input by the user; using the plot selection large language model, generating the response information of other roles according to the line modification information and the background information of the role and the plot context corresponding to the line modification information; according to the response information of the other roles, using the plot scaffolding system, determining the subsequent plot in the script to be adapted, and generating a target script; wherein the plot scaffolding system includes a plurality of preset plot anchor points, each plot anchor point corresponds to a key decision node in the script to be adapted; based on the target script, generating a drama video showing the script content of the target script.

[0076] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0077] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the interactive drama design method based on the large language model provided by the above-mentioned methods, which includes: obtaining the dialogue modification information of any role in the script to be adapted input by the user; using the plot selection large language model to generate response information of other roles according to the dialogue modification information and the background information of the role and the plot context corresponding to the dialogue modification information; based on the response information of the other roles, using the plot scaffolding system, determine the subsequent plot in the script to be adapted and generate a target script; wherein the plot scaffolding system includes a plurality of preset plot anchor points, each plot anchor point corresponding to a key decision node in the script to be adapted; based on the target script, generate a drama video showing the script content of the target script.

[0078] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the interactive drama design method based on a large language model provided by the above-mentioned methods, the method comprising: obtaining the dialogue modification information of any role in the script to be adapted input by a user; using the plot selection large language model to generate response information of other roles according to the dialogue modification information and the background information of the role and the plot context corresponding to the dialogue modification information; based on the response information of the other roles, using the plot scaffolding system, determining the subsequent plot in the script to be adapted and generating a target script; wherein the plot scaffolding system includes a plurality of preset plot anchor points, each plot anchor point corresponding to a key decision node in the script to be adapted; based on the target script, generating a drama video showing the script content of the target script.

[0079] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0080] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An interactive drama design method based on a large language model, characterized in that: include: Obtaining the dialogue modification information of any character in the script to be adapted input by the user; Using the plot selection large language model, generating response information of other characters according to the line modification information, the background information of the character, and the plot context corresponding to the line modification information; According to the response information of the other characters, the subsequent plot in the script to be adapted is determined by using the plot scaffolding system to generate a target script; wherein the plot scaffolding system includes a plurality of preset plot anchor points, each plot anchor point corresponding to a key decision node in the script to be adapted; Based on the target script, a drama video is generated that displays the script content of the target script.

2. The interactive drama design method based on a large language model according to claim 1, characterized in that: The step of generating a drama video showing the script content of the target script based on the target script includes: Using the trained dialogue generation model, based on the target script, generate the dialogue dubbing for each paragraph of the target script; Generate an editing timeline based on all the line dubbing; wherein the editing timeline is composed of a plurality of time segments, each time segment corresponds to a line dubbing, and the length of each time segment is the same as the length of the line dubbing corresponding to it; Using a large language model that supports visual question answering, and according to the plot text of the lines and dubbing corresponding to each time segment, a video segment corresponding to each time segment is obtained from a pre-recorded video material library; Each line of dialogue is dubbed and each video clip is placed on the corresponding time segment of the editing timeline to synthesize the drama video.

3. The interactive drama design method based on a large language model according to claim 2, characterized in that: The method further comprises: The AI ​​technology is used to adjust the lip shape of each character in the drama video to match the corresponding line dubbing.

4. The interactive drama design method based on a large language model according to claim 2, characterized in that: The dialogue generation model is obtained by training in the following manner: Generating a training data set based on the voices of the actors in the drama video; The training data set is used to train an initial end-to-end text-to-speech model to obtain the dialogue generation model.

5. The interactive drama design method based on a large language model according to claim 1, characterized in that: The method of determining the subsequent plot in the script to be adapted and generating the target script based on the response information of the other characters by using the plot scaffolding system comprises: Selecting, from the plot scaffolding system, a plot path with the highest matching degree with the plot corresponding to the response information of the other characters; The target script is generated based on the plot path and the previous plot of the response information of other characters in the script to be adapted.

6. The interactive drama design method based on a large language model according to any one of claims 1 to 5, characterized in that: The method further comprises: Obtaining user feedback on the drama video; generating reflection prompt words based on the feedback; The reflection prompt words are input into the plot selection large language model so that the plot selection large language model performs context learning according to the reflection prompt words.

7. An interactive drama design device based on a large language model, characterized in that: include: An acquisition module is used to acquire the dialogue modification information of any role in the script to be adapted input by the user; A first generating module is used to select a large language model by using the plot, and generate response information of other characters according to the line modification information, the background information of the character, and the plot context corresponding to the line modification information; A determination module, for determining the subsequent plot in the script to be adapted and generating a target script by using a plot scaffolding system according to the response information of the other characters; wherein the plot scaffolding system includes a plurality of preset plot anchor points, each plot anchor point corresponding to a key decision node in the script to be adapted; The second generating module is used to generate a drama video showing the script content of the target script based on the target script.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the interactive drama design method based on the large language model as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the interactive drama design method based on a large language model as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the interactive drama design method based on a large language model as described in any one of claims 1 to 6 is implemented.

Images