Information processing method and device, program product and electronic equipment

Abstract

The invention provides an information processing method and device, a program product and electronic equipment, and relates to the technical field of computers. The method comprises the steps of obtaining a to-be-converted object; decomposing the to-be-converted object, and determining a plurality of script entry point events of the to-be-converted object and script outline information corresponding to each script entry point event; obtaining interaction mode information; and generating a plurality of script scene contents according to the interaction mode information, the plurality of script entry point events and the script outline information corresponding to each script entry point event. In the embodiment of the invention, the to-be-converted object can be automatically converted, so that the script conversion efficiency is improved to a certain extent.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of computer, and more particularly, to an information processing method, an information processing apparatus, a computer program product, and an electronic device. BACKGROUND

[0002] At present, with the continuous development of technology, more and more people like to read content with strong interactivity and self-adjustment. Therefore, it is an urgent problem to be solved to convert books with traditional pure text content into multi-modal scripts.

[0003] In the related art, the script conversion is generally performed by a scriptwriter manually. Specifically, the scriptwriter manually divides books with traditional pure text content into scripts according to different modalities, and then manually writes corresponding extended content to obtain new modal scripts. SUMMARY

[0004] As can be seen, in the above manual script conversion process, the scriptwriter manually processes the whole process, and the overall processing efficiency is low.

[0005] In view of this, the present disclosure provides an information processing method, an information processing apparatus, a computer program product, and an electronic device to improve the efficiency of script conversion to a certain extent.

[0006] According to a first aspect of the present disclosure, an information processing method is provided, the method comprising:

[0007] obtaining a to-be-converted object;

[0008] performing decomposition processing on the to-be-converted object to determine a plurality of script entry point events of the to-be-converted object and script outline information corresponding to each of the script entry point events;

[0009] obtaining interaction mode information;

[0010] generating a plurality of script scene contents according to the interaction mode information, the plurality of script entry point events, and the script outline information corresponding to each of the script entry point events.

[0011] In a possible implementation, the decomposition processing on the to-be-converted object to determine the plurality of script entry point events of the to-be-converted object and the script outline information corresponding to each of the script entry point events comprises:

[0012] performing structured data extraction processing on the to-be-converted object to obtain a role relationship matrix, a plot conflict graph, and a world view element library;

[0013] determining the plurality of script entry point events of the to-be-converted object according to the role relationship matrix, the plot conflict graph, and the world view element library;

[0014] According to the plurality of script breakpoint events, script outline information corresponding to each of the script breakpoint events is generated.

[0015] In a possible implementation, according to the role relationship matrix, the plot conflict graph, and the world view element library, a plurality of script breakpoint events of the to-be-converted object are determined, including:

[0016] The plot conflict graph is scanned to determine a plurality of target paragraph contents, and plot density information of each of the target paragraph contents is determined;

[0017] According to each of the target paragraph contents and the role relationship matrix, role weight information of each of the target paragraph contents is determined;

[0018] According to each of the target paragraph contents and the world view element library, world view uniqueness information of each of the target paragraph contents is determined;

[0019] According to the plot density information, the role weight information, and the world view uniqueness information of each of the target paragraph contents, a plurality of script breakpoint events are determined.

[0020] In a possible implementation, the plot conflict graph is scanned to determine a plurality of target paragraph contents, including:

[0021] The number of conflict events marked in the plot conflict graph by a preset number of characters is determined by using a sliding window algorithm;

[0022] When the number information is greater than a preset threshold, the preset number of characters are determined as target paragraph contents.

[0023] In a possible implementation, according to each of the target paragraph contents and the role relationship matrix, role weight information of each of the target paragraph contents is determined, including:

[0024] For each of the target paragraph contents, the following operations are performed:

[0025] A to-be-compared role included in the target paragraph content is determined;

[0026] In the role relationship matrix, a core role matched with each of the to-be-compared roles is determined, and role weight information of the target paragraph content is determined according to weight information of the core role.

[0027] In a possible implementation, according to each of the target paragraph contents and the world view element library, world view uniqueness information of each of the target paragraph contents is determined, including:

[0028] For each of the target passage content, the following operations are performed:

[0029] determining the to-be-compared elements included in the target passage content;

[0030] determining rare elements matching the respective to-be-compared elements in the world view element library, and determining world view uniqueness information of the target passage content according to the rare elements.

[0031] In a possible implementation, the plurality of script entry point events are determined according to the plot density information, the character weight information, and the world view uniqueness information of each of the target passage content, including:

[0032] determining comprehensive information of each of the target passage content according to the plot density information, the character weight information, and the world view uniqueness information of each of the target passage content;

[0033] sorting the plurality of target passage contents according to the comprehensive information of each of the target passage content and the historical behavior data of the first object, to obtain sorting result information;

[0034] screening, according to the sorting result information, target passage contents as script entry point events from the plurality of target passage contents, to obtain the plurality of script entry point events.

[0035] In a possible implementation, the screening, according to the sorting result information, target passage contents as script entry point events from the plurality of target passage contents includes:

[0036] receiving selection information of a second object;

[0037] screening, according to the selection information and the sorting result information, target passage contents as script entry point events from the plurality of target passage contents.

[0038] In a possible implementation, the plurality of script scene contents are generated according to the interaction mode information, the plurality of script entry point events, and script outline information corresponding to each of the script entry point events, including:

[0039] For each of the script entry point events, the following operations are performed:

[0040] analyzing and processing the script outline information corresponding to the script entry point event to determine script scene description information;

[0041] performing scene keyword extraction processing on the script scene description information to generate image generation prompt words and audio generation prompt words;

[0042] The scene interaction mode information corresponding to the conflict type of the script cut-in point event in the plot conflict graph is filtered from the interaction mode information as the scene interaction mode information of the script cut-in point event.

[0043] The script scene content is generated according to the script scene description information, the image generation prompt word, the audio generation prompt word, and the scene interaction mode information.

[0044] In a possible implementation, the scene interaction mode information corresponding to the conflict type of the script cut-in point event in the plot conflict graph is filtered from the interaction mode information as the scene interaction mode information of the script cut-in point event, including:

[0045] The first interaction form information matching the conflict type is filtered from the interaction mode information.

[0046] A matching element in the script cut-in point event that matches the world view element library is determined, and first specific interaction information corresponding to the matching element is determined, and second interaction form information of the first specific interaction information is generated.

[0047] The interaction form information of the script cut-in point event is determined according to the first interaction form information and the second interaction form information.

[0048] In a possible implementation, the script outline information corresponding to the script cut-in point event is analyzed and processed to determine the script scene description information, including:

[0049] The stage description information of the script cut-in point event is determined according to the script outline information corresponding to the script cut-in point event.

[0050] The plot branch information of the user selectable item is determined according to the scene description information of each development stage in the stage description information.

[0051] The script scene description information is determined according to the stage description information, the scene description information of each development stage, and the plot branch information of the user selectable item.

[0052] In a possible implementation, the stage description information of the script cut-in point event is determined according to the script outline information corresponding to the script cut-in point event, including:

[0053] The event flow of the context original text of the script cut-in point event is determined according to the script outline information corresponding to the script cut-in point event.

[0054] The event flow is analyzed according to the plot conflict graph to determine a plurality of development stages of the script cut-in point event, and the stage description information is determined according to the plurality of development stages.

[0055] In a possible implementation, the method further includes:

[0056] In a possible implementation, the method further includes:

[0057] In a possible implementation, the method further includes:

[0058] In a possible implementation, the method further includes:

[0059] In a possible implementation, the method further includes:

[0060] In a possible implementation, the method further includes:

[0061] In a possible implementation, the method further includes:

[0062] In a possible implementation, the method further includes:

[0063] In a possible implementation, the method further includes:

[0064] In a possible implementation, the method further includes:

[0065] In a possible implementation, the method further includes:

[0066] In a possible implementation, the method further includes:

[0067] In a possible implementation, the method further includes:

[0068] In a possible implementation, the method further includes:

[0069] According to historical behavior data of the first object, the target plot is adjusted to obtain a new plot, and the new plot is displayed.

[0070] In a possible implementation, the method further includes:

[0071] Obtaining total record information of the first object;

[0072] Performing clustering processing on the total record information, determining type information corresponding to the first object, and generating to-be-shared content corresponding to the first object according to the type information and the total record information.

[0073] According to a second aspect of the present disclosure, an information processing apparatus is provided, and the apparatus includes:

[0074] An acquisition unit configured to determine a to-be-converted object;

[0075] A processing unit configured to perform decomposition processing on the to-be-converted object, determine a plurality of script entry point events of the to-be-converted object and script outline information corresponding to each of the script entry point events;

[0076] A first generation unit configured to determine interaction mode information, and generate a plurality of script scene contents according to the interaction mode information, the plurality of script entry point events and the script outline information corresponding to each of the script entry point events.

[0077] In a possible implementation, the processing unit is specifically configured to:

[0078] Perform structural data extraction processing on the to-be-converted object to obtain a role relationship matrix, a plot conflict graph and a world view element library;

[0079] Determine the plurality of script entry point events of the to-be-converted object according to the role relationship matrix, the plot conflict graph and the world view element library;

[0080] Generate the script outline information corresponding to each of the script entry point events according to the plurality of script entry point events.

[0081] In a possible implementation, the processing unit is specifically configured to:

[0082] Perform scanning processing on the plot conflict graph to determine a plurality of target paragraph contents and determine plot density information of each of the target paragraph contents;

[0083] Determine role weight information of each of the target paragraph contents according to each of the target paragraph contents and the role relationship matrix, respectively;

[0084] According to each of the target paragraph content and the world view element library, world view uniqueness information of each of the target paragraph content is determined.

[0085] According to the plot density information, the role weight information and the world view uniqueness information of each of the target paragraph content, a plurality of script entry point events are determined.

[0086] In a possible implementation, the processing unit is specifically configured to:

[0087] The number information of the conflict events marked in the plot conflict graph is determined by using a sliding window algorithm.

[0088] When the number information is greater than a preset threshold, the text in the preset number is determined as the target paragraph content.

[0089] In a possible implementation, the processing unit is specifically configured to:

[0090] For each of the target paragraph content, the following operations are performed:

[0091] A to-be-compared role included in the target paragraph content is determined.

[0092] In the role relationship matrix, a core role matched with each of the to-be-compared roles is determined, and the role weight information of the target paragraph content is determined according to the weight information of the core role.

[0093] In a possible implementation, the processing unit is specifically configured to:

[0094] For each of the target paragraph content, the following operations are performed:

[0095] A to-be-compared element included in the target paragraph content is determined.

[0096] In the world view element library, a rare element matched with each of the to-be-compared elements is determined, and the world view uniqueness information of the target paragraph content is determined according to the rare element.

[0097] In a possible implementation, the processing unit is specifically configured to:

[0098] According to the plot density information, the role weight information and the world view uniqueness information of each of the target paragraph content, comprehensive information of each of the target paragraph content is determined.

[0099] According to the comprehensive information of each of the target paragraph content and the historical behavior data of the first object, the plurality of target paragraph contents are sorted to obtain sorting result information.

[0100] According to the sorting result information, target paragraph contents serving as script entry point events are screened out from the multiple target paragraph contents to obtain multiple script entry point events.

[0101] In a possible implementation, the processing unit is specifically configured to:

[0102] receiving selection information of a second object;

[0103] According to the selection information and the sorting result information, target paragraph content serving as a script entry point event is screened out from the plurality of target paragraph contents.

[0104] In a possible implementation manner, the first generating unit is specifically configured to:

[0105] For each of the script entry point events, perform the following operations:

[0106] Analyze and process the script outline information corresponding to the script entry point event to determine the script scene description information;

[0107] Performing scene keyword extraction processing on the script scene description information to generate image generation prompt words and audio generation prompt words;

[0108] Filtering, from the interaction mode information, scene interaction mode information corresponding to the conflict type of the script entry point event in the plot conflict map as the scene interaction mode information of the script entry point event;

[0109] The script scene content is generated according to the script scene description information, the image generation prompt words, the audio generation prompt words and the scene interaction mode information.

[0110] In a possible implementation manner, the first generating unit is specifically configured to:

[0111] Filtering first interaction form information matching the conflict type from the interaction mode information;

[0112] Determining a matching element in the script entry point event that matches the worldview element library, determining first specific interaction information corresponding to the matching element, and generating second interaction form information corresponding to the first specific interaction information;

[0113] The interactive form information of the script entry point event is determined according to the first interactive form information and the second interactive form information.

[0114] In a possible implementation manner, the first generating unit is specifically configured to:

[0115] According to script outline information corresponding to the script breakpoint event, determine stage description information of the script breakpoint event;

[0116] According to scene description information of each development stage in the stage description information, determine plot branch information of user selectable items;

[0117] According to the stage description information, the scene description information of each development stage, and the plot branch information of user selectable items, determine the script scene description information.

[0118] In a possible implementation, the first generation unit is specifically configured to:

[0119] According to script outline information corresponding to the script breakpoint event, determine event flow of the context original text of the script breakpoint event;

[0120] According to the plot conflict graph, analyze the event flow to determine a plurality of development stages of the script breakpoint event, and according to the plurality of development stages, determine stage description information.

[0121] In a possible implementation, the first generation unit is specifically configured to:

[0122] According to scene description information of each development stage in the stage description information, perform causal chain design processing on each user selectable item to obtain corresponding plot branch information;

[0123] The plot branch information includes result type information for indicating plot development and a dynamic adjustment hook for adjusting plot development according to a trigger condition check or a probability event.

[0124] In a possible implementation, the apparatus further includes a second generation unit, specifically configured to:

[0125] Obtain a target script breakpoint event, and select target script scene content matched with the target script breakpoint event;

[0126] Generate target plot corresponding to the target script scene content, and display the target plot.

[0127] In a possible implementation, the apparatus further includes a second generation unit, specifically configured to:

[0128] Input the target script scene content and an additional constraint condition into a first model to generate a text plot; the additional constraint condition includes a role consistency constraint sub-condition, an element constraint sub-condition, and a branch depth constraint sub-condition;

[0129] Input the image generation prompt word and the audio generation prompt word in the target script scene content into a second model to generate scene multimedia information.

[0130] Perform cross-modal alignment verification processing on the text plot and the scene multimedia information to generate a target plot.

[0131] In a possible implementation, the apparatus further includes a second generation unit, specifically configured to:

[0132] Receive operation information of a first object for the target plot;

[0133] According to the operation information, determine a sub-plot in the target plot to display the sub-plot; or,

[0134] According to the operation information, generate a new sub-plot to display the new sub-plot; or,

[0135] According to historical behavior data of the first object, adjust the target plot to obtain a new plot to display the new plot.

[0136] In a possible implementation, the apparatus further includes a second generation unit, specifically configured to:

[0137] Obtain total record information of the first object;

[0138] Perform clustering processing on the total record information to determine type information corresponding to the first object, and generate to-be-shared content corresponding to the first object according to the type information and the total record information.

[0139] According to a third aspect of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the method of the first aspect and possible implementation manners thereof.

[0140] According to a fourth aspect of the present disclosure, an electronic device is provided, including a processor and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the executable instructions to perform the method of the first aspect and possible implementation manners thereof.

[0141] The technical solution of the present disclosure has the following beneficial effects:

[0142] In the embodiments of the present disclosure, the object to be converted can be acquired, and the object to be converted is automatically decomposed to determine a plurality of script entry point events of the object to be converted and script outline information corresponding to each script entry point event; interaction mode information is acquired, and then a plurality of script scene contents are automatically generated according to the interaction mode information, the plurality of script entry point events and the script outline information corresponding to each script entry point event. That is, in the embodiments of the present disclosure, the object to be converted, for example, book content, can automatically generate a plurality of script scene contents, and the script generation speed is more than several times of manual writing, greatly improving the script generation efficiency, and making the operation work change from the content production side to the content audit, thereby reducing the content production cost to a certain extent.

[0143] Other features and advantages of the present disclosure will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present disclosure. The objects and other advantages of the present disclosure can be achieved and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0144] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the embodiments of the present disclosure will be briefly introduced below. Obviously, the drawings introduced below are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0145] Figure 1 An application scenario schematic diagram in the present exemplary embodiment is shown;

[0146] Figure 2 A schematic diagram of an information processing method in the present exemplary embodiment is shown;

[0147] Figure 3 A flowchart of an information processing method in the present exemplary embodiment is shown;

[0148] Figure 4 A flowchart of determining target passage content in the present exemplary embodiment is shown;

[0149] Figure 5 A flowchart of generating script scene content in the present exemplary embodiment is shown;

[0150] Figure 6 A schematic diagram of script scene content in the present exemplary embodiment is shown;

[0151] Figure 7 A schematic diagram of a target plot in the present exemplary embodiment is shown;

[0152] Figure 8 A scenario diagram showing one target scenario interactive in the present exemplary embodiment;

[0153] Figure 9 A diagram showing one user type classification in the present exemplary embodiment;

[0154] Figure 10 A diagram showing one content to be shared in the present exemplary embodiment;

[0155] Figure 11 A diagram showing the structure of an information processing apparatus in the present exemplary embodiment;

[0156] Figure 12 A diagram showing the structure of an electronic device in the present exemplary embodiment. DETAILED DESCRIPTION

[0157] For the purpose of making the objects, technical solutions, and advantages of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part but not all of the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present disclosure. The embodiments in the present disclosure and the features in the embodiments can be combined with each other arbitrarily without conflict. Moreover, although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0158] In the specification and claims of the present disclosure, the term “comprising” and any variations thereof are intended to cover not exclusively. For example, a process, method, system, product, or device including a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to the process, method, product, or device.

[0159] One or more of the embodiments of the present disclosure, "multiple" refers to two or more than two. "And / or", which describes the association relationship of the associated objects, indicates that there can be three kinds of relationships, for example, A and / or B, which can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0160] It should be noted that the terms "first", "second", and the like in the description, claims, and drawings of the present disclosure, and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order, sequence, size, and priority, for example, the first interaction form information and the second interaction form information in the embodiments of the present disclosure, which are only used to distinguish different interaction form information. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The implementation described in the following exemplary embodiments does not represent all implementations consistent with the present disclosure. Instead, they are only examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0161] The exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which are schematic illustrations of the present disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the drawings can be functional entities, which do not necessarily have to correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in hardware modules or integrated circuits, or in networks, processors or microcontrollers. The implementation can be implemented in various forms and should not be understood as being limited to the examples set forth herein. The features, structures or characteristics described in the present disclosure can be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to give a sufficient understanding of the embodiments of the present disclosure. However, those skilled in the art should realize that one or more specific details can be omitted in the implementation of the technical solutions of the present disclosure, or other methods, components, devices, steps, etc. can be used instead of one or more specific details. It should be noted that in the embodiments of the present disclosure, the collection, transmission, use, display, etc. of data comply with relevant national laws and regulations. SUMMARY

[0163] Currently, the conversion of traditional book content into multi-modal scripts (such as films, games, and interactive reading) relies on manual scripting, which has problems such as low efficiency, high cost, and limited creativity.

[0164] In view of this, the embodiments of the present disclosure provide an information processing method, by which a to-be-converted object can be obtained, the to-be-converted object is automatically decomposed, a plurality of script entry point events of the to-be-converted object and script outline information corresponding to each script entry point event are determined, interaction mode information is obtained, and then a plurality of script scene contents are automatically generated according to the interaction mode information, the plurality of script entry point events, and the script outline information corresponding to each script entry point event. That is, in the embodiments of the present disclosure, the to-be-converted object, for example, book content, can be automatically converted into a plurality of script scene contents, the script generation speed is increased by more than several times compared with manual writing, the script generation efficiency is greatly improved, and the operation work is changed from a content production party to a content review, thereby reducing the content production cost to a certain extent.

[0165] After introducing the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure will be specifically introduced below.

[0166] Overview of application scenarios

[0167] To better understand the technical solutions provided by the embodiments of the present disclosure, the application scenarios to which the technical solutions provided by the embodiments of the present disclosure are applied will be briefly introduced below. It should be noted that the following application scenarios are only used to illustrate the embodiments of the present disclosure and are not limiting. In specific implementation, the technical solutions provided by the embodiments of the present disclosure can be flexibly applied according to actual needs.

[0168] In the embodiments of the present disclosure, in order to facilitate understanding of the technical solutions provided by the present disclosure, some key terms related to the present disclosure will be introduced first below:

[0169] Experience copy: Through artificial intelligence (AI), a novel main line is constructed, secondary story lines, character development, and background settings related to the main line are presented to enrich story content, expand world view, increase reading interest and depth, and at the same time, based on user interaction behavior and preset rules, a personalized branch path is provided to convert traditional linear content into a multi-dimensional experience space. In the following, it can also be referred to as a target plot.

[0170] Sliding window algorithm: By maintaining a dynamic window that slides on the data structure, the time complexity is optimized and repeated calculations are reduced. For example, in the book content analysis stage, the sliding window algorithm is used to quantify the local plot density, high-conflict paragraphs are identified through dynamic scanning of the text, precise entry point candidates are provided for the AI engine to generate experience copies, the complexity is reduced, the calculation efficiency is improved, and the calculation time is reduced.

[0171] Extreme Gradient Boosting Tree (XGBoost): In the embodiments of the present disclosure, it is used to predict the probability of users' potential entry points for books, and by analyzing historical behavior data and content features, it provides personalized entry point recommendation ranking for operators, significantly improving user engagement after copy generation.

[0172] Contrastive Language-Image Pretraining (CLIP): CLIP model is a multi-modal neural network that realizes cross-modal association between text and image through contrastive learning. In the scenario construction link of the embodiments of the present disclosure, CLIP plays a key role in semantic alignment and content generation guidance.

[0173] K-means clustering algorithm: It is an unsupervised learning algorithm that divides data into several groups (clusters) so that the similarity within the same cluster is high, and the difference between different clusters is large. For example, in the experience copy, K-means can be used for user behavior analysis and user classification to provide personalized experience.

[0174] Role relationship matrix: It is a tool that sorts out the relationships between characters in a structured way, aiming to clearly present the interaction logic, emotional ties, interest conflicts and identity relationships between characters. Among them, multiple relationships include emotional dimensions (such as family, love, friendship, hostility, worship) relationships, social attributes (such as teacher-student, superior-subordinate, allies, blood relatives) relationships; event association (such as participants who have experienced certain events, collaborators or competitors of a certain goal) relationships; dynamic evolution (such as the process of changing from hostility to reconciliation) relationships, etc. In the embodiments of the present disclosure, the association weights of cooperation, hostility, blood relationship between characters can be analyzed based on the role relationship matrix.

[0175] Conflict graph: It is a tool that presents the contradiction context of the story in a visual or structured way, aiming to systematically sort out the types, levels and evolution trajectories of conflicts, and reveal the internal driving force of plot development. It usually takes the form of a context diagram or a hierarchical framework, and the core elements include: conflict type: marking specific contradiction attributes (such as inner struggle of oneself, interest opposition of others, survival confrontation with environment); conflict subject: clarifying the characters or forces involved in the contradiction (such as the confrontation between the protagonist and the villain, the interest struggle between families); conflict intensity: dividing the intensification stages of the contradiction (such as foreshadowing, gradual escalation, climax, and residual dissipation); and correlation context: presenting the intersection points of different conflict lines (such as how secondary conflicts promote the escalation of main conflicts), etc. In the embodiments of the present disclosure, key event nodes and their emotional intensity values (0-10 points) can be marked based on the conflict graph.

[0176] Worldview element library: is the core tool of systematic integration of the space-time background of story occurrence, rule system and setting details, aims to build logically consistent foundation for fictional world, ensure that the plot and character behavior comply with the inherent laws of the world. It usually collects the following core elements in the form of entries: spatiotemporal framework: clearly the geographical map of the world, historical era, civilization development stage; rule system: covers natural laws (such as magic operation principle, superpower limitation), social system (such as cultivation level, interstellar federation political system), cultural customs (such as festivals); material composition: including unique species, technology level, special items (such as magic props, energy sources); implicit logic: extract the value core and contradiction source of the world. In the embodiments of the present disclosure, the magic system, power distribution, geographical environment, etc. can be determined based on the worldview element library.

[0177] In the embodiments of the present disclosure, information processing technology can be applied to various book works for script conversion corresponding business scenarios, which are not limited in the embodiments of the present disclosure.

[0178] Please refer to Figure 1 , Figure 1 is one of the application scenarios that the technical solutions of the embodiments of the present disclosure can be applied to. In the scene diagram, it includes terminal devices 110 and service devices 120, wherein the plurality of terminal devices 110 are devices corresponding to users of each to-be-generated script, Figure 1 The service device 120 can be understood as a server that provides conversion services for the to-be-converted object. The service device 120 and the terminal device 110 can be directly or indirectly connected through one or more networks 130.

[0179] In the embodiments of the present disclosure, the operator can log in to the corresponding service platform through the terminal device 110, and then determine the to-be-converted object, so that the artificial intelligence core processing system (AI engine) deployed in the service device 120 can obtain the conversion object and perform decomposition processing on the to-be-converted object to determine a plurality of script entry point events of the to-be-converted object and script outline information corresponding to each script entry point event; obtain interaction mode information, and then generate a plurality of script scene contents according to the interaction mode information, the plurality of script entry point events and the script outline information corresponding to each script entry point event.

[0180] Among them, the AI engine refers to a core system integrating artificial intelligence algorithms, models and computing capabilities. Through the AI engine, data processing, model training and reasoning can be performed to realize intelligent decision-making, pattern recognition, natural language processing and other tasks. In other words, the AI engine in the embodiments of the present disclosure can include a plurality of models, such as an audio generation model, a large language model, an image generation model, etc.

[0181] In the embodiments of the present disclosure, when the AI engine generates a plurality of script scene contents, referring to FIG. 6, the operator can also select a target script entry point event, so that the AI engine can generate a target plot. Further, the service device 120 can publish the target plot on a service platform, so that the user can operate on the target plot on the service platform, so that the AI engine can receive the operation information of the user on the target plot, determine a sub-plot in the target plot according to the operation information, and display the sub-plot; or generate a new sub-plot according to the operation information, and display the new sub-plot; or adjust the target plot according to the historical behavior data of the first object, obtain a new plot, and display the new plot. Figure 2

[0182] The terminal device 110 in FIG. 1 can be a mobile phone, a tablet computer (PAD), a personal computer (PC), a smart television, a smart watch, a smart speaker, a smart vehicle device, a wearable device, and the like, but is not limited thereto. Figure 1 The service device 120 in FIG. 1 can also be a stand-alone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server or cloud server cluster that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, but is not limited thereto.

[0183] Figure 1 The service device 120 in FIG. 1 can also be a stand-alone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server or cloud server cluster that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, but is not limited thereto.

[0184] Of course, the method provided by the embodiments of the present disclosure is not limited to the application scenarios shown in FIG. 1, and can also be used in other possible application scenarios, for example, the service device obtains the to-be-converted object and processes the to-be-converted object, and the embodiments of the present disclosure do not limit this. That is, the technical solutions provided by the embodiments of the present disclosure can be independently implemented by the service device, or jointly implemented by the terminal device and the service device, and the embodiments of the present disclosure do not limit this. Figure 1

[0185] Exemplary method

[0186] ​​To further illustrate the technical solutions provided by the embodiments of the present disclosure, the following will describe in detail in combination with the drawings and specific embodiments. Although the embodiments of the present disclosure provide the method operation steps as described in the following embodiments or shown in the drawings, more or less operation steps can be included in the method based on conventional or non-creative labor. The execution order of the steps is not limited to the execution order provided by the embodiments of the present disclosure in logically unnecessary causal relationship. The method can be executed in sequence or in parallel when the actual processing process or the device is executed according to the method order shown in the embodiments or drawings.

[0187] Please refer to Figure 3 , Figure 3 The flowchart of an information processing method in the embodiments of the present disclosure. The flow of the method may, for example, be executed by an electronic device, such as a service device 120 in Figure 1 The specific implementation process of the method is as follows:

[0188] Step 301: Obtain a to-be-converted object.

[0189] In the embodiments of the present disclosure, the electronic device can determine the to-be-converted object according to a preset rule, wherein the preset rule is, for example, to select the book with the highest user preference or the highest reading volume in the service platform as the to-be-converted object, or to select the book with the highest recommendation volume as the to-be-converted object. Of course, other rules are also possible, which are not limited in the embodiments of the present disclosure.

[0190] In the embodiments of the present disclosure, the user can determine the to-be-converted object through the service platform, so that the terminal device sends a conversion request carrying the to-be-converted object to the electronic device, so that the electronic device can determine the to-be-converted object based on the conversion request.

[0191] In the embodiments of the present disclosure, the to-be-converted object obtained by the electronic device can be understood as a book, that is, a publication recorded by text, image or other symbol system and presented in the form of bound books.

[0192] Step 302: Decompose the to-be-converted object to determine a plurality of script entry point events of the to-be-converted object and script outline information corresponding to each script entry point event.

[0193] In the embodiments of the present disclosure, the electronic device can perform structured data extraction processing on the to-be-converted object to obtain a role relationship matrix, a plot conflict graph, and a world view element library, and then determine a plurality of script entry point events of the to-be-converted object according to the role relationship matrix, the plot conflict graph, and the world view element library. Thus, the script outline information corresponding to each script entry point event can be generated according to the plurality of script entry point events.

[0194] In the embodiments of the present disclosure, the electronic device can perform structured data extraction processing on the to-be-converted object by a natural language processing (NLP) technology and a Bidirectional Encoder Representations from Transformers (BERT) model, so as to obtain a role relationship matrix, a plot conflict graph, and a worldview element library. The role relationship matrix can analyze the association weights such as cooperation, hostility, and blood relationship between roles. The plot conflict graph can mark key event nodes and their emotional intensity values (0-10 points). The worldview element library can determine the magic system, power distribution, geographical environment, and the like.

[0195] In the embodiments of the present disclosure, referring to FIG. 4, the following steps can be used to determine the multiple script entry point events of the to-be-converted object, but are not limited thereto: Figure 4

[0196] Step 401: performing scanning processing on the plot conflict graph, determining multiple target paragraph contents, and determining plot density information of each target paragraph content.

[0197] In the embodiments of the present disclosure, the sliding window algorithm can be used to determine the number information of conflict events marked in the plot conflict graph within a preset number of words; when the number information is greater than a preset threshold, the words within the preset number are determined as the target paragraph content.

[0198] For example, the preset number is 1000 words, and the preset threshold is 3 intense conflicts. The electronic device can use the sliding window algorithm to calculate the number of conflict events per thousand words, and then check how many “conflict events” (such as quarrels, battles, and major discoveries) are marked in the plot conflict graph within this paragraph. Combined with the position and intensity of the “conflict events” marked in the plot conflict graph, the conflict event intensive area (such as more than 3 intense conflicts within a certain 1000 words) within the thousand words can be determined, which can be marked as a potential “target paragraph”, so that the target paragraph content can be determined.

[0199] Step 402: determining role weight information of each target paragraph content according to each target paragraph content and the role relationship matrix, respectively.

[0200] In the embodiments of the present disclosure, the following operations can be performed on each target paragraph content: determining the to-be-compared roles included in the target paragraph content; determining the core roles matched with each to-be-compared role in the role relationship matrix, and determining the role weight information of the target paragraph content according to the weight information of the core roles.

[0201] ​In the disclosed embodiment, after determining the target paragraph, the AI ​​engine uses the character relationship matrix to determine whether the target paragraph is "worth exploring further." Specifically, the AI ​​engine can use the character relationship matrix to display the importance of all characters in the book and their relationships (who is an ally, enemy, lover, etc.) to determine which core characters (usually protagonists or important supporting characters with high weights in the matrix) are involved in the target paragraph. The more core characters involved in the target paragraph and the more intense the relationship conflicts (such as a head-on confrontation between two enemies), the higher the "character weight" of the target paragraph will be.

[0202] Step 403: Determine the unique worldview information of each target paragraph content based on the content of each target paragraph and the worldview element library;

[0203] In the embodiment of the present disclosure, the following operations can be performed on each target paragraph content: determining the elements to be compared included in the target paragraph content; determining rare elements that match each element to be compared in the world view element library, and determining the world view uniqueness information of the target paragraph content based on the rare elements.

[0204] In the disclosed embodiment, after determining the target paragraph, the AI ​​engine can check the "rarity" of the elements (places, items, rules, organizations, etc.) that appear in this target paragraph in the world view element library. Among them, the world view element library records all the set elements under the world view of the object to be converted. In this way, when it is determined that the target paragraph contains very unique elements in the book that are rarely seen elsewhere (such as a mysterious lost magic / sword manual, a place that only appears in legends), the "world view uniqueness" score of the target paragraph will be high. This unique performance can increase the freshness of the experience.

[0205] Step 404: Determine multiple script entry point events based on the plot density information, character weight information, and worldview uniqueness information of each target paragraph content.

[0206] In the disclosed embodiment, comprehensive information of each target paragraph content can be determined based on the plot density information, character weight information, and world view uniqueness information of each target paragraph content; multiple target paragraph contents can be sorted based on the comprehensive information of each target paragraph content and the historical behavior data of the first object to obtain sorting result information; based on the sorting result information, target paragraph contents that serve as script entry point events can be screened out from the multiple target paragraph contents to obtain multiple script entry point events.

[0207] In the embodiments of the present disclosure, the AI engine can add the plot density information, the character weight information and the world view uniqueness information of the target paragraph content obtained in the above three steps according to a preset ratio (for example, 6:3:1) to obtain a comprehensive priority score as the comprehensive information of the target paragraph content. At the same time, the AI can call the XGBoost model. Based on the XGBoost model, the historical behavior data of the user (for example, whether the user likes to watch battles or solve puzzles in the past, and which character the user pays more attention to) can be analyzed, so that the XGBoost model can predict the degree of interest of the current user in the potential cut-in point paragraph, and determine the sorting information of the target paragraph content by combining the degree of interest and the comprehensive information, and then the sorting result information of the multiple target paragraph contents can be obtained. In this way, the target paragraph content serving as the script cut-in point event can be selected from the multiple target paragraph contents according to the sorting result information, so as to obtain multiple script cut-in point events.

[0208] Optionally, the selection information of the second object can be received, and then the target paragraph content serving as the script cut-in point event can be selected from the multiple target paragraph contents according to the selection information and the sorting result information.

[0209] In the embodiments of the present disclosure, the Top10 candidate cut-in point list can be output for the operation personnel to check, and when the check information of the operation personnel is received, the target paragraph content serving as the script cut-in point event can be selected from the multiple target paragraph contents according to the selection information and the sorting result information.

[0210] Step 303: obtaining interaction mode information;

[0211] In the embodiments of the present disclosure, the interaction mode information can be determined by the electronic device according to historical experience, or the interaction mode information can be determined by the operation personnel, so that the service platform deployed on the electronic device can obtain the interaction mode information, and the present disclosure does not limit this.

[0212] The interaction mode information can be understood as a set of interaction modes developed in advance, including branch options, voice dialogues, time sequence operations (for example, time limit and continuous hit), multi-sensory feedback (for example, vibration, sound effect, gyroscope and step count), and the present disclosure does not limit this.

[0213] Step 304: generating multiple script scene contents according to the interaction mode information, the multiple script cut-in point events and the script outline information corresponding to each script cut-in point event.

[0214] In the embodiments of the present disclosure, referring to FIG. 3, the following operations can be performed on each script cut-in point event to generate the corresponding script scene content, including: Figure 5

[0215] ​Step 501: Analyzing and processing the script outline information corresponding to the script cut-in point event to determine the script scene description information.

[0216] In the embodiments of the present disclosure, the stage description information of the script cut-in point event can be determined according to the script outline information corresponding to the script cut-in point event, then the plot branch information of the user selectable item can be determined according to the scene description information of each development stage in the stage description information, and the script scene description information can be determined according to the stage description information, the scene description information of each development stage, and the plot branch information of the user selectable item.

[0217] Optionally, the event flow of the context original text of the script cut-in point event can be determined according to the script outline information corresponding to the script cut-in point event, and the event flow can be analyzed according to the plot conflict graph to determine a plurality of development stages of the script cut-in point event, and the stage description information can be determined according to the plurality of development stages.

[0218] The stage description information can be understood as decomposing the cut-in point event into logically coherent "acts" to guide the user experience rhythm. The stage description information can be the event flow of the context original text analyzed by the AI engine, combined with the "cause and effect" nodes of the event in the plot conflict graph.

[0219] Optionally, the stage division includes: (1) Cause stage: the direct cause of the occurrence of the cut-in point event. For example, why does the main character touch the attack prop 2? Is it exploration or accident? (2) Conflict outbreak stage: the occurrence of the core event, such as the awakening of the antagonist A and the confrontation of the enemy. (3) Upgrade / choice stage: the user needs to make a key selection. For example, fighting, escaping, communicating, etc. (4) Climax / solution stage: the direct consequences of the selection. For example, the results of the battle, the success of the escape, the feedback of the communication, etc. (5) Aftermath / transition stage: the influence on the subsequent plot after the end of the event. For example, obtaining an item, triggering a new clue, state change, etc.

[0220] For example, the stage description information is: ["triggering mechanism", "antagonist A awakens and confronts", "time-limited choice", "battle climax", "scene n vibration escape"].

[0221] In the embodiments of the present disclosure, the AI engine can generate user-selectable options that conform to the characters, world view and drive the plot based on the current stage and in combination with core constraint driving information and diversified design information. The core constraint driving information includes: constraint driving information for the character relationship matrix, which is that the options need to reflect the relationship between characters. For example, under a high enemy value, the success rate of the "sincere apology" option is extremely low and may appear abrupt. The constraint driving information for the world view element library is that the options have available means. For example, trigger the "use attack prop 2" option because attack prop 2 has a light attribute and is effective against the villain character A; trigger "throw XXX" if the user has obtained the "XXX" prop. The constraint driving information for the plot conflict intensity is that the options need to match the tension, for example, "negotiate slowly" may not be appropriate under an intensity of 8.5. The user-selectable options need to meet at least one of the above three constraint driving information. The diversified design information can be understood as information that provides options with different risks / policies, such as attack, defense, wisdom, and escape.

[0222] In the embodiments of the present disclosure, the main AI in the AI engine gives an option framework based on the diversified design information, for example, "[attack] [defense] [use item] [special ability]", and the sub-AI fills in specific text based on the preset model and checks whether it meets the constraints based on the core constraint driving information (such as the "use item" option automatically associates with the available and world view-compliant props in the user's backpack), thereby generating user-selectable options.

[0223] For example, the user-selectable options are: [quick thrust]: attack with speed advantage, high risk but may interrupt the villain character A from continuing to attack; [shield defense]: block the first wave of attack from the villain character A and look for a counterattack opportunity; [raise XXX]: try to activate the light power of XXX to dispel the villain character A! (XXX needs to be obtained); [throw XXX]: create chaos and escape! (XXX needs to be in the backpack).

[0224] In the embodiments of the present disclosure, when the AI engine determines the user-selectable options, it can preset the direct plot branches caused by different options to determine the plot branch information of the user-selectable options.

[0225] In the embodiments of the present disclosure, the causal chain design processing can be performed on each user-selectable option according to the scene description information of each development stage in the stage description information, and the corresponding plot branch information is obtained; wherein the plot branch information includes result type information for indicating plot development and dynamic adjustment hooks for adjusting plot development according to trigger conditions or probability events.

[0226] In the embodiments of the present disclosure, the AI engine can correspond to each user selectable item a preset path ID. Among them, the main AI in the AI engine designs reasonable and meaningful results based on the role relationship matrix (for example, the strength of the villain character A, the ability of the main character), the world view element library (for example, the effect of XXX, the range of HHH) and the plot conflict intensity. Among them, the result type includes, for example: success / failure: based on the reasonableness of the options and the preset difficulty; state change: consume props (for example, consume XXX), change character state (for example, from normal to injured), affect relationship (for example, annoy the villain character A); advance / branch: unlock new area, get clues, guide to different sub-scenes. The dynamic adjustment hook may contain trigger condition check (for example, whether there is a prop) or probability event (for example, the success rate of XXX activation is 70%). In this way, the direct consequence description of each option selection and the jump of the subsequent stage / scene can be clearly described.

[0227] For example, assuming that the user selectable item is [hold up XXX], when the result is success (70%), the plot branch information is: “XXX bursts out of the burning white light! The villain character A emits a sharp and piercing scream, and the action is obviously delayed. Take this opportunity, you... ”→ Jump to the [battle climax-advantage] stage. When the result is failure (30%), the plot branch information is: “XXX only flickered weakly. The villain character A emits a mocking click sound, and attacks you, and you hurriedly block... ”→ Jump to the [battle climax-disadvantage] stage + the main character obtains the [light injury] state.

[0228] Step 502: Perform scene keyword extraction processing on the script scene description information to generate image generation prompt words and audio generation prompt words.

[0229] In the embodiments of the present disclosure, the AI engine can extract key nouns, adjectives and verbs in the script scene description. Then, supplement visual details in combination with the world view element library, such as “architectural style”, “white walls”, “XXX”, etc. Further, perform semantic enhancement and alignment through the CLIP model, identify core concepts, such as “scene 1”, “awakened villain character A”, “XXX”, “confrontation”, etc., and associate the most suitable visual style keywords, such as “movie-level light and shadow”, “dynamic perspective”, etc. And, filter out invalid or conflicting words, so as to output the image generation prompt words and the audio generation prompt words in a preset output format. Among them, the preset format is, for example, a comma-separated keyword list sorted by importance.

[0230] For example, the image generation prompt words and the audio generation prompt words are: “scene 1, architectural style, white walls, XXX, awakened villain character A (broken black clothes, long sword, dark eye makeup), falling stones, dynamic perspective, movie-level light and shadow, high detail, tense confrontation”.

[0231] Step 503: From the interaction mode information, screen the scene interaction mode information corresponding to the conflict type of the script cut-in point event in the plot conflict graph as the scene interaction mode information of the script cut-in point event.

[0232] In the embodiments of the present disclosure, the first interactive form information matching the conflict type can be screened from the interaction mode information; the matching element in the script cut-in point event matching the world view element library is determined, and the first specific interaction information corresponding to the matching element is determined, the second interactive form information of the first specific interaction information is generated; and the interactive form information of the script cut-in point event is determined according to the first interactive form information and the second interactive form information.

[0233] For example, if the conflict type is confrontation, the first interactive form information is determined to be "time-limited battle strategy selection" (button / gesture). If the conflict type is puzzle decryption, the first interactive form information is determined to be "prop combination / environment interaction" (drag / gyroscope / scan). If the conflict type is plot choice, the first interactive form information is determined to be "multi-branch dialogue selection" (button). If the conflict type is exploration discovery, the first interactive form information is determined to be "free movement / click investigation" (virtual joystick / click).

[0234] For example, if it is determined that the matching element in the script cut-in point event matching the world view element library is a certain interaction requiring a specific prop / ability, such as "ZZZ" to select the "chant" option, the pre-developed interaction mode is determined to be voice, vibration, gyroscope, etc.

[0235] In this way, the interactive form information of the script cut-in point event can be determined according to the first interactive form information and the second interactive form information.

[0236] For example, if the conflict type is confrontation, the interactive form information of the script cut-in point event is determined to be "time-limited button selection (10-second countdown)" or "quick swipe hit (simulated attack action)".

[0237] Step 504: generating script scene content according to script scene description information, image generation prompt words, audio generation prompt words, and scene interaction mode information.

[0238] In the embodiments of the present disclosure, when the script scene description information, the image generation prompt words, the audio generation prompt words, and the scene interaction mode information are obtained, the AI engine can generate the script scene content. For example, referring to Figure 6 , a schematic diagram of script scene content is shown. Among them, Figure 6 is the script scene content generated by the AI engine processing a novel P. Figure 6 is the script scene content generated by the AI engine processing a novel P.

[0239] In a possible implementation, a target script breakpoint event can also be obtained, target script scene content matching the target script breakpoint event is selected, and a target plot corresponding to the target script scene content is generated to display the target plot. The target script breakpoint event can be determined by an operator, for example, and can also be determined by an AI engine based on historical experience or rules, which is not limited in the embodiments of the present disclosure. For example, refer to Figure 7 as shown, Figure 7 a schematic diagram of a target plot is shown. Wherein, Figure 7 a schematic diagram of a target plot opening interface and a schematic diagram of a scene plot interface of a specific scene are shown in the figure.

[0240] In the embodiments of the present disclosure, the target script scene content and the additional constraint conditions can be input into the first model to generate a text plot. The additional constraint conditions include a role consistency constraint sub-condition, an element constraint sub-condition, and a branch depth constraint sub-condition. For example, the target script scene content and the additional constraint conditions can be input into the first model, such as a large language model (LLM) model, to obtain text plot content. The role consistency constraint sub-condition is, for example, "deviation from original character personality deviation > 20%", the element constraint sub-condition is, for example, "prohibition of appearance of science and technology elements (such as firearms)", and the branch depth constraint sub-condition is, for example, "each selection needs to derive ≥3 layers of sub-plots". It should be noted that the role consistency constraint sub-condition, the element constraint sub-condition, and the branch depth constraint sub-condition can be updated and adjusted based on the content of the object to be converted, which is not limited in the embodiments of the present disclosure.

[0241] In addition, the image generation prompt words and the audio generation prompt words in the target script scene content can also be input into the second model to generate scene multimedia information. For example, the second model, such as an AI image engine (Stable Diffusion XL), can receive the image generation prompt words and the audio generation prompt words to generate scene graphs and character graphs, i.e., obtain scene multimedia information.

[0242] In the embodiments of the present disclosure, when the text plot and the scene multimedia information are obtained, the text plot and the scene multimedia information can be subjected to cross-modal alignment verification processing to generate a target plot.

[0243] For example, the resolution can be automatically adjusted according to the performance of the user equipment to complete dynamic rendering optimization of the scene multimedia information, and a multi-modal contrast learning model (such as an ImageBind model) can be used to perform cross-modal alignment verification processing on the text plot and the scene multimedia information to ensure the emotional consistency of the text, the image, and the audio, so that the error tolerance of the generated target plot is <5%.

[0244] In the embodiments of the present disclosure, after the target plot is obtained, operation information of the first object for the target plot can also be received; according to the operation information, a sub-plot in the target plot is determined, and the sub-plot is displayed; or, according to the operation information, a new sub-plot is generated, and the new sub-plot is displayed; or, according to the historical behavior data of the first object, the target plot is adjusted, a new plot is obtained, and the new plot is displayed.

[0245] Referring to Figure 8 , a plot example in which a target plot is interactive is shown. Figure 8 For example, if the user is in an exploration scene, the user can perform a left-looking operation, such as clicking or sliding the arrow in Figure 8 pointing to the left arrow to view the left environment, or performing a right-looking operation, such as clicking or sliding the arrow in Figure 8 pointing to the right arrow to view the right environment. For another example, if the user is in an open answer interactive scene, the user can input “answer” in Figure 8 . For another example, if the user is in an option type interactive scene, the user can click “option A” in Figure 8 , and call resources in the backpack to resist. That is, in the embodiments of the present disclosure, the user can perform user operations such as branch options, voice dialogues, time sequence operations (time limit, continuous hit), multi-sensory feedback (vibration, sound effect, gyroscope, step count), etc. on the target plot.

[0246] In the embodiments of the present disclosure, the terminal device can transmit user operations, such as branch options / voice dialogues / time sequence operations (time limit, continuous hit) / multi-sensory feedback (vibration, sound effect, gyroscope, step count), etc. to the service device, and then the service device can perform behavior analysis and record the option sentiment value, interaction time consumption, emotional feedback (microphone emotion recognition), etc. obtained by analysis.

[0247] In the embodiments of the present disclosure, when the user selects to match a preset branch, a cached plot is directly called to complete the calling of the preset path. When the user selects to deviate from the preset, the following processes are triggered: user abnormal selection, extraction of a current plot state vector, AI engine regeneration of a subsequent branch, and insertion of a temporary cache node. In addition, the plot can also be dynamically adjusted according to the analysis of the historical behavior of the user to realize personalized plot control.

[0248] In a possible implementation, the service device can also obtain total record information of the first object, perform clustering processing on the total record information, determine type information corresponding to the first object, and generate the to-be-shared content corresponding to the first object according to the type information and the total record information.

[0249] In the disclosed embodiments, the service device can perform real-time interaction data collection to record user decision-making behavior. For example, it can record: click speed (recording millisecond-level response timestamps), the length of time the option is displayed (interaction time), and emotional feedback (analyzing voice intonation fluctuations through microphones).

[0250] In the embodiment of the present disclosure, the total recorded information of the first object can be determined based on the recorded user decision-making behavior, and then the user types can be divided using the K-means Clustering Algorithm (K-means Clustering Algorithm).

[0251] For example, see Figure 9 As shown, Figure 9 This is a schematic diagram of an example user type classification. For example, if user A's total recorded information indicates a high frequency of clicking on hidden clues with an average dwell time of 9 seconds, then user A's type is determined to be suspenseful. It should be noted that in this embodiment of the disclosure, user type determination can be based on analysis of actual recorded user decision-making behavior, and this is not a limitation in this embodiment of the disclosure.

[0252] In the embodiment of the present disclosure, after obtaining the type information, the content to be shared corresponding to the first object can be generated based on the type information and the total record information. In other words, the content to be shared can be generated based on the data indicators. The content to be shared can be, for example, a personalized data card or title reward, which is convenient for users to share on social media. For example, see Figure 10 As shown, Figure 10 It is a schematic diagram of the content to be shared. Among them, different data indicators correspond to different personalized data cards or title rewards, and different plots correspond to different personalized data cards or title rewards, that is, the content to be shared can be determined based on the actual implementation, which is not limited in the embodiments of the present disclosure. For example, personalized data cards are, for example, decision-making style radar charts (suspense / passion / healing three dimensions, bond index (interaction frequency with core characters × emotional weight), achievement badges (such as "crack ancient puzzles within 10 seconds"), etc., which are not limited in the embodiments of the present disclosure.

[0253] In the embodiments of the present disclosure, a productization process is provided for inputting book content through a unified interface and automatically parsing and generating a structured outline (role relationship, plot conflict, world view label). Specifically, a modular product architecture based on "main AI generated outline and sub AI engine fills in scenes" can be used, in which the main AI agent (artificial intelligence agent) acts as the "director", and the sub AI acts as the "screenwriter / artist / sound effects" in a division of labor and cooperation mode. For example, the main AI outputs the "medieval battlefield | legion night raid" outline, the sub AI generates battle dialogues based on the LLM model, generates scene sketches based on the Stable Diffusion XL model, and generates war drum sound effects based on an audio generation model such as AudioLM, etc.

[0254] It can be seen that, compared with the manual writing method, the script scene content generated based on the AI engine can improve the generation efficiency of the overall script scene content by more than 10 times, and can support real-time rendering of a million-level branch plot, thereby reducing the content production cost. Moreover, in the embodiments of the present disclosure, based on the multi-modal alignment engine, the continuity of the plot can be ensured as much as possible, thereby improving the user immersion experience. In addition, since the embedding process is based on the pre-developed user interaction method, the AI understands the pre-set user interaction method and naturally integrates the interaction method into the plot, so that the user can be provided with an interaction form that is more consistent with the plot, so that the user can have a more immersive experience of the automatically generated plot, thereby improving the user experience.

[0255] Exemplary apparatus

[0256] The exemplary embodiments of the present disclosure also provide an information processing apparatus. Referring to Figure 11 As shown in the figure, the information processing apparatus 1100 includes the following program units:

[0257] The acquisition unit 1101 is configured to determine a to-be-converted object;

[0258] The processing unit 1102 is configured to perform decomposition processing on the to-be-converted object, determine a plurality of script cut-in point events of the to-be-converted object and script outline information corresponding to each script cut-in point event;

[0259] The first generation unit 1103 is configured to determine interaction method information, and generate a plurality of script scene contents according to the interaction method information, the plurality of script cut-in point events and the script outline information corresponding to each script cut-in point event.

[0260] In a possible implementation, the processing unit 1102 is specifically configured to:

[0261] perform structured data extraction processing on the to-be-converted object to obtain a role relationship matrix, a plot conflict graph, and a world view element library;

[0262] determine a plurality of script entry point events of the to-be-converted object according to the role relationship matrix, the plot conflict graph, and the world view element library;

[0263] generate script outline information corresponding to each of the script entry point events according to the plurality of script entry point events.

[0264] In a possible implementation, the processing unit 1102 is specifically configured to:

[0265] perform scanning processing on the plot conflict graph to determine a plurality of target paragraph contents, and determine plot density information of each of the target paragraph contents;

[0266] determine role weight information of each of the target paragraph contents according to each of the target paragraph contents and the role relationship matrix respectively;

[0267] determine world view uniqueness information of each of the target paragraph contents according to each of the target paragraph contents and the world view element library respectively;

[0268] determine a plurality of script entry point events according to the plot density information, the role weight information, and the world view uniqueness information of each of the target paragraph contents.

[0269] In a possible implementation, the processing unit 1102 is specifically configured to:

[0270] determine, by using a sliding window algorithm, quantity information of conflict events marked in the plot conflict graph for a preset quantity of texts;

[0271] when it is determined that the quantity information is greater than a preset threshold, determine that the texts in the preset quantity are target paragraph contents.

[0272] In a possible implementation, the processing unit 1102 is specifically configured to:

[0273] for each of the target paragraph contents, perform the following operations:

[0274] determine a to-be-compared role included in the target paragraph content;

[0275] determine, in the role relationship matrix, a core role matched with each of the to-be-compared roles, and determine role weight information of the target paragraph content according to weight information of the core role.

[0276] In a possible implementation, the processing unit 1102 is specifically configured to:

[0277] for each of the target paragraph contents, perform the following operations:

[0278] determining target passage content including to-be-compared elements;

[0279] In the world view element library, rare elements matching the to-be-compared elements are determined, and world view uniqueness information of the target passage content is determined according to the rare elements.

[0280] In a possible implementation, the processing unit 1102 is specifically configured to:

[0281] According to the plot density information, the character weight information, and the world view uniqueness information of each target passage content, comprehensive information of each target passage content is determined.

[0282] According to the comprehensive information of each target passage content and historical behavior data of the first object, the multiple target passage contents are sorted to obtain sorting result information.

[0283] According to the sorting result information, target passage contents serving as script entry point events are filtered out from the multiple target passage contents, to obtain multiple script entry point events.

[0284] In a possible implementation, the processing unit 1102 is specifically configured to:

[0285] receiving selection information of a second object;

[0286] According to the selection information and the sorting result information, target passage contents serving as script entry point events are filtered out from the multiple target passage contents.

[0287] In a possible implementation, the first generation unit 1103 is specifically configured to:

[0288] For each script entry point event, the following operations are performed:

[0289] The script outline information corresponding to the script entry point event is analyzed and processed to determine script scene description information;

[0290] The script scene description information is subjected to scene keyword extraction processing to generate image generation prompt words and audio generation prompt words;

[0291] From the interaction mode information, scene interaction mode information corresponding to a conflict type of the script entry point event in the plot conflict graph is filtered out as scene interaction mode information of the script entry point event;

[0292] According to the script scene description information, the image generation prompt words, the audio generation prompt words, and the scene interaction mode information, script scene content is generated.

[0293] In a possible implementation, the first generation unit 1103 is specifically configured to:

[0294] screen, from the interaction mode information, first interaction form information matching the conflict type;

[0295] determine a matching element in the script breakpoint event that matches the world view element library, determine first specific interaction information corresponding to the matching element, and generate second interaction form information corresponding to the first specific interaction information;

[0296] determine, according to the first interaction form information and the second interaction form information, the interaction form information of the script breakpoint event.

[0297] In a possible implementation, the first generation unit 1103 is specifically configured to:

[0298] determine, according to script outline information corresponding to the script breakpoint event, stage description information of the script breakpoint event;

[0299] determine, according to scene description information of each development stage in the stage description information, plot branch information of a user selectable item;

[0300] determine, according to the stage description information, the scene description information of each development stage, and the plot branch information of the user selectable item, the script scene description information.

[0301] In a possible implementation, the first generation unit 1103 is specifically configured to:

[0302] determine, according to script outline information corresponding to the script breakpoint event, an event flow of a context of the script breakpoint event;

[0303] analyze, according to the plot conflict graph, the event flow, determine a plurality of development stages of the script breakpoint event, and determine stage description information according to the plurality of development stages.

[0304] In a possible implementation, the first generation unit 1103 is specifically configured to:

[0305] perform, according to scene description information of each development stage in the stage description information, a causal chain design process on each user selectable item to obtain corresponding plot branch information;

[0306] The plot branch information includes result type information for indicating plot development and a dynamic adjustment hook for adjusting plot development according to a trigger condition check or a probability event.

[0307] In a possible implementation, the apparatus further includes a second generation unit, specifically configured to:

[0308] obtain a target script breakpoint event, select target script scene content matched with the target script breakpoint event;

[0309] generate a target plot corresponding to the target script scene content, and display the target plot.

[0310] In a possible implementation, the apparatus further includes a second generation unit, specifically configured to:

[0311] input the target script scene content and additional constraint conditions into a first model to generate a text plot; the additional constraint conditions include a role consistency constraint sub-condition, an element constraint sub-condition, and a branch depth constraint sub-condition;

[0312] input image generation prompt words and audio generation prompt words in the target script scene content into a second model to generate scene multimedia information;

[0313] perform cross-modal alignment verification processing on the text plot and the scene multimedia information to generate a target plot.

[0314] In a possible implementation, the apparatus further includes a second generation unit, specifically configured to:

[0315] receive operation information of a first object on the target plot;

[0316] determine a sub-plot in the target plot according to the operation information, and display the sub-plot; or

[0317] generate a new sub-plot according to the operation information, and display the new sub-plot; or

[0318] adjust the target plot according to historical behavior data of the first object to obtain a new plot, and display the new plot.

[0319] In a possible implementation, the apparatus further includes a second generation unit, specifically configured to:

[0320] obtain total record information of the first object;

[0321] perform clustering processing on the total record information, determine type information corresponding to the first object, and generate to-be-shared content corresponding to the first object according to the type information and the total record information.

[0322] The specific details of the above-mentioned parts of the apparatus have been described in detail in the method part of the embodiments, and the details not disclosed can be referred to the content of the method part of the embodiments, and thus will not be described again.

[0323] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, such division is not mandatory. Indeed, according to the example embodiments of the present disclosure, the features and functionalities of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functionalities of one module or unit described above can be further divided into embodied by multiple modules or units.

[0324] Exemplary program product

[0325] The example embodiments of the present disclosure also provide a computer program product. The computer program product includes a computer program which, when executed by a processor, implements the above information processing method.

[0326] In an embodiment, the computer program product can be a tangible product containing the computer program, such as a computer readable storage medium storing the computer program. The readable storage medium can be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, etc. signals, including but not limited to: random access memory (RAM), read only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid state disk (SSD), etc. For example, the computer program product can be implemented as a non-volatile storage medium storing the computer program, such as a read only memory, a Nand flash, etc.

[0327] In an embodiment, the computer program product can be an intangible product containing the computer program. For example, the computer program product can be implemented as a virtual digital product, such as an executable file, an installation package, etc. digital file storing the computer program.

[0328] The code of the computer program can be written in one or more programming languages. Programming languages such as C, Java, C++, etc. The program code can be executed entirely on the user computing device, or partially on the user computing device, or as a separate software package, or partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case involving a remote computing device, the remote computing device can be connected to the user computing device through any kind of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (for example, through an Internet connection provided by an operator).

[0329] The computer program can be carried or transmitted by an electric, magnetic, optical, electromagnetic, infrared, or the like signal. The electronic device can convert the signal carrying the computer program into a digital signal, and then run the computer program. When the computer program is run on the electronic device, its code is used to make the electronic device perform (more specifically, can make the processor of the electronic device perform) the method steps of various exemplary embodiments of the present disclosure, such as can perform the information processing method described above, which includes the following steps: step 301: obtaining a to-be-converted object; step 302: performing decomposition processing on the to-be-converted object to determine a plurality of script entry point events of the to-be-converted object and script outline information corresponding to each script entry point event; step 303: obtaining interaction mode information; step 304: generating a plurality of script scene contents according to the interaction mode information, the plurality of script entry point events, and the script outline information corresponding to each script entry point event.

[0330] By implementing the above method steps through the computer program, the to-be-converted object can be obtained, and the to-be-converted object is automatically decomposed and processed to determine a plurality of script entry point events of the to-be-converted object and script outline information corresponding to each script entry point event; the interaction mode information is obtained, and then a plurality of script scene contents are automatically generated according to the interaction mode information, the plurality of script entry point events, and the script outline information corresponding to each script entry point event. That is, in the embodiments of the present disclosure, a plurality of script scene contents can be automatically generated from the to-be-converted object, such as book content, the script generation speed is improved by more than several times compared with manual writing, the script generation efficiency is greatly improved, and the operation work is changed from the content production side to the content audit, which reduces the content production cost to a certain extent.

[0331] Exemplary electronic device

[0332] The exemplary embodiments of the present disclosure also provide an electronic device. The electronic device can include a processor and a memory. The memory stores executable instructions of the processor, such as a computer program. The processor executes the method steps of various exemplary embodiments of the present disclosure by executing the executable instructions.

[0333] The following refers to Figure 12 The electronic device is exemplarily illustrated in the form of a general computing device. It should be understood that Figure 12 The electronic device 1200 shown is merely an example and should not limit the functions and use range of the embodiments of the present disclosure.

[0334] As Figure 12 shown, the electronic device 1200 can include a processor 1210, a memory 1220, a bus 1230, an I / O (input / output) interface 1240, and a network adapter 1250.

[0335] The memory 1220 can include volatile memory, such as RAM 1221, and cache 1222, and non-volatile memory, such as ROM 1223. The memory 1220 can also include one or more program modules 1224, which include, but are not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or a combination can include implementation of a network environment. For example, the program modules 1224 can include the units in the above-described apparatus.

[0336] The processor 1210 can include one or more processing units, such as: the processor 1210 can include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, an encoder, a decoder, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc.

[0337] The processor 1210 can be used to execute executable instructions stored in the memory 1220, such as can execute the above-described information processing method, which includes the following steps: step 301: obtaining a to-be-converted object; step 302: performing decomposition processing on the to-be-converted object to determine a plurality of script entry point events of the to-be-converted object and script outline information corresponding to each script entry point event; step 303: obtaining interaction mode information; step 304: generating a plurality of script scene contents according to the interaction mode information, the plurality of script entry point events, and the script outline information corresponding to each script entry point event.

[0338] By executing the above method steps through the processor 1210, the to-be-converted object can be obtained, and the to-be-converted object can be automatically decomposed and processed to determine a plurality of script entry point events of the to-be-converted object and script outline information corresponding to each script entry point event; the interaction mode information is obtained, and then a plurality of script scene contents are automatically generated according to the interaction mode information, the plurality of script entry point events, and the script outline information corresponding to each script entry point event. That is, in the embodiments of the present disclosure, a plurality of script scene contents can be automatically generated from the to-be-converted object, such as book content, the script generation speed is more than several times that of manual writing, the script generation efficiency is greatly improved, and the operation work is changed from the content production side to the content audit, which reduces the content production cost to a certain extent.

[0339] Bus 1230 serves to enable communication among the various components of electronic device 1200, and can be implemented in various forms such as a data bus, address bus, and control bus.

[0340] Electronic device 1200 can communicate with one or more external devices 700 (e.g., a keyboard, a mouse, a printer, etc.) through I / O interface 1240.

[0341] Electronic device 1200 can communicate with one or more networks through network adapter 1250, which can provide a mobile communication solution such as 3G / 4G / 5G, or a wireless communication solution such as a wireless local area network, Bluetooth, near field communication, etc. Network adapter 1250 can communicate with other modules of electronic device 1200 through bus 1230.

[0342] Although Figure 12 Other hardware and / or software modules can also be included in electronic device 1200, such as microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc., which are not shown in FIG. 12.

[0343] As can be seen, the technical solutions of the present disclosure can be implemented as a method, an apparatus, a system, a computer program product, a storage medium, an electronic device, etc. Those skilled in the art can understand that various aspects of the present disclosure can be implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, such as can be referred to as "circuitry", "module", or "system".

[0344] It should be understood that the present disclosure is not limited to the specific methods steps or structural components described above and illustrated in the drawings, and various modifications and changes can be made without departing from the scope of the present disclosure. Those skilled in the art, based on the specific embodiments provided by the present disclosure, will easily think of other embodiments. Therefore, the specific embodiments provided by the present disclosure are only exemplary, and the scope and spirit of the present disclosure are indicated by the claims, and should cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure, and include common knowledge or conventional technical means in the technical field of the present disclosure that are not disclosed by the present disclosure.

Claims

1. An information processing method, characterized in that: The method comprises: Get the object to be converted; Decomposing the object to be converted to determine a plurality of script entry point events of the object to be converted and script outline information corresponding to each script entry point event; Get interaction mode information; A plurality of script scene contents are generated according to the interaction mode information, the plurality of script entry point events and the script outline information corresponding to each of the script entry point events.

2. The method according to claim 1, characterized in that Decomposing the object to be converted to determine multiple script entry point events of the object to be converted and script outline information corresponding to each script entry point event, including: Performing structured data extraction processing on the object to be converted to obtain a role relationship matrix, a plot conflict map, and a worldview element library; Determining multiple script entry point events of the object to be converted based on the role relationship matrix, plot conflict map, and worldview element library; According to the plurality of script entry point events, script outline information corresponding to each of the script entry point events is generated.

3. The method according to claim 2, characterized in that Determine multiple script entry point events of the object to be converted based on the role relationship matrix, plot conflict map, and worldview element library, including: Scanning the plot conflict map to determine a plurality of target paragraph contents, and determining plot density information of each target paragraph content; Determining role weight information of each target paragraph content according to each target paragraph content and the role relationship matrix; Determining the worldview uniqueness information of each target paragraph content based on each target paragraph content and the worldview element library; Multiple script entry point events are determined based on the plot density information, character weight information, and world view uniqueness information of each target paragraph content.

4. The method according to claim 3, characterized in that The plot conflict map is scanned to determine the contents of multiple target paragraphs, including: Using a sliding window algorithm, determining the number of conflict events marked by a preset number of words in the plot conflict map; When it is determined that the quantity information is greater than a preset threshold, the text within the preset quantity is determined to be the target paragraph content.

5. The method according to claim 3, characterized in that Determining the role weight information of each target paragraph content according to each target paragraph content and the role relationship matrix, including: For each target paragraph, perform the following operations: Determine the roles to be compared included in the target paragraph content; In the role relationship matrix, a core role matching each of the roles to be compared is determined, and based on the weight information of the core role, the role weight information of the target paragraph content is determined.

6. The method according to claim 3, characterized in that Determining the worldview uniqueness information of each target paragraph content based on each target paragraph content and the worldview element library, including: For each target paragraph, perform the following operations: Determine the elements to be compared included in the target paragraph content; In the worldview element library, rare elements matching the elements to be compared are determined, and based on the rare elements, the worldview uniqueness information of the target paragraph content is determined.

7. The method according to any one of claims 3 to 6, characterized in that: Based on the plot density information, character weight information, and worldview uniqueness information of each target paragraph content, multiple script entry point events are determined, including: Determining comprehensive information about the content of each target paragraph based on the plot density information, character weight information, and worldview uniqueness information of the content of each target paragraph; sorting the plurality of target paragraph contents according to the comprehensive information of each target paragraph content and the historical behavior data of the first object to obtain sorting result information; According to the sorting result information, target paragraph contents serving as script entry point events are screened out from the multiple target paragraph contents to obtain multiple script entry point events.

8. An information processing device, characterized in that The device comprises: An acquisition unit, used to determine an object to be converted; a processing unit, configured to decompose the object to be converted, determine a plurality of script entry point events of the object to be converted and script outline information corresponding to each of the script entry point events; The first generating unit is used to determine interaction mode information and generate multiple script scene contents according to the interaction mode information, the multiple script entry point events and the script outline information corresponding to each of the script entry point events.

9. An electronic device, characterized in that: include: processor; a memory for storing executable instructions of the processor; The processor is configured to perform the method according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer program product having a computer program stored thereon, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images