Story generation method and device, equipment and medium

Abstract

The embodiment of the invention discloses a story generation method and device, equipment and a medium, and relates to the technical field of artificial intelligence. The method comprises the steps of obtaining at least one target role of a to-be-created story; obtaining first text information which corresponds to the at least one target role and is used for describing role setting; generating a story name of a story to be created according to the first text information; and generating story data of the to-be-created story according to the first text information and the story name. The embodiment of the invention provides a simplified interaction mode, so that the user can easily create a story with specific role setting, and the satisfaction degree of the user in the creation process is increased.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and medium for generating a story. Background Art

[0002] The purpose of the story generation task is to help story creators generate a coherent and accurate story content. Artificial intelligence models can be used to assist creators in story creation and generate stories. However, the above scheme requires users to write prompts based on the stories they want to create in order to generate stories. Writing prompts requires strong professional skills and requires professional prompt engineers to complete. It is difficult for ordinary users to complete the writing of prompts. Therefore, it is difficult to generate stories based on this interactive method. In addition, the specific application scenarios and application designs of large artificial intelligence models are also hot topics and difficulties that everyone is currently discussing. Summary of the invention

[0003] In view of the above problems of the prior art, the embodiments of the present disclosure provide a method, device, equipment and medium for generating a story. The embodiments of the present disclosure provide a simplified interactive method, which enables users to easily create stories with specific role settings and increases the user's participation and satisfaction in the creation process.

[0004] To achieve the above objective, the present disclosure provides a first aspect of a story generation method, comprising:

[0005] Obtain at least one target role of the story to be created;

[0006] Acquire first text information corresponding to at least one target role and used to describe role settings;

[0007] Generate a story name for the story to be created according to the first text information;

[0008] Story data of a story to be created is generated according to the first text information and the story name.

[0009] As a possible implementation of the first aspect, the story data includes text description data and story visual data;

[0010] Generate story data of the story to be created according to the first text information and the story name, including:

[0011] Generate text description data according to the first text information and the story name;

[0012] Story visual data is generated according to the first text information and / or the text description data.

[0013] As a possible implementation manner of the first aspect, obtaining at least one target character of a story to be created includes:

[0014] Obtaining a specified style of a story to be created; wherein the specified style is used to indicate a design theme of the story to be created;

[0015] Based on at least one created character in the specified style, obtaining a character list in the specified style; wherein the character list includes a character name and character visual data of the created character;

[0016] In response to a user's selection operation on the role list, at least one target role of the story to be created is obtained.

[0017] As a possible implementation of the first aspect, obtaining a specified style of a story to be created includes:

[0018] In response to a user's request to generate a story, a style list including at least one story style is obtained; in response to a user's selection operation on the style list, the story style selected by the user is used as a designated style of the story to be created; and / or,

[0019] In response to a user's request to generate a story, a story list including at least one created story is obtained; wherein the story list includes a story name and story data of the created story; in response to a user's selection operation on the story list, a story style of the created story selected by the user is used as a specified style of the story to be created.

[0020] As a possible implementation of the first aspect, obtaining a role list of the specified style based on at least one created role of the specified style includes:

[0021] Get the popularity data of each created character under the specified style;

[0022] Determining an order of at least one created role based on the popularity data;

[0023] Generates a list of roles containing at least one created role, based on the order.

[0024] As a possible implementation of the first aspect, the method further includes:

[0025] In response to a user's operation request for a story name and / or story data, the first text information, the story name, and the story data are stored correspondingly; and / or,

[0026] Add the story name and story data to the user's community list.

[0027] As a possible implementation of the first aspect, the method further includes:

[0028] Generate story keywords for the story to be created based on the story name and story data.

[0029] A second aspect of the present disclosure provides a story generating device, comprising:

[0030] A first acquisition unit is used to: acquire at least one target character of a story to be created;

[0031] A second acquisition unit is used to: acquire first text information corresponding to the at least one target role and used to describe role settings;

[0032] A first generating unit is used to: generate a story name of the to-be-created story according to the first text information;

[0033] The second generating unit is used to generate story data of the to-be-created story according to the first text information and the story name.

[0034] As a possible implementation of the second aspect, the story data includes text description data and story visual data;

[0035] The second generation unit is used to:

[0036] Generate text description data according to the first text information and the story name;

[0037] Story visual data is generated according to the first text information and / or the text description data.

[0038] As a possible implementation manner of the second aspect, the first acquiring unit includes:

[0039] The first acquisition subunit is used to: acquire a specified style of the story to be created; wherein the specified style is used to indicate a design theme of the story to be created;

[0040] The second acquisition subunit is used to: obtain a character list of the specified style based on at least one created character of the specified style; wherein the character list includes a character name and character visual data of the created character;

[0041] The third acquisition subunit is used to: in response to the user's selection operation on the role list, acquire at least one target role of the story to be created.

[0042] As a possible implementation manner of the second aspect, the first acquiring subunit is used to:

[0043] In response to a user's request to generate a story, a style list including at least one story style is obtained; in response to a user's selection operation on the style list, the story style selected by the user is used as a designated style of the story to be created; and / or,

[0044] In response to a user's request to generate a story, a story list including at least one created story is obtained; wherein the story list includes a story name and story data of the created story; in response to a user's selection operation on the story list, a story style of the created story selected by the user is used as a specified style of the story to be created.

[0045] As a possible implementation manner of the second aspect, the second acquiring subunit is used to:

[0046] Get the popularity data of each created character under the specified style;

[0047] Determining an order of at least one created role based on the popularity data;

[0048] Generates a list of roles containing at least one created role, based on the order.

[0049] As a possible implementation manner of the second aspect, the apparatus further includes a storage unit, configured to:

[0050] In response to a user's operation request for a story name and / or story data, the first text information, the story name, and the story data are stored correspondingly; and / or,

[0051] Add the story name and story data to the user's community list.

[0052] As a possible implementation manner of the second aspect, the apparatus further includes a third generating unit, configured to:

[0053] Generate story keywords for the story to be created based on the story name and story data.

[0054] A third aspect of the present disclosure provides an electronic device, including:

[0055] a memory for storing a computer program product;

[0056] The processor is used to execute the computer program product stored in the memory, and when the computer program product is executed, the method described in any one of the first aspects above is implemented.

[0057] A fourth aspect of the present disclosure provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the method described in any one of the first aspects above is implemented.

[0058] The fifth aspect of the present disclosure provides a computer program product, including computer program instructions, which, when executed by a processor, implement any of the methods described in the first aspect. The technical solution of the present disclosure is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0060] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0061] Figure 1 A flowchart of an embodiment of a method for generating a story disclosed herein;

[0062] Figure 2 A flowchart of generating a story name according to an embodiment of the method for generating a story disclosed herein;

[0063] Figure 3 A flowchart of generating story data according to an embodiment of the method for generating a story disclosed herein;

[0064] Figure 4 A flowchart of an embodiment of a method for generating a story disclosed herein;

[0065] Figure 5 A flowchart of generating story visual data according to an embodiment of the method for generating a story disclosed herein;

[0066] Figure 6 A schematic diagram of an interactive interface of an embodiment of the method for generating a story disclosed herein;

[0067] Figure 7 A flowchart of an embodiment of a method for generating a story disclosed herein;

[0068] Figure 8 A schematic diagram of an interactive interface of an embodiment of the method for generating a story disclosed herein;

[0069] Fig. 9 A schematic diagram of an interactive interface of an embodiment of the method for generating a story disclosed herein;

[0070] Fig.10 A flowchart of an embodiment of a method for generating a story disclosed herein;

[0071] Fig.11 It is a structural schematic diagram of an embodiment of a device for generating a story disclosed in the present invention;

[0072] Fig.12 It is a structural schematic diagram of an embodiment of a device for generating a story disclosed in the present invention;

[0073] Fig.13 It is a structural schematic diagram of an embodiment of a device for generating a story disclosed in the present invention;

[0074] Fig.14A block diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0075] Although the embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0076] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0077] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0078] The following first introduces the defects of the existing methods, and then introduces the technical solution of the present invention in detail.

[0079] In a prior art story generation solution, the user is required to write a prompt based on the story he wants to create, and the user inputs the prompt into the artificial intelligence model to generate the story. The writing of the above prompt requires learning complex prompt writing skills, which can only be achieved by professional technicians and is impossible for ordinary users.

[0080] In summary, the existing technology has the following defects: the operation of generating stories is difficult, resulting in poor user experience.

[0081] The present disclosure provides a more simplified interactive method. First, at least one target character is selected from the created characters for the story to be created. There is no need to write difficult prompt words. Based on the first text information corresponding to at least one target character for describing the character setting, the story name and story data can be automatically generated through the multi-stage text generation technology of the artificial intelligence AI large model. This method makes the entire interactive process extremely simple, with low operating difficulty, and improves the user experience, thereby solving the problems of high operating difficulty and poor user experience mentioned in the prior art.

[0082] In the disclosed embodiment, first, a target character of a story to be created is obtained from pre-created characters. The target character includes a human image, an animal image, an image of a static object (such as a table, a ship, a bus, etc.), etc. Among them, the pre-created character is pre-generated based on the description information and the character style of the character. First, based on the description information and the character style of the character, the relevant information of the character is generated. Then, based on the relevant information of the character, a corresponding character is created, and the created character is added to the community (studio) list.

[0083] Specifically, the description information and the character style of the character can be obtained first. The description information is used to indicate the character setting requirements; the character style is used to indicate the design category theme of the character. The character style can include cartoon style, realistic style, Japanese and Korean style, European and American style, Pixar style, Hayao Miyazaki style, etc. For example, the user can enter the description information for the character in the interactive interface of the creation tool: "I want a decent hero". The creation tool receives the user's description information for the character through the input box. The user can also select the character style of the character in the interactive interface of the creation tool, and the creation tool obtains the character style of the character in response to the user's selection operation.

[0084] Further, based on the description information of the role, a first text information corresponding to the role is generated for describing the role setting. The first text information includes the role story information and basic information. The role story information is used to describe the social environment in which the role is located, the social relationship of the role, and the character, skills, etc. of the role, and the basic information of the role is used to describe the basic information of the role, such as the species, appearance and body shape. Optionally, the role story information includes at least one of the following: role prop information, role personality information, role skill information or role social relationship information, and the basic information includes at least one of the following: role attribute information such as role name, role gender, role age, role height or role weight. Based on the first text information, a description of the role visual data is generated, and then based on the description of the role visual data and the role style, the role visual data is generated. The role visual data is the typical and representative image data of the role, and the role visual data includes static image data and dynamic video data. Further, a visual avatar can be cut out based on the role visual data. The automatic generation results of each of the above steps can be realized based on a multimodal large model. Among them, the generated role visual data can be reused to generate multiple role visual data with consistent characteristics of the role. The above generated character-related text information and character visual data, including the first text information, character visual data description, character visual data, visual avatar, and character style, constitute the character-related information. Based on the character-related information, a corresponding character can be created, and the created character can be added to the community (studio) list.

[0085] In the creation tool, each user can create his or her own studio and add the created characters to the user's own studio list, which makes it easier for users to find, continue to create, and share characters, thereby improving the user experience. In an example of a creation tool that supports story making and game development, each character created by a user using the creation tool can be used as a separate studio. Characters created by users are added to the user's own studio list by default. All users can arbitrarily select characters created by others and add them to their own studio list. Subsequent users can search for the added characters in the studio list and continue to create based on the added characters.

[0086] A storage system containing character text descriptions and image information can be established in the creation tool, and the first text information, the generated character visual data description, the character visual data, and the character style are stored as the relevant text information and character visual data of the created character. In the subsequent creation process, the relevant information of the created character can be obtained from the storage system. Specifically, the first text information, character visual data description or character visual data of the corresponding character can be queried in the storage system through the character style or the character story information or the basic information of the character in the first text information of the character, and displayed on the front end of the creation tool so that the user can select the required character.

[0087] Figure 1 FIG. 1 is a flow chart of an embodiment of a method for generating a story disclosed in the present invention. Figure 1 As shown, it may specifically include:

[0088] Step S110, obtaining at least one target role of the story to be created, wherein the target role may be at least one role selected by the user from the community list for the story to be created.

[0089] A role list of created roles can be displayed to the user on the interactive interface of the creation tool. The role list includes at least one role in the pre-created studio list. The user can select at least one target role for the story to be created on the interactive interface of the creation tool.

[0090] In one example, the role list includes the following roles: upright hero, supermodel, beggar, magician, etc. The user selects "upright hero" in the role list, and the authoring tool obtains the target role selected by the user as "upright hero" through the role list.

[0091] Step S120, obtaining first text information corresponding to at least one target role and used to describe role settings. Specifically, the target role may be searched in a storage system to obtain the first text information of the target role.

[0092] Step S130, based on the first text information, generate a story name for the story to be created. For example, a large language model technology can be used to input the first text information into the large language model, and the story name of the story to be created is generated after being processed by the large language model. The large language model can deeply understand the context and semantics of the language, and can generate a professional story name that can express the theme and emotion based on the first text information. For example, the target role selected by the user is "upright hero", and the story name of the story to be created generated by the large language model based on the target role is "Battle of Justice". Based on step S130, a story name with a story overview can be generated, which not only allows users to access story information more intuitively, but also facilitates subsequent story searches and multiple users to choose to join the story based on the story name.

[0093] Step S140, generating story data of the story to be created according to the first text information and the story name. The types of story data used for story description setting include: text type, voice type, and visual type such as image or video.

[0094] Optionally, a multimodal large model technology can be used to input the first text information of at least one target character selected by the user and the story name generated in step S130 into the multimodal large model. The multimodal large model can not only understand the context and semantics of the language and the visual content of the image, but also express these contents in an appropriate text form. After being processed by the multimodal large model, story data with coherence and accuracy can be generated. In view of the strong text processing ability of the large language model, in the optional present embodiment, the combined application of the large language model with the first text information and the story name can make the generated story more in line with the user's expectations, and enhance the user's experience in the process of generating the story. Specifically, the first text information and the story name of the text type are input into the large language model, and the first text information and the story name are processed by the large language model to generate story data for the story description setting. The large language model can deeply understand the context and semantics of the language, ensuring that professional and story-like story data can be generated based on simple text information.

[0095] An exemplary story data may include: background settings such as the time and place of the story, an introduction to the story such as the main events and development process of the story, and the theme, meaning and values ​​embodied in the story.

[0096] In summary, the disclosed embodiments provide a simplified interactive method, which only requires the user to select at least one target character, and does not require the difficult writing of prompt words. Through the multi-stage text generation technology of the artificial intelligence AI large model, a story with a specific character setting can be easily created. This method reduces the difficulty of participating in the creation and improves the user's satisfaction in the creation process. In addition, the relevant information corresponding to each character has been pre-stored in the storage system of the creation tool. The user can generate character visual data with consistent style and characteristics based on the relevant information of the same character in the subsequent creation process, ensuring the consistency of the character visual data and the coherence of the creation, and improving the visual effect of the character visual data.

[0097] In one embodiment, Figure 1 In step S130, generating a story name of the story to be created according to the first text information includes:

[0098] The first text information of at least one target character is input into a first processing module based on a large language model, and the story name of the story to be created is output through the first processing module.

[0099] In the authoring tool, a first Agent module can be constructed based on the large language model as a first processing module, so that it can generate a professional story name that can express the theme and emotion for the story to be created based on the first text information of at least one target character.

[0100] Figure 2 The "studio_name (story name) Agent" module in can be used as the first processing module. Figure 2 , input the role_profile (role setting, i.e. the first text information) of at least one target role into the "studio_nameAgent" module, and output the studio_name (story name) of the story to be created through the "studio_name Agent" module. In the case of many story roles, the story name can be generated based on the main role. Figure 2 , you can set the story name to be generated based on the top 4 characters selected by the user. Figure 2 In the "retry" step, if the user is not satisfied with the generated story name, the process can be repeated in response to the user's request to regenerate a new story name.

[0101] In the above process, the user only needs to select at least one target character, and the story name can be automatically generated after being processed by the first processing module. The entire interactive process is extremely simple, which reduces the difficulty of creation and improves the efficiency of creation.

[0102] In one embodiment, Figure 1 Step S140 in the above method generates story data of the story to be created according to the first text information and the story name, including:

[0103] The first text information and the story name of at least one target character are input into a second processing module based on the multimodal large model, and the story data of the story to be created is output through the second processing module.

[0104] In the previous step, the first processing module generates the story name. In the creation tool, a second Agent module can be constructed based on the multimodal large model as the second processing module, so that it can generate story data of the story to be created based on the first text information of the target character and the story name.

[0105] In one example, the story data may include textual description data. Figure 3 The "studio_profile (story text description data) Agent" module in can be used as the second processing module. Figure 3, input the studio_name (story name) and the role_profile (role setting) of at least one target role into the "studio_profile Agent" module, and the "studio_profile Agent" module outputs the studio_profile (story text description data) of the story to be created. In the case of many story roles, the story text description data can be generated based on the main roles. Figure 3 , you can set the story text description data based on the top 4 characters selected by the user. Figure 3 In the "retry" step, if the user is not satisfied with the generated story text description data, the process can be repeated in response to the user's request to regenerate a new story text description data.

[0106] In the above process, the user only needs to select at least one target character, and the story data can be automatically generated after being processed by the second processing module. The entire interactive process is extremely simple, which reduces the difficulty of creation and improves the efficiency of creation.

[0107] Figure 4 FIG. 1 is a flow chart of an embodiment of a method for generating a story disclosed in the present invention. Figure 4 As shown, in one embodiment, the story data includes text description data and story visual data, and the story visual data includes static story image data and dynamic story video data; Figure 1 Step S140 in the above method generates story data of the story to be created according to the first text information and the story name, including:

[0108] Step S141, generating text description data according to the first text information and the story name;

[0109] Step S142, generating story visual data according to the first text information and / or text description data.

[0110] The generated story visual data may include a story background image and / or a story video. The story background image may include images of characters or story scenes. Using a background image or video to describe a story allows users to intuitively understand the characters and story content. Visual elements can quickly convey information and help users quickly enter the story context. Through the story background image or video, users can more intuitively understand the theme and plot of the story. By displaying the story background image or video, the user's attention is guided through visual elements, thereby enhancing the appeal and understanding of the story, which can make the story more vivid and fascinating.

[0111] In step S141, text description data can be generated based on the multimodal large model, see the above Figure 3In step S142, the first text information and / or text description data of the target character is input into a third processing module based on a multimodal macro model, and the third processing module outputs story visual data of the story to be created.

[0112] See also Figure 5 In the creation tool, a third Agent module can be constructed based on the multimodal large model as a third processing module, so that it can generate story visual data of the story to be created based on the first text information and / or text description data of the target character. Figure 5 The "studio_design (story visual data) Agent" module is the third Agent module.

[0113] See also Figure 5 , Channel_id (channel ID) is also called studio_id (community ID). Users can share resources through studio (community). In the creation tool, each user can create his own studio and add the created characters to the user's own studio list, which is convenient for users to find, continue to create, and share characters, thereby improving the user experience. In an example of a creation tool that supports story making and game development, each character or story created by each user of the creation tool can be used as a separate studio. The characters or stories created by the user are added to the user's own studio list by default. All users can arbitrarily select characters or stories created by others and add them to their own studio list. The studio that the user chooses to join will be displayed in his own list, see Figure 6 The effect diagram of the list of multiple studios that the user has joined is shown. Figure 6 The left rectangular box in the figure shows the roles and stories in the user's studio list. During the creation process, the role or story selected by the user will appear in the role input box on the right, and the generated results such as story visual data and text description data will be displayed below the role input box.

[0114] See also Figure 5According to the user's specified Channel_id (community identifier), the studio_profile (story text description data) corresponding to the story being edited by the user can be obtained. The studio_profile (story text description data) is input into the "studio_design_description Agent" module, and the "studio_design_des cription Agent" module outputs the studio_design_description (story visual data description). The story visual data description can be used as a prompt word for the "studio_design Agent" module. The story visual data description is input into the "studio_designAgent" module, and the "studio_design" (story visual data) of the story to be created is output. See Figure 5 In the "retry" step, if the user is not satisfied with the generated story visual data, the process can be repeated in response to the user's request to regenerate a new story visual data. Figure 5 In the "selection" step, among the multiple generated story visual data versions, the user can select the most representative visual data as the channel background image.

[0115] In summary, in the implementation process of story generation provided by the present disclosure, the user only needs to perform simple input or selection of the target character, and the story name, story text description data and story visual data can be automatically generated after processing by the multimodal large model. The entire interactive process is extremely simple. Furthermore, a storage system containing text descriptions and image information of characters and stories is established to store story names, text description data and story visual data, as well as relevant information about the characters in the story. In the subsequent creation process, the user generates multiple visual data of the target character in different scenes based on the above stored story information and relevant information of the character, and a series of stable and highly consistent character visual data can be obtained.

[0116] like Figure 7 As shown, in one embodiment, Figure 1 Step S130 in the step of obtaining at least one target character of the story to be created includes:

[0117] Step S210, obtaining a specified style of the story to be created; wherein the specified style is used to indicate a design theme of the story to be created;

[0118] Step S220, based on at least one created character in the specified style, obtaining a character list of the specified style; wherein the character list includes the character name and character visual data of the created character;

[0119] Step S230, in response to the user's selection operation on the role list, obtaining at least one target role of the story to be created.

[0120] Through this embodiment, the user can directly select the desired target role from the roles under the specified style by selecting the specified style for describing the design theme, thereby reducing the user's screening workload and facilitating the user's operation.

[0121] Figure 8 An example interactive interface for creating a story in an authoring tool is shown. Figure 7 and Figure 8 In the interactive interface of the creation tool, the user can select the specified style of the story to be created in the style selection box. For example, the specified style selected by the user is "superhero". The creation tool obtains the specified style of the story to be created selected by the user through the selection box, and then generates a character list of the specified style based on the characters created under the specified style, so that the user can select the target character in the character list. Among them, the character name and character visual data of the created character can be displayed in each character option in the character list. See Figure 8 , the characters in the character list are Lufei, Sun Wukong, Nami, and Zoro, Figure 8 The character names in the style are only for example and do not involve specific character information or copyright information. The user can select at least one character under this style. The authoring tool uses the character selected by the user as the target character of the story to be created. In subsequent steps, the authoring tool can generate a story name and story data based on the relevant information of the target character.

[0122] See also Figure 8 , the list on the left is based on the style of the selected character, and only shows characters of that style. In an interactive example, the user clicks on the character list area to switch to the add state and enter the state of adding character information. The user can filter the characters in the list. The character card on the right shows the character visual data of the character selected by the user, which can include character pictures or character videos. Click any blank space to close the character list.

[0123] See also Figure 8 In an interactive example, if you want to remove the selected character, you can click the selected character in the list again. In addition, the function of inverting is to select the part outside the current selection. If no character is selected after inverting, the list will refresh and show characters of all styles. You can remove the character by directly clicking the delete button in the upper right corner of the character card.

[0124] In one embodiment, Figure 7 Step S210 in the example, obtaining a specified style of a story to be created, includes:

[0125] In response to a user's request to generate a story, a style list including at least one story style is obtained; in response to a user's selection operation on the style list, the story style selected by the user is used as a designated style of the story to be created; and / or,

[0126] In response to a user's request to generate a story, a story list including at least one created story is obtained; wherein the story list includes the story name and story data of the created story; in response to the user's selection operation on the story list, the story style of the created story selected by the user is used as the specified style of the story to be created.

[0127] In the interactive interface of the creation tool, in response to the user's request to generate a story, a pre-set style list is obtained and displayed to the user. The style list can be pre-set based on the usage data of each story style. For example, based on the usage data, the story styles with higher usage frequency are screened out and set in the style list; or, based on the usage data, multiple story styles are sorted and set in the style list in order of usage frequency from high to low. The usage data of the story style may include: the number of stories created under the story style, the number of stories shared, the number of stories commented on, the number of stories liked, and the number of stories collected. The user selects a desired story style from the style list as the specified style of the story to be created.

[0128] In addition, in response to the user's request to generate a story, a pre-set story list of created stories can also be displayed to the user in the interactive interface. The story name and story data of the created story can be displayed in each story option in the story list. The user can select a story from the story list of created stories, and can create a sub-story based on the story, with the story style of the story being used as the specified style of the story to be created.

[0129] In one embodiment, step S220, based on at least one created character in the specified style, obtaining a character list of the specified style includes:

[0130] Get the popularity data of each created character under the specified style;

[0131] Determining an order of at least one created role based on the popularity data;

[0132] Generates a list of roles containing at least one created role, based on the order.

[0133] The popularity data of the created characters may include usage data of each created character, such as the number of videos and / or pictures generated based on the character, the number of shares, the number of comments, the number of likes, the number of favorites, etc. Multiple characters may be sorted based on the popularity data of the created characters, and the created characters may be placed in a character list in descending order of popularity.

[0134] The order of roles in the role list created based on popularity data can provide users with more personalized role recommendations based on their preferences and historical behaviors, thereby improving user satisfaction and experience. In addition, using popular content can increase content exposure and traffic, thereby improving the value and competitiveness of the platform.

[0135] See also Figure 8 In an interactive example, the default text of the role search box is: "role_style name | search role". At this time, only roles under this style can be searched. After adding at least one role, the story name automatic writing function is enabled, and the role_profile of the added role is used as input, and the Agent automatically writes the story name. After writing, you can click Auto Write again, and the Agent will generate new text and overwrite the previous historical version.

[0136] See also Figure 8 In an interactive example, the story name can be repeated as a whole, but not in the following special cases: 1) The story name cannot be the same as any style to avoid confusion. 2) The story name cannot be the same as the parent story name to facilitate distinction. In addition, the Studio ID display can be added to the story homepage and / or character homepage as the logo of different studios to distinguish items with the same name.

[0137] See also Figure 8 In the editing state of the story creation page, you can modify the story name, story data, add or remove characters. If it is an already created story, the user can enter the story creator through the Edit button. In an example of the editing process, the last character cannot be removed, that is, at least one character must be retained, so the style type of the story cannot be changed. The story style can only be changed after the current process is ended and a new process is started. Removing a character does not affect the display of the generated and being generated content on the studio and homepage, but the character cannot be selected through the "@" operator to generate a new shot.

[0138] See also Figure 8, the automatic writing conditions of story data are: at least one target role is selected and the story name is filled in. The role_profile (role setting) and story_name (story name) of the added target role are used as input, and the Agent automatically writes the story data. After writing, you can click Auto Write again, and the Agent will generate a new text and overwrite the previous historical version.

[0139] In one embodiment, the above method further comprises:

[0140] In response to a user's operation request for a story name and / or story data, the first text information, the story name, and the story data are stored correspondingly; and / or,

[0141] Add the story name and story data to the user's community list.

[0142] The operation request is the user's confirmation operation on the story name and story data. After the story name and story data are generated, a story can be created based on the story name and story data. Specifically, a storage system for storing relevant information of the story is pre-established, and a storage unit for storing story information is allocated in the storage system, and the generated story name and story data are written into the storage unit. In the creation tool, each user can create his or her own community (studio) and add the created story to the user's community list. Each character or story created by the user can be used as a separate studio. The characters or stories created by the user are added to the user's own studio list by default, see Figure 6 The effect diagram of the list of multiple studios that the user has joined is shown.

[0143] In one embodiment, the method further includes: generating story keywords for the story to be created based on the story name and the story data. Specifically, the story name and the story data can be input into the multimodal big model, and the multimodal big model processes the input information to generate story keywords. The multimodal big model can deeply understand the context, semantics and visual data of the language, and can generate highly relevant and representative story keywords for subsequent user retrieval.

[0144] In the studio list, you can view the information about the created stories. Users can click the story icon in the list to enter the sub-page to view the relevant information of the story. Fig. 9 As shown, the relevant information of the story displayed in the sub-page may include: at least one of: story visual data, story name, text description data, story style, story keywords, and relevant information of characters in the story.

[0145] In one example, a user creates a story based on pre-created characters. The characters included in the story can form a character group, and a target character can be selected from the pre-created character group for creating a story. Fig.10 , the whole process of generating stories based on the authoring tool can include the following steps:

[0146] Step S1) receiving a specified style selected by a user: the user selects a desired specified style from a plurality of story styles; or selects a story from a created story, i.e., creates a sub-story, the style of which is the selected specified style. The creation tool receives the specified style of the story to be created selected by the user.

[0147] Step S2) Generate a character list: Based on the specified style selected by the user, obtain the created characters under the style, and generate a character list that the user can select, so that the user can subsequently select the target character to be added in the list. The pre-stored information in the character list includes the character's visual avatar and the first text information used to describe the character setting. The first text information may include the character's name, basic character information, appearance description, and character story information. The order of the characters in the character list can be sorted according to the user's preference or the time of creation.

[0148] Step S3) Obtaining at least one target role of the story to be created: The user selects at least one target role from the above role list. The authoring tool obtains the target role selected by the user through the role list.

[0149] Step S4) Generate story text description data: The user can write the story text description data by himself, or the creation tool automatically generates the story name and story text description data according to the role settings of the first few roles selected by the user. Among them, the role selected earliest can be the most important and ranked in the front by default.

[0150] Step S5) Generate story visual data: Generate story visual data based on the story text description data and the role settings of all the characters in the pre-stored story.

[0151] Step S6) Storing the created story: Storing the story text description data, the role settings of all the characters in the story, the character visual data description, the character visual data, and the story visual data in a corresponding manner.

[0152] Step S7) By default, the user adds the created story to his / her studio list: the story text description data and story visual data are visible to the user, and the user can edit the story he / she created.

[0153] In summary, the embodiments of the present disclosure provide a simplified interactive method by establishing a storage system containing text descriptions and image information of characters and stories, and utilizing the multimodal large model's ability to understand and process text and images. The system can automatically generate relevant information such as story names and story data, allowing users to easily create stories with specific character settings, thereby improving user experience.

[0154] In addition, the user can generate character visual data corresponding to the target character multiple times based on the relevant information of the target character in the subsequent creation process. For example, the user can indicate multiple actions of the target character, and the creation tool uses multimodal large model technology to generate multiple character visual data with consistent style and characteristics based on the relevant information of the target character and the actions indicated by the user. Multiple character visual data of the same character are generated based on the relevant information of the character, thus ensuring the consistency and diversity of the character visual data, supporting a wider range of creative activities, and can be applied to story production or game development material production, which improves the practical value of character visual data and the coherence of creation.

[0155] The storage system including the created characters and the created stories established in the creation tool can store the first text information, the second text information, the first character visual data, and the character style of the created characters as the character information of the created characters, and can store the story name, story data, and the first text information, the second text information, the first character visual data of the characters included in the story. Based on the above pre-stored character information and story information, visual data of one or more characters can be further generated.

[0156] The process of generating corresponding visual data based on the created characters and stories includes:

[0157] (1) Obtaining character information of at least one designated character and instruction information corresponding to each designated character; wherein the character information includes at least one of the following: first text information for describing character settings, second text information for describing visual data of the first character, a character style for indicating a character design theme, and visual data of the first character; the instruction information is used to indicate an action of the designated character.

[0158] A character list may be displayed to the user on the interactive interface of the creation tool. The character list includes at least one character in the pre-created studio list. The user may select at least one designated character on the interactive interface of the creation tool. The character information of the designated character may include at least one of the following: first text information for describing the character setting, second text information for describing the visual data of the first character, a character style for indicating a character design theme, the visual data of the first character, etc.

[0159] In addition, a text input box can be set on the interactive interface of the creation tool to receive instruction information input by the user for indicating the action of the specified character. The user can enter simple text in the text input box to indicate the action of the specified character. For example, the user enters: "Running in the wilderness" in the input box corresponding to the specified character "The Honest Warrior". The creation tool then receives the user's instruction through the input box that the action corresponding to the "Honest Warrior" is "Running in the wilderness".

[0160] In another example, the instruction information input by the user may also include voice information. The user may click the microphone icon next to the input box to switch to voice input mode, and then start inputting instruction information in the form of voice information. The authoring tool converts the received voice information into text information, thereby obtaining the instruction information.

[0161] (2) Based on the character information of the designated character and the instruction information, third text information for describing the second character visual data corresponding to the designated character is generated.

[0162] The second character visual data includes an action image corresponding to the specified character. In order to generate an action image that matches the user's instruction information, a third text information for describing the action image may be first generated, and then the third text information may be used as a prompt word for the multimodal large model to guide the multimodal large model to finally generate an action image that matches the user's instruction information.

[0163] Specifically, the multimodal large model technology can be used to generate the third text information based on the role information of the specified role and the instruction information input by the user. The multimodal large model can not only understand the context and semantics of the language and the visual content of the image, but also express these contents in an appropriate text form. After processing by the multimodal large model, the third text information with clarity, relevance, specificity and guidance can be generated. Then the third text information is directly input into the multimodal large model as a prompt word, and after processing by the multimodal large model, the second role visual data corresponding to the specified role can be generated.

[0164] In this step, the role information and third text information of the specified role are directly converted into professional prompt words that can be directly input into the multimodal large model, thereby not requiring users to learn how to write prompt words, avoiding the complicated work of learning model prompt words, and not requiring users to have strong professional capabilities, greatly reducing the difficulty of user operation.

[0165] (3) Based on the role information and the third text information of the specified role, the second role visual data of the specified role is generated. The role information and the third text information of the specified role are input into the multimodal large model. The multimodal large model can deeply understand the context and semantics of the language and the visual content of the image. After being processed by the multimodal large model, the second role visual data corresponding to the specified role can be generated.

[0166] In the creation process of the above example, for the same designated character, the second character visual data with different postures and actions generated each time is generated based on the character information of the designated character. Therefore, different images of the same character contain the characteristics of the character setting of the character, thereby generating stable and highly consistent arbitrary visual data of the character, thereby maintaining the consistency of the character image and the coherence of the creation.

[0167] In summary, the disclosed embodiments provide a simplified interactive method that does not require the difficult writing of prompt words. The multimodal large model technology can generate corresponding second character visual data based on the user-specified role, increasing the user's satisfaction in the creation process. In addition, the second character visual data of the same role in different scenes are all generated based on the role information of the specified role, which can ensure the consistency of the visual data and the coherence of the creation, and improve the visual effect of the visual data.

[0168] like Fig.11 As shown, the present disclosure also provides an embodiment of a corresponding story generation device. For the beneficial effects or technical problems solved by the device, please refer to the description of the method corresponding to each device, or refer to the description in the invention content, which will not be repeated here.

[0169] In an embodiment of the story generating device, the device comprises:

[0170] The first acquisition unit 100 is used to: acquire at least one target character of a story to be created;

[0171] The second acquisition unit 200 is used to: acquire first text information corresponding to the at least one target role and used to describe role settings;

[0172] The first generating unit 300 is used to: generate a story name of the to-be-created story according to the first text information;

[0173] The second generating unit 400 is used to generate story data of the to-be-created story according to the first text information and the story name.

[0174] In one embodiment, the story data includes text description data and story visual data;

[0175] The second generating unit 400 is used for:

[0176] Generate text description data according to the first text information and the story name;

[0177] Story visual data is generated according to the first text information and / or the text description data.

[0178] like Fig.12 As shown, in one implementation, the first acquisition unit 100 includes:

[0179] The first acquisition subunit 101 is used to: acquire a specified style of the story to be created; wherein the specified style is used to indicate a design theme of the story to be created;

[0180] The second acquisition subunit 102 is used to: obtain a character list of the specified style based on at least one created character of the specified style; wherein the character list includes the character name and the character visual data of the created character;

[0181] The third acquisition subunit 103 is used to: in response to the user's selection operation on the role list, acquire at least one target role of the story to be created.

[0182] In one implementation, the first acquisition subunit 101 is used to:

[0183] In response to a user's request to generate a story, a style list including at least one story style is obtained; in response to a user's selection operation on the style list, the story style selected by the user is used as a designated style of the story to be created; and / or,

[0184] In response to a user's request to generate a story, a story list including at least one created story is obtained; wherein the story list includes a story name and story data of the created story; in response to a user's selection operation on the story list, a story style of the created story selected by the user is used as a specified style of the story to be created.

[0185] In one implementation, the second acquisition subunit 102 is used to:

[0186] Get the popularity data of each created character under the specified style;

[0187] Determining an order of at least one created role based on the popularity data;

[0188] Generates a list of roles containing at least one created role, based on the order.

[0189] like Fig.13 As shown, in one embodiment, the above device further includes a storage unit 500, which is used to:

[0190] In response to a user's operation request for a story name and / or story data, the first text information, the story name, and the story data are stored correspondingly; and / or,

[0191] Add the story name and story data to the user's community list.

[0192] like Fig.13As shown, in one embodiment, the above device further includes a third generating unit 600, which is used to:

[0193] Generate story keywords for the story to be created based on the story name and story data.

[0194] Below, reference Fig.14 The electronic device according to the embodiment of the present disclosure is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signals from them.

[0195] Fig.14 A block diagram of an electronic device according to an embodiment of the present disclosure is illustrated.

[0196] like Fig.14 As shown, the electronic device includes one or more processors and memory.

[0197] The processor may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0198] The memory may store one or more computer program products, and the memory may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program products may be stored on the computer-readable storage medium, and the processor may run the computer program product to implement the various embodiments of the present disclosure described above and / or other desired functions.

[0199] In one example, the electronic device may further include: an input device and an output device, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0200] In addition, the input device may also include, for example, a keyboard, a mouse, and the like.

[0201] The output device can output various information to the outside, including determined distance information, direction information, etc. The output device can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0202] Of course, to simplify, Fig.14Only some of the components related to the present disclosure in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device may further include any other appropriate components.

[0203] In addition to the above methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present disclosure described in the above part of this specification.

[0204] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0205] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps of the method according to various embodiments of the present disclosure described in the above part of this specification.

[0206] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0207] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0208] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0209] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0210] The method and apparatus of the present disclosure may be implemented in many ways. For example, the method and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0211] It should also be noted that in the apparatus, device and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0212] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0213] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for generating a story, characterized in that: include: Obtain at least one target role of the story to be created; Acquire first text information corresponding to the at least one target role and used to describe role settings; Generating a story name of the to-be-created story according to the first text information; Story data of the story to be created is generated according to the first text information and the story name.

2. The method according to claim 1, characterized in that The story data includes text description data and story visual data; The step of generating story data of the to-be-created story according to the first text information and the story name includes: Generate the text description data according to the first text information and the story name; The story visual data is generated according to the first text information and / or the text description data.

3. The method according to claim 1, characterized in that The step of obtaining at least one target character of the story to be created includes: Acquire a specified style of the story to be created; wherein the specified style is used to indicate a design theme of the story to be created; Based on at least one created character in the specified style, obtaining a character list of the specified style; wherein the character list includes a character name and character visual data of the created character; In response to a user's selection operation on the role list, at least one target role of a story to be created is obtained.

4. The method according to claim 3, characterized in that: The step of obtaining the specified style of the story to be created includes: In response to a user's request to generate a story, a style list including at least one story style is obtained; in response to a user's selection operation on the style list, the story style selected by the user is used as the specified style of the story to be created; and / or, In response to a user's request to generate a story, a story list including at least one created story is obtained; wherein the story list includes the story name and story data of the created story; in response to a user's selection operation on the story list, the story style of the created story selected by the user is used as the specified style of the story to be created.

5. The method according to claim 3, characterized in that: The obtaining a list of roles of the specified style based on at least one created role of the specified style comprises: Obtaining popularity data of each of the created characters under the specified style; Determining the order of the at least one created role based on the popularity data; Based on the sequence, the role list including the at least one created role is generated.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: In response to a user's operation request for the story name and / or the story data, the first text information, the story name, and the story data are stored correspondingly; and / or, The story name and the story data are added to the user's community list.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Based on the story name and the story data, story keywords of the story to be created are generated.

8. A story generating device, characterized in that: include: A first acquisition unit is used to: acquire at least one target character of a story to be created; A second acquisition unit is used to: acquire first text information corresponding to the at least one target role and used to describe role settings; A first generating unit is used to: generate a story name of the to-be-created story according to the first text information; The second generating unit is used to generate story data of the to-be-created story according to the first text information and the story name.

9. An electronic device, characterized in that: include: a memory for storing a computer program product; A processor is used to execute the computer program product stored in the memory, and when the computer program product is executed, it implements the method described in any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method described in any one of claims 1 to 7 is implemented.

Images