Work generation method and device, equipment and storage medium

Abstract

The invention relates to a work generation method and device, equipment and a storage medium, and relates to the technical field of multimedia. In the method, a terminal login object and a role controlled by artificial intelligence perform multiple rounds of dialogues, a work can be generated and displayed based on dialogue information of the multiple rounds of dialogues, and the work comprises a story plot generated by two dialogue roles and the dialogue information of the multiple rounds of dialogues, so that the work can be generated in a dialogue form; the terminal does not need to log in the object for various operations, and the man-machine interaction efficiency is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of multimedia technology, and in particular to a work generation method, device, equipment and storage medium. Background Art

[0002] With the development of artificial intelligence technology, the use of artificial intelligence big models is becoming more and more extensive. For example, artificial intelligence big models can be used to generate works such as novels.

[0003] In the related art, when using artificial intelligence big models to generate novels, the artificial intelligence big models are fed with summary content such as themes and keywords, and the artificial intelligence big models automatically generate works based on the input content. However, the works generated by this method are generally more uniform in content and lack more personalized information, resulting in poor quality of the generated works. Summary of the invention

[0004] The present disclosure provides a method, device, equipment and storage medium for generating works, which enables the works to have personalized characteristics, thereby improving the quality of the works. The technical solution of the present disclosure is as follows.

[0005] According to one aspect of an embodiment of the present disclosure, a method for generating a work is provided, the method comprising:

[0006] In response to an initialization operation on the work, a dialogue interface between a first character and a second character is displayed, wherein the first character is controlled by a first object, which is a terminal login object, and the second character is controlled by artificial intelligence;

[0007] In response to the dialogue operation of the first object on the dialogue interface, displaying multiple rounds of dialogue between the first character and the second character on the dialogue interface to obtain dialogue information of the multiple rounds of dialogue;

[0008] In response to a work generation operation, a work generated based on the dialogue information of the multiple rounds of dialogue is displayed, the work including a storyline generated by the first character, the second character, and the dialogue information of the multiple rounds of dialogue.

[0009] In some embodiments, the method further comprises:

[0010] Displaying a configuration interface, wherein the configuration interface is used to configure attribute information of the second role;

[0011] In response to the dialogue operation of the first object on the dialogue interface, displaying multiple rounds of dialogues between the first character and the second character on the dialogue interface includes:

[0012] In response to the dialogue operation of the first object on the dialogue interface, the dialogue information sent by the first character and the reply information sent by the second character are displayed on the dialogue interface, and the reply information corresponds to the attribute information of the second character.

[0013] In some embodiments, in response to the work generation operation, displaying the work generated based on the dialogue information of the multiple rounds of dialogues includes:

[0014] In response to the work generation operation, displaying a story outline generated based on the dialogue information of the multiple rounds of dialogue;

[0015] In response to a confirmation operation on the story outline, a work generated based on the dialogue information of the multiple rounds of dialogue and the story outline is displayed.

[0016] In some embodiments, the method further comprises:

[0017] In response to a modification operation on the story outline, displaying the modified story outline;

[0018] In response to a confirmation operation on the modified story outline, a work generated based on the dialogue information of the multiple rounds of dialogue and the modified story outline is displayed.

[0019] In some embodiments, in response to the work generation operation, displaying a story outline generated based on the dialogue information of the multiple rounds of dialogues includes:

[0020] In response to the work generation operation, displaying an editing interface for the dialogue information of the multiple rounds of dialogue;

[0021] In response to an editing operation on the dialogue information of the multiple rounds of dialogues, displaying the edited dialogue information;

[0022] In response to a confirmation operation on the edited dialogue information, a story outline generated based on the edited dialogue information is displayed.

[0023] In some embodiments, displaying a story outline generated based on the dialogue information of the multiple rounds of dialogues includes:

[0024] Displaying a plurality of story outline templates, wherein the plurality of story outline templates are all associated with the dialogue information of the plurality of dialogue rounds;

[0025] In response to the confirmation operation of the story outline, displaying the dialogue information of the multiple rounds of dialogue and the work generated by the story outline includes:

[0026] In response to a selection operation of any story outline template, a work generated based on the dialogue information of the multiple rounds of dialogue and the selected story outline template is displayed.

[0027] In some embodiments, in response to the confirmation operation of the story outline, displaying the dialogue information of the multiple rounds of dialogue and the work generated by the story outline includes:

[0028] In response to a confirmation operation on the story outline, displaying a draft of a work text generated based on the dialogue information of the multiple rounds of dialogue and the story outline;

[0029] In response to a confirmation operation on the first draft of the work text, a work generated based on the first draft of the work text is displayed.

[0030] In some embodiments, the method further comprises:

[0031] In response to a modification operation on the draft text of the work, displaying a modified draft text of the work, the draft text of the work includes character dialogue text, narration information and environment description information generated from the dialogue information of the multiple rounds of dialogue, the modification operation includes at least one of an operation of adjusting the order of the character dialogue text, an operation of adding, an operation of deleting, an operation of modifying the narration information and an operation of modifying the environment description information;

[0032] In response to a confirmation operation on the modified draft text of the work, a work generated based on the modified draft text of the work is displayed.

[0033] In some embodiments, the method further comprises:

[0034] In response to the confirmation operation of the story outline, displaying modification prompt information of the first draft of the work text, wherein the modification prompt information is used to prompt a method for modifying the first draft of the work text;

[0035] The method of displaying the modified draft text of the work in response to the modification operation on the draft text of the work includes:

[0036] In response to a triggering operation on the modification prompt information, a first draft of the work text modified based on the modification prompt information is displayed.

[0037] In some embodiments, in response to the confirmation operation on the draft text of the work, displaying the work generated based on the draft text of the work includes:

[0038] In response to a confirmation operation on the draft text of the work, a final text of the work and music information generated based on the draft text of the work are displayed, wherein the music information includes timbre information of each of the two characters, background music information, and at least one of sound effect information and voice information at multiple locations in the final text of the work, wherein the voice information includes at least one of speech speed, intonation, tone, and voice emotion;

[0039] In response to a confirmation operation on the final draft of the work text and the music information, a work generated based on the final draft of the work text and the music information is displayed.

[0040] In some embodiments, the method further comprises at least one of the following:

[0041] In response to a modification operation on the music information, the modified music information is displayed; in response to a confirmation operation on the final work text and the modified music information, a work generated based on the final work text and the modified music information is displayed;

[0042] In response to an audition operation on any segment in the final draft of the work text, the segment is played based on the soundtrack information corresponding to the segment.

[0043] According to another aspect of the present disclosure, a method for generating a work is provided, the method comprising:

[0044] Acquire a dialogue message sent by a first character on a dialogue interface, wherein the dialogue interface is a dialogue interface between the first character and a second character, the first character is controlled by a first object, the first object is a terminal login object, and the second character is controlled by artificial intelligence;

[0045] Based on the dialogue information of the first character, generating multiple rounds of dialogues between the first character and the second character;

[0046] A work is generated based on the dialogue information of the multiple rounds of dialogue, wherein the work includes a storyline generated by the first character, the second character, and the dialogue information of the multiple rounds of dialogue.

[0047] In some embodiments, generating a work based on the dialogue information of the multiple rounds of dialogues includes:

[0048] Generating a story outline of the work based on the dialogue information of the multiple rounds of dialogue;

[0049] The work is generated based on the dialogue information of the multiple rounds of dialogue and the story outline.

[0050] In some embodiments, generating a story outline of the work based on the dialogue information of the multiple rounds of dialogues includes:

[0051] Based on the dialogue information of the multiple rounds of dialogue, determining multiple target plots and emotion information in the dialogue information of the multiple rounds of dialogue;

[0052] The story outline is generated based on the dialogue information of the multiple rounds of dialogue, the multiple target plots and the emotion information.

[0053] In some embodiments, generating the work based on the dialogue information of the multiple rounds of dialogue and the story outline includes:

[0054] Based on the dialogue information of the multiple rounds of dialogue and the story outline, a preliminary draft of the work text is generated, wherein the preliminary draft of the work text includes character dialogue text, narration information, and environment description information generated from the dialogue information of the multiple rounds of dialogue;

[0055] The work is generated based on the first draft of the work text.

[0056] In some embodiments, generating a first draft of the work text based on the dialogue information of the multiple rounds of dialogue and the story outline includes:

[0057] Based on the dialogue information of the multiple rounds of dialogue and the story outline, the dialogue information of the multiple rounds of dialogue is expanded, and based on the expanded dialogue information and the story outline, a first draft of the work text is generated.

[0058] In some embodiments, generating the work based on the first draft of the work text includes:

[0059] Based on the draft text of the work, a final draft text of the work and music information are generated, wherein the music information includes timbre information of each of the two characters, background music information, and at least one of sound effect information and voice information at multiple locations in the final draft text of the work, wherein the voice information includes at least one of speech speed, intonation, tone, and voice emotion;

[0060] The work is generated based on the final draft of the work text and the soundtrack information.

[0061] In some embodiments, generating the final draft of the work text and the music information based on the first draft of the work text includes:

[0062] Based on the first draft of the work text, generating the final draft of the work text;

[0063] The music information is generated based on the final draft of the work text.

[0064] In some embodiments, generating the soundtrack information based on the final draft of the work text includes at least one of the following:

[0065] Determining the personality characteristics of the first character and the second character based on the final draft of the work text, and determining the timbre information of the first character and the second character based on the personality characteristics of the first character and the second character;

[0066] Based on the final draft of the work text, determining the dialogue scenes and environmental elements of each of the multiple positions in the final draft of the work text, and based on the dialogue scenes and environmental elements of each of the multiple positions, determining the sound effect information of each of the multiple positions;

[0067] Based on the final draft of the work text, the emotional information of each of the multiple positions in the final draft of the work text is determined, and based on the emotional information of each of the multiple positions, the voice information of the multiple positions is determined.

[0068] According to another aspect of an embodiment of the present disclosure, a work generation device is provided, the device comprising:

[0069] An interface display unit is configured to execute, in response to an initialization operation on the work, a display of a dialogue interface between a first character and a second character, wherein the first character is controlled by a first object, which is a terminal login object, and the second character is controlled by artificial intelligence;

[0070] a dialogue unit, configured to execute a dialogue operation in response to the first object on the dialogue interface, display multiple rounds of dialogue between the first character and the second character on the dialogue interface, and obtain dialogue information of the multiple rounds of dialogue;

[0071] A work display unit is configured to execute a work generation operation in response to the work generation operation, and is configured to execute the display of the work generated based on the dialogue information of the multiple rounds of dialogue, wherein the work includes a storyline generated by the first character, the second character and the dialogue information of the multiple rounds of dialogue.

[0072] In some embodiments, the interface display unit is further configured to execute:

[0073] Displaying a configuration interface, wherein the configuration interface is used to configure attribute information of the second role;

[0074] The dialog display unit is configured to execute:

[0075] In response to the dialogue operation of the first object on the dialogue interface, the dialogue information sent by the first character and the reply information sent by the second character are displayed on the dialogue interface, and the reply information corresponds to the attribute information of the second character.

[0076] In some embodiments, the work display unit is configured to execute:

[0077] In response to the work generation operation, displaying a story outline generated based on the dialogue information of the multiple rounds of dialogue;

[0078] In response to a confirmation operation on the story outline, a work generated based on the dialogue information of the multiple rounds of dialogue and the story outline is displayed.

[0079] In some embodiments, the work display unit is further configured to execute:

[0080] In response to a modification operation on the story outline, displaying the modified story outline;

[0081] In response to a confirmation operation on the modified story outline, a work generated based on the dialogue information of the multiple rounds of dialogue and the modified story outline is displayed.

[0082] In some embodiments, the work display unit is further configured to execute:

[0083] In response to the work generation operation, displaying an editing interface for the dialogue information of the multiple rounds of dialogue;

[0084] In response to an editing operation on the dialogue information of the multiple rounds of dialogues, displaying the edited dialogue information;

[0085] In response to a confirmation operation on the edited dialogue information, a story outline generated based on the edited dialogue information is displayed.

[0086] In some embodiments, the work display unit is further configured to execute:

[0087] Displaying a plurality of story outline templates, wherein the plurality of story outline templates are all associated with the dialogue information of the plurality of dialogue rounds;

[0088] In response to a selection operation of any story outline template, a work generated based on the dialogue information of the multiple rounds of dialogue and the selected story outline template is displayed.

[0089] In some embodiments, the work display unit is further configured to execute:

[0090] In response to a confirmation operation on the story outline, displaying a draft of a work text generated based on the dialogue information of the multiple rounds of dialogue and the story outline;

[0091] In response to a confirmation operation on the first draft of the work text, a work generated based on the first draft of the work text is displayed.

[0092] In some embodiments, the work display unit is further configured to execute:

[0093] In response to a modification operation on the draft text of the work, displaying a modified draft text of the work, the draft text of the work includes character dialogue text, narration information and environment description information generated from the dialogue information of the multiple rounds of dialogue, the modification operation includes at least one of an operation of adjusting the order of the character dialogue text, an operation of adding, an operation of deleting, an operation of modifying the narration information and an operation of modifying the environment description information;

[0094] In response to a confirmation operation on the modified draft text of the work, a work generated based on the modified draft text of the work is displayed.

[0095] In some embodiments, the apparatus further comprises:

[0096] A first information display unit is configured to display modification prompt information of the first draft of the work text in response to a confirmation operation on the story outline, wherein the modification prompt information is used to prompt a method for modifying the first draft of the work text;

[0097] The work display unit is configured to execute:

[0098] In response to a triggering operation on the modification prompt information, a first draft of the work text modified based on the modification prompt information is displayed.

[0099] In some embodiments, the work display unit is configured to execute:

[0100] In response to a confirmation operation on the draft text of the work, a final text of the work and music information generated based on the draft text of the work are displayed, wherein the music information includes timbre information of each of the two characters, background music information, and at least one of sound effect information and voice information at multiple locations in the final text of the work, wherein the voice information includes at least one of speech speed, intonation, tone, and voice emotion;

[0101] In response to a confirmation operation on the final draft of the work text and the music information, a work generated based on the final draft of the work text and the music information is displayed.

[0102] In some embodiments, the apparatus further comprises at least one of the following:

[0103] A second information display unit is configured to display the modified music information in response to a modification operation on the music information, and to display a work generated based on the final work text and the modified music information in response to a confirmation operation on the final work text and the modified music information;

[0104] The playing unit is configured to execute a listening operation on any segment in the final draft of the work text and play the segment based on the soundtrack information corresponding to the segment.

[0105] According to another aspect of an embodiment of the present disclosure, a work generation device is provided, the device comprising:

[0106] an information acquisition unit, configured to acquire dialogue information sent by a first role on a dialogue interface, wherein the dialogue interface is a dialogue interface between the first role and a second role, the first role is controlled by a first object, the first object is a terminal login object, and the second role is controlled by artificial intelligence;

[0107] a dialogue generating unit, configured to generate multiple rounds of dialogue between the first character and the second character based on the dialogue information of the first character;

[0108] A work generation unit is configured to generate a work based on the dialogue information of the multiple rounds of dialogues, wherein the work includes a storyline generated by the first character, the second character and the dialogue information of the multiple rounds of dialogues.

[0109] In some embodiments, the work generation unit is configured to execute:

[0110] Generating a story outline of the work based on the dialogue information of the multiple rounds of dialogue;

[0111] The work is generated based on the dialogue information of the multiple rounds of dialogue and the story outline.

[0112] In some embodiments, the work generation unit is configured to execute:

[0113] Based on the dialogue information of the multiple rounds of dialogue, determining multiple target plots and emotion information in the dialogue information of the multiple rounds of dialogue;

[0114] The story outline is generated based on the dialogue information of the multiple rounds of dialogue, the multiple target plots and the emotion information.

[0115] In some embodiments, the work generation unit is configured to execute:

[0116] Based on the dialogue information of the multiple rounds of dialogue and the story outline, a preliminary draft of the work text is generated, wherein the preliminary draft of the work text includes character dialogue text, narration information, and environment description information generated from the dialogue information of the multiple rounds of dialogue;

[0117] The work is generated based on the first draft of the work text.

[0118] In some embodiments, the work generation unit is configured to execute:

[0119] Based on the dialogue information of the multiple rounds of dialogue and the story outline, the dialogue information of the multiple rounds of dialogue is expanded, and based on the expanded dialogue information and the story outline, a first draft of the work text is generated.

[0120] In some embodiments, the work generation unit is configured to execute:

[0121] Based on the draft text of the work, a final draft text of the work and music information are generated, wherein the music information includes timbre information of each of the two characters, background music information, and at least one of sound effect information and voice information at multiple locations in the final draft text of the work, wherein the voice information includes at least one of speech speed, intonation, tone, and voice emotion;

[0122] The work is generated based on the final draft of the work text and the soundtrack information.

[0123] In some embodiments, the work generation unit is configured to execute:

[0124] Based on the first draft of the work text, generate the final draft of the work text;

[0125] The music information is generated based on the final draft of the work text.

[0126] In some embodiments, the work generation unit is configured to perform at least one of the following:

[0127] Determining the personality characteristics of the first character and the second character based on the final draft of the work text, and determining the timbre information of the first character and the second character based on the personality characteristics of the first character and the second character;

[0128] Based on the final draft of the work text, determining the dialogue scenes and environmental elements of each of the multiple positions in the final draft of the work text, and based on the dialogue scenes and environmental elements of each of the multiple positions, determining the sound effect information of each of the multiple positions;

[0129] Based on the final draft of the work text, the emotional information of each of the multiple positions in the final draft of the work text is determined, and based on the emotional information of each of the multiple positions, the voice information of the multiple positions is determined.

[0130] According to another aspect of an embodiment of the present disclosure, an electronic device is provided, the electronic device comprising:

[0131] processor;

[0132] a memory for storing instructions executable by the processor;

[0133] The processor is configured to execute the instructions to implement the above-mentioned work generation method.

[0134] According to another aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the above-mentioned work generation method.

[0135] According to another aspect of an embodiment of the present disclosure, a computer program product is provided, wherein the computer program product includes a computer program, and when the computer program is executed by a processor, the above-mentioned work generation method is implemented.

[0136] The disclosed embodiment provides a method for generating a work, in which a terminal login object conducts multiple rounds of dialogues with a character controlled by artificial intelligence, and a work can be generated and displayed based on the dialogue information of the multiple rounds of dialogues. The work includes a storyline generated by two dialogue characters and the dialogue information of the multiple rounds of dialogues. In this way, the work can be generated through dialogue, and the terminal login object does not need to perform various operations, thereby improving the efficiency of human-computer interaction.

[0137] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0138] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0139] Figure 1 It is a schematic diagram showing an implementation environment according to an exemplary embodiment.

[0140] Figure 2 The present invention is a flowchart of a method for generating works according to an exemplary embodiment.

[0141] Figure 3 The present invention is a flowchart of another method for generating works according to an exemplary embodiment.

[0142] Figure 4 It is a schematic diagram showing a role configuration according to an exemplary embodiment.

[0143] Figure 5 The figure is a schematic diagram of an editing interface for a first draft of a work text according to an exemplary embodiment.

[0144] Figure 6 It is a schematic diagram of another editing interface of a draft text of a work according to an exemplary embodiment.

[0145] Figure 7 The figure is a flowchart of music processing according to an exemplary embodiment.

[0146] Figure 8 The figure is a flowchart of text editing according to an exemplary embodiment.

[0147] Fig. 9 The present invention is a flowchart of another method for generating works according to an exemplary embodiment.

[0148] Fig.10 It is a block diagram of a device for generating works according to an exemplary embodiment.

[0149] Fig.11 It is a block diagram of another device for generating works according to an exemplary embodiment.

[0150] Fig.12 It is a block diagram of a terminal according to an exemplary embodiment.

[0151] Fig.13 It is a block diagram of a server according to an exemplary embodiment. DETAILED DESCRIPTION

[0152] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0153] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0154] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions. For example, the conversation information, attribute information, etc. involved in this disclosure are all obtained with full authorization.

[0155] The work generation method provided by the embodiment of the present disclosure can be executed by an electronic device, and the electronic device can be provided as at least one of a terminal and a server. Figure 1 This is a schematic diagram of an implementation environment provided by the embodiment of the present disclosure, see Figure 1 , the implementation environment includes: a terminal 101 and a server 102.

[0156] In the disclosed embodiment, a target application is installed on the terminal 101, and the target application is used to generate works based on dialogue. Optionally, the target application provides a dialogue interface for the first role and the second role, and the two roles are controlled by the terminal login object and artificial intelligence respectively. The terminal login object performs dialogue operations on the dialogue interface, and the second role can automatically reply based on artificial intelligence, and then the dialogue interface can display multiple rounds of dialogue between the two roles to obtain dialogue information of multiple rounds of dialogue. In response to the work generation operation, the work generated based on the dialogue information of multiple rounds of dialogue can be displayed.

[0157] Server 102 is a background server of the target application, and is used to provide background services for the target application, such as providing reply information of the second character, generating works based on dialogue information of multiple rounds of dialogue, etc.

[0158] The terminal 101 may be at least one of a smart phone, a smart watch, a desktop computer, a laptop, a virtual reality terminal, an augmented reality terminal, a wireless terminal, and a laptop computer. The terminal 101 has a communication function and can access a wired network or a wireless network. The terminal 101 may generally refer to one of a plurality of terminals, and those skilled in the art may know that the number of the above terminals may be more or less. The server 102 may be an independent physical server, or a server cluster or a distributed file system composed of a plurality of physical servers, or a cloud server 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, CDN (Content Delivery Network), and big data and artificial intelligence platforms. In some embodiments, the server 102 is directly or indirectly connected to the terminal 101 via a wired or wireless communication method, which is not limited in the embodiments of the present disclosure. Optionally, the number of the above servers 102 may be more or less, which is not limited in the embodiments of the present disclosure. Of course, the server 102 may also include other functional servers to provide more comprehensive and diversified services. Among them, the server 102 undertakes the main computing work, and the terminal 101 undertakes the secondary computing work; or, the server 102 undertakes the secondary computing work, and the terminal 101 undertakes the main computing work; or, the server 102 or the terminal 101 can each independently undertake the computing work, which is not limited in the embodiments of the present disclosure.

[0159] Figure 2 is a flowchart of a method for generating works according to an exemplary embodiment. Figure 2 As shown, the method is executed by a terminal, and the method includes the following steps.

[0160] In step S201, in response to the initialization operation of the work, the terminal displays a dialogue interface between a first character and a second character, the first character is controlled by a first object, which is a terminal login object, and the second character is controlled by artificial intelligence.

[0161] In the disclosed embodiment, the initialization operation can be set and changed as needed. If the terminal provides a control for the initialization operation, the initialization operation refers to a triggering operation on the control. Accordingly, the control is also an entry control of the dialogue interface. Optionally, the terminal performs the initialization operation on the initialization interface of the work, and enters the dialogue interface after completing the initialization operation. The initialization interface is used to initialize the work, such as initializing the attribute information of the first character and the second character.

[0162] The first role and the second role may be roles in the real world, such as a teacher, a doctor, etc., or roles in the virtual world, such as a role in a TV series, a movie, or a cartoon.

[0163] In step S202, in response to the dialogue operation of the first object on the dialogue interface, the terminal displays multiple rounds of dialogue between the first character and the second character on the dialogue interface.

[0164] In the disclosed embodiment, the dialogue information sent by the first object based on the dialogue operation can be at least one of text information, voice information, picture information or video information. The second character is controlled by artificial intelligence, and the reply information of the second character is automatically generated by the artificial intelligence based on the dialogue information of the first object. The reply information of the second character can be at least one of text information, voice information, picture information or video information. The method supports multiple interaction modes such as voice and text during the dialogue process, which enhances ease of use and flexibility.

[0165] In the disclosed embodiment, the information sent by the second character may not only be a reply message to the dialogue message of the first object, but also be a dialogue message automatically generated based on the generated dialogue, such as an inquiry message to the first object.

[0166] In step S203, in response to the work generation operation, the terminal displays a work generated based on the dialogue information of multiple rounds of dialogue, where the work includes a storyline generated by the first character, the second character and the dialogue information of multiple rounds of dialogue.

[0167] In some embodiments, a work generation control is displayed on the dialogue interface, and the work generation operation is a trigger operation on the work generation control; or the work generation operation is a preset gesture operation on the dialogue interface, which is not specifically limited here.

[0168] In the disclosed embodiment, the work may be a text work, an audio work or a video work, etc. The text work may be a novel, a script, etc., the audio work may be an audio novel, a song, etc., and the video work may be a movie, etc. Optionally, the terminal provides a work type option, and when generating a work, you may choose to generate a work of any work type.

[0169] The disclosed embodiment provides a method for generating a work, wherein a terminal login object conducts multiple rounds of dialogue with a character controlled by artificial intelligence, and a work can be generated and displayed based on the dialogue information of the multiple rounds of dialogue, and the work includes a storyline generated by two dialogue characters and the dialogue information of the multiple rounds of dialogue, so that the work can be generated through dialogue, without the need for the terminal login object to perform various operations, thereby improving the efficiency of human-computer interaction. Moreover, this method not only lowers the threshold for the creation of works, but also enables the terminal login object to deeply participate in the creation of the works, so that on the basis of improving the efficiency of human-computer interaction, the generated works are more in line with the personalized needs of the terminal login object, thereby improving the quality of the works.

[0170] Above Figure 2 The following is only the basic process of the present disclosure. The solution provided by the present disclosure is further described based on a specific implementation method. Figure 3 , Figure 3 It is a flowchart of another method for generating works according to an exemplary embodiment. The method includes the following steps.

[0171] In step S301, the terminal displays a configuration interface, where the configuration interface is used to configure attribute information of a second character, where the second character is controlled by artificial intelligence.

[0172] The attribute information of the second character includes at least one of the role type, personality traits, voice style, and role relationship of the second character with the first character.

[0173] In some embodiments, the configuration interface displays multiple role types, multiple personality traits, multiple voice styles, and multiple role relationships, that is, the terminal displays a role selection interface on which personalized selections can be made. The first object can select any role type, any personality trait, any voice style, and any role relationship to be configured as the attribute information of the second role.

[0174] In other embodiments, the first object may also customize the attribute information of the second character. For example, when customizing personality traits, the first object may input personality traits on the configuration interface and configure the input personality type as the personality type in the attribute information of the second object.

[0175] In some embodiments, the configuration interface may also be used to configure a dialogue scene. Optionally, the configuration interface displays a variety of dialogue scenes, and the first object may select any dialogue scene to configure as the dialogue scene of the work; or, the first object may also customize the dialogue scene, which is not specifically limited here. In some embodiments, the configuration interface may also be used to configure the attribute information of the first character, and the process is the same as the process of configuring the attribute information of the second character, which will not be repeated here.

[0176] In step S302, in response to a confirmation operation on the attribute information configured in the configuration interface, the terminal displays a dialogue interface between the first role and the second role, the first role is controlled by the first object, and the first object is a terminal login object.

[0177] In some embodiments, a confirmation control is displayed on the configuration interface, and the confirmation operation is also a triggering operation of the confirmation control. Alternatively, the confirmation operation refers to a preset gesture operation on the configuration interface, which is not specifically limited here.

[0178] In this embodiment, the process of displaying the dialogue interface between the first character and the second character in response to the initialization operation of the work is implemented through the above-mentioned step S302. In this embodiment, the confirmation operation on the attribute information completes the initialization operation of the work, and the basic information of the work is obtained. The attribute information of the second character is configured in advance through the configuration interface, so that the dialogue content between the first character and the second character revolves around the pre-configured attribute information, ensuring the consistency of the character behavior and providing a basis for subsequent dialogue and content generation.

[0179] For example, see Figure 4 , Figure 4 This is a schematic diagram of a role configuration according to an exemplary embodiment, wherein the first object can select a role from the provided roles, or can customize a role, and after the role is configured, the initialization of the dialogue scene is realized.

[0180] In step S303, in response to the dialogue operation of the first object on the dialogue interface, the terminal displays multiple rounds of dialogue between the first character and the second character on the dialogue interface.

[0181] In each round of dialogue, in response to the dialogue operation of the first object on the dialogue interface, the terminal displays the dialogue information sent by the first character and the reply information sent by the second character on the dialogue interface. Since the second character is controlled by artificial intelligence, the reply information sent by the second character is generated by artificial intelligence. Optionally, the reply information is generated by artificial intelligence through a server. In the embodiment, the terminal sends the dialogue information of the first character to the server, the server obtains the dialogue information sent by the first character, generates the reply information of the second character based on the dialogue information of the first character, and then returns the reply information to the terminal to display the reply information of the second character on the dialogue interface of the terminal.

[0182] In the disclosed embodiment, the attribute information of the second character is configured in advance, and optionally, the reply information of the second character also corresponds to the attribute information of the second character. Accordingly, the server obtains the attribute information of the second character, and generates the reply information of the second character based on the attribute information of the second character and the dialogue information of the first character. Among them, the server can construct a personality characteristic model of the second character based on the attribute information of the second character, and the personality characteristic model includes information such as the language style and emotional tendency of the second character, and then generates the reply information of the second character based on the personality characteristic model.

[0183] In this embodiment, the reply information of the second character is also generated based on the attribute information of the second character, so that the dialogue content between the first character and the second character revolves around the uniformly configured attribute information, ensuring the consistency of the character behavior and providing a basis for subsequent dialogue and content generation.

[0184] In the disclosed embodiments, context retention of long conversations is supported. To ensure the continuity of the conversation and the consistency of the character behaviors, when generating the reply information of the second character, the server not only refers to the conversation information of the first character and the attribute information of the second character in the current conversation, but also can refer to the conversation information of previous rounds of conversations. That is, during the conversation, the artificial intelligence can understand the context logic and make replies that are consistent with the role settings to ensure the continuity and consistency of multiple rounds of conversations.

[0185] In the disclosed embodiment, the first object conducts a dialogue with the second character controlled by artificial intelligence as the first character, and the artificial intelligence generates a natural and coherent dialogue response with the first character based on the attribute information of the set second character. The server can record the dialogue content of each round of dialogue in real time, which is convenient for subsequent use. Among them, the server records the dialogue text between the first character and the second character by role. Further, the role action information and emotional information of the first character and the second character when sending the information are also recorded. Optionally, the role action information and emotional information can exist in the dialogue information sent by the first character and the second character. For example, if the dialogue information is: You shouldn’t do this, (blinked at this time), then blinking is the role action information. Further, the server can also automatically extract the role action information and emotional information from the dialogue information. For example, if the dialogue information is: I am so happy, then the corresponding role action information can be laughing. In this embodiment, by recording the dialogue content, the original creative material is accumulated, which provides a basis for the generation of plots in subsequent works.

[0186] In step S304, in response to the work generation operation, the terminal displays a story outline generated based on the dialogue information of multiple rounds of dialogue.

[0187] The story outline includes at least one of the plot context and character relationships.

[0188] In some embodiments, a story outline is generated by a server, that is, in response to a work generation operation, the terminal sends a story outline generation instruction to the server, and the server generates a story outline based on dialogue information of multiple rounds of dialogue, and returns the story outline to the terminal for display.

[0189] In some embodiments, the process by which the server generates a story outline of a work based on dialogue information from multiple rounds of dialogue includes the following implementation methods: the server determines multiple target plots and emotional information in the dialogue information from multiple rounds of dialogue based on the dialogue information from multiple rounds of dialogue; and generates a story outline based on the dialogue information from multiple rounds of dialogue, multiple target plots and emotional information.

[0190] The emotional information may refer to multiple emotions in multiple rounds of dialogue, or may refer to emotional change information in multiple rounds of dialogue. Optionally, the server performs semantic and emotional analysis on the dialogue information of the multiple rounds of dialogue to extract the target plot and emotional change information therein.

[0191] In other embodiments, the server uses key sentence recognition and event extraction technology to extract important plots and events in the dialogue to obtain multiple target plots. That is, the target plot includes important plot parts that can express the theme of the work or explain important story lines, and the target plot may also include plot parts where preset events occur.

[0192] Optionally, the server generates an emotional curve of the dialogue according to the emotional changes in the dialogue, and then guides the development and climax setting of the plot based on the emotional curve, and then generates a story outline in combination with multiple target plots.

[0193] In some embodiments, the conversation information used to generate a story outline can also be modified to generate a story outline based on the modified conversation information. The above process in which the terminal displays a story outline generated based on conversation information of multiple rounds of conversations in response to a work generation operation includes the following steps: in response to the work generation operation, the terminal displays an editing interface for conversation information of multiple rounds of conversations; in response to an editing operation on conversation information of multiple rounds of conversations, the edited conversation information is displayed; in response to a confirmation operation on the edited conversation information, the story outline generated based on the edited conversation information is displayed.

[0194] The editing interface is used to edit the dialogue information of multiple rounds of dialogue. The dialogue information of multiple rounds of dialogue is displayed on the editing interface. The editing operation of the dialogue information of multiple rounds of dialogue can be a deletion operation or a content modification operation of any round of dialogue, or can be an addition of one or more rounds of dialogue information, which is not specifically limited here. It should be noted that if the dialogue information is not edited on the editing interface, then in response to the confirmation operation of the dialogue information on the editing interface, the story outline generated based on the dialogue information of multiple rounds of dialogue is directly displayed.

[0195] In this embodiment, an editing interface for conversation information of multiple rounds of conversations is displayed, so that the first object can edit the conversation information, that is, the first object is allowed to customize the editing of the conversation information, which further improves the participation of the first object and makes the generated story outline more in line with the personalized needs of the first object, thereby improving the user experience.

[0196] In step S305, in response to the confirmation operation on the story outline, the terminal displays the dialogue information of the multiple rounds of dialogue and the work generated by the story outline.

[0197] In some embodiments, a confirmation control is displayed on the display interface of the story outline, and the confirmation operation on the story outline refers to a triggering operation on the confirmation control; or, the confirmation operation on the story outline is a preset gesture operation on the display interface.

[0198] In some embodiments, the work is generated by the server, that is, in response to the confirmation operation of the story outline, the terminal sends a work generation instruction to the server, and the server generates the work based on the dialogue information of multiple rounds of dialogue and the story outline, and returns the work to the terminal for display.

[0199] In some embodiments, the first object can also modify the story outline, and then generate a work based on the modified story outline. In response to the modification operation of the story outline, the terminal displays the modified story outline; in response to the confirmation operation of the modified story outline, the terminal displays the dialogue information based on the multi-round dialogue and the work generated by the modified story outline.

[0200] Optionally, the story outline displayed by the terminal can be directly edited and modified, that is, a visual editing interface for the story outline is provided. In this embodiment, providing a visual editing interface allows the first object to make personalized modifications to the story outline, that is, allowing the first object to customize the story outline, further improving the participation of the first object, making the story outline more in line with the personalized needs of the first object, and then making the generated work more in line with the personalized needs of the first object, thereby improving the quality of the work.

[0201] In some embodiments, the terminal displays a story outline generated based on conversation information of multiple rounds of conversations, which means displaying multiple story outline templates, and the multiple story outline templates are all associated with the conversation information of multiple rounds of conversations; then the above-mentioned process in which the terminal displays the conversation information based on multiple rounds of conversations and the work generated by the story outline in response to the confirmation operation of the story outline, includes the following implementation method: in response to the selection operation of any story outline template, the terminal displays the work generated based on the conversation information of multiple rounds of conversations and the selected story outline template.

[0202] Each story outline template includes at least one of a plot context and a role relationship. Different story outline templates have at least a part of different plot contexts or different role relationships. It should be noted that the first object can modify any selected story outline template to further improve the flexibility and convenience of the operation.

[0203] In this embodiment, a plurality of story outline templates are provided for the first object, that is, a variety of choices are provided for the first object, so that the provided story outline meets the needs of the first object as much as possible, reducing the possibility of the first object modifying the story outline, that is, reducing operations and improving efficiency.

[0204] In other embodiments, the terminal further provides a visual plot editor, which includes multiple plot elements, and the first object can customize the plot by dragging the plot elements to generate a story outline. For example, the plot elements may include forest, happiness, running, etc.

[0205] In the disclosed embodiment, the above steps S304-S305 implement the process of the terminal displaying the work generated based on the dialogue information of multiple rounds of dialogue in response to the work generation operation. In this embodiment, when the work is generated based on the dialogue information of multiple rounds of dialogue, the story outline is first generated and displayed. When the first object confirms that the story outline is feasible, the work is generated based on the story outline. In this way, the story outline is first generated, that is, a preliminary plot framework is formed, and then the work is generated based on the story outline. The story outline can be used to convert the dialogue information into a coherent story structure, so that the storyline and plot in the work are more reasonable, coherent and complete, and the story outline has been confirmed by the first object, so that the generated work is more in line with the personalized needs of the first object, further improving the quality of the work.

[0206] In the disclosed embodiments, works can be directly generated from the dialogue information and story outline of multiple rounds of dialogue. In other embodiments, a draft of the work text can be generated first, and then the work is generated based on the draft of the work text. The above process of the terminal displaying the work generated based on the dialogue information and story outline of multiple rounds of dialogue in response to the confirmation operation of the story outline includes the following steps: in response to the confirmation operation of the story outline, the terminal displays the draft of the work text generated based on the dialogue information and story outline of multiple rounds of dialogue; in response to the confirmation operation of the draft of the work text, the terminal displays the work generated based on the draft of the work text.

[0207] The first draft of the work text includes character dialogue text, narration information and environment description information generated from the dialogue information of multiple rounds of dialogue. In this embodiment, the first draft of the work text is generated based on the dialogue information of multiple rounds of dialogue and the story outline, that is, the dialogue information is converted into a preliminary work text, which presents the content in a role-in-role manner. It is a structured first draft of the work text, and the dialogue text and narration of each character are arranged in sequence. If the work to be generated is a novel, the first draft of the work text is a preliminary novel text. In this embodiment, the first draft of the work text is generated, that is, the basic text of the work is generated first, which is convenient for providing materials for subsequent editing.

[0208] Among them, the narration information and the environment description information can be automatically generated by the server based on the dialogue information of multiple rounds of dialogue, so as to expand the first draft of the work text, so that the first draft of the work text is richer in content and higher in quality.

[0209] In some embodiments, a first draft of the text of the work is generated by the server, that is, in response to a confirmation operation on the story outline, the terminal sends an instruction to generate a first draft of the text of the work to the server, and the server generates a process of the work based on the dialogue information of multiple rounds of dialogue and the story outline, that is, the server generates a first draft of the text of the work based on the dialogue information of multiple rounds of dialogue and the story outline, and generates the work based on the first draft of the text of the work.

[0210] In this embodiment, when a work is generated based on the conversation information and story outline of multiple rounds of conversations, a first draft of the work text is first generated and displayed. When the first object confirms that the first draft of the work text is feasible, the work is generated based on the first draft of the work text. Displaying the first draft of the work text to the first object increases the first object's participation, and the generated work is more in line with the first object's personalized needs, further improving the quality of the work.

[0211] In some embodiments, when generating a first draft of the text of the work, the server can also expand the conversation information, that is, the server generates a first draft of the text of the work based on the conversation information and story outline of multiple rounds of conversations, including the following implementation method: the server expands the conversation information of multiple rounds of conversations based on the conversation information and story outline of multiple rounds of conversations, and generates a first draft of the text of the work based on the expanded conversation information and story outline.

[0212] Among them, expanding the dialogue information of multiple rounds of dialogue includes adding at least one more round of dialogue on the basis of the original multiple rounds of dialogue, and also includes adding content to the dialogue information in at least one round of dialogue, so that the dialogue information of the first character and the reply information of the second character are richer.

[0213] In this embodiment, the dialogue information is expanded based on the dialogue information and story outline of multiple rounds of dialogue, so that the expanded dialogue information is logically consistent with the original dialogue information and story outline, and the content is reasonable, ensuring the effectiveness of the expansion. The first draft of the work text is generated based on the expanded dialogue information and story outline, so that the content of the first draft of the work text is richer and the quality is higher.

[0214] In some embodiments, the first object can also modify the draft text of the work. In response to the modification operation on the draft text of the work, the terminal displays the modified draft text of the work, and the modification operation includes at least one of the following operations: adjusting the order of the character dialogue text, adding, deleting, modifying the narration information, and modifying the environment description information; in response to the confirmation operation on the modified draft text of the work, the work generated based on the modified draft text of the work is displayed.

[0215] For example, see Figure 5 , Figure 5A schematic diagram of an editing interface for a draft text of a work according to an exemplary embodiment. The first object can modify any segment in the draft text of the work. Furthermore, the audio of any segment can be edited on the editing interface. The audio is also the soundtrack, including at least one of background music, sound effect information, timbre information, voice information, etc. And the audio of any segment can be auditioned on the editing interface. Furthermore, at least one round of dialogue, narration information or environmental description information can be added, and audio can be set for the added content. For example, see Figure 6 .

[0216] Among them, the draft text of the work displayed by the terminal can be directly edited and modified, that is, a visual editing interface for the draft text of the work is provided. In this embodiment, providing a visual editing interface allows the first subject to make personalized modifications to the draft text of the work, that is, allowing the first subject to customize and edit the draft text of the work, and then the first subject can improve the draft text of the work, providing high-quality materials for the generation of works and soundtracks, further improving the participation of the first subject, making the draft text of the work more in line with the personalized needs of the first subject, and then making the generated work more in line with the personalized needs of the first subject, and improving the quality of the work.

[0217] In some embodiments, a one-click modification function for the draft text of the work is also provided. In response to the confirmation operation of the story outline, the terminal displays modification prompt information for the draft text of the work, and the modification prompt information is used to prompt the method of modifying the draft text of the work; in response to the modification operation of the draft text of the work, the terminal displays the modified draft text of the work, including the following implementation methods: in response to the triggering operation of the modification prompt information, the terminal displays the draft text of the work modified based on the modification prompt information.

[0218] The modification prompt information includes modification prompts for at least one aspect of the first draft of the work text, such as prompts on how to modify narration information, prompts on how to polish the text, prompts on how to adjust the plot, etc.

[0219] In this embodiment, the modification prompt information is not only used to prompt the first object to modify the draft text of the work, but also prompts how to modify it, thereby improving the transparency of information. Triggering the modification prompt information can modify the draft text of the work and generate the work in one click, thereby improving the efficiency of human-computer interaction.

[0220] In some embodiments, the terminal displays modification prompt information while displaying the draft text of the work. In other embodiments, the terminal displays modification prompt information only when a modification operation on the draft text of the work is detected. Furthermore, the modification prompt information is generated based on the modified content of the first object, so that the modification prompt information is more in line with the personalized modification requirements of the first object.

[0221] Furthermore, the terminal may display a plurality of modification prompt information, and the plurality of modification prompt information is used to indicate a plurality of different modification methods, so that the first subject may independently select any modification method to modify the first draft of the work text, thereby improving the diversity of selection and modification efficiency.

[0222] In the above embodiments, the example of directly generating a work based on a preliminary draft of the work text is used for explanation. In other embodiments, the above process in which the terminal displays the work generated based on the preliminary draft of the work text in response to the confirmation operation of the preliminary draft of the work text also includes the following implementation method: in response to the confirmation operation of the preliminary draft of the work text, the terminal displays the final draft of the work text and music information generated based on the preliminary draft of the work text, the music information includes the timbre information of each of the two characters, the background music information, and at least one of the sound effect information and voice information at multiple positions in the final draft of the work text, and the voice information includes at least one of the speech speed, intonation, tone and voice emotion; in response to the confirmation operation of the final draft of the work text and the music information, the work generated based on the final draft of the work text and the music information is displayed.

[0223] In some embodiments, the final draft of the work text and the music information are generated by the server, that is, in response to the confirmation operation of the preliminary draft of the work text, the terminal sends a generation instruction of the final draft of the work text and the music information to the server, and the server generates the final draft of the work text and the music information based on the preliminary draft of the work text, and returns the final draft of the work text and the music information to the terminal for display.

[0224] Among them, the process of the server generating the final draft of the work text and music information based on the preliminary draft of the work text includes the following steps: the server generates the final draft of the work text based on the preliminary draft of the work text; the server generates music information based on the final draft of the work text.

[0225] Optionally, the format of the final work text is different from the format of the first work text, for example, the first work text is a text content that is common to various types of works, while the final work text is a text content that is specific to a certain type of work, so the two have different formats, that is, the first work text is processed based on the format of the type of work to be generated to obtain the final work text. Furthermore, if the first object modifies the first work text, the first work text is also processed based on the modification information to obtain the final work text.

[0226] Accordingly, when displaying the draft text of the work, the terminal can also display multiple work types. In response to the selection operation of any work type, the terminal displays the final draft text of the work corresponding to the work type, and then subsequently generates works of this work type.

[0227] In some embodiments, the process of the server generating the soundtrack information based on the final draft of the work text includes at least one of the following implementations:

[0228] (1) The server determines the personality characteristics of the first character and the second character based on the final draft of the work text, and determines the timbre information of the first character and the second character based on the personality characteristics of the first character and the second character.

[0229] The timbre information may include at least one of pitch, speed, and timbre fullness. In some embodiments, the timbre information of the character may also be obtained based on the basic timbre. For example, the basic timbre may be converted to a timbre corresponding to the character's personality traits through a timbre conversion model. The timbre conversion model may obtain the timbre of the character based on one basic timbre, or may combine multiple basic timbres to obtain the timbre of the character, which is not specifically limited here.

[0230] In some embodiments, a large number of real voice samples can be pre-recorded, and then the most matching timbre can be selected according to the character's personality characteristics. Further, a speech synthesis plug-in can be used to synthesize more timbres to provide more choices.

[0231] In this embodiment, the personality characteristics of any character may be the personality characteristics of the character automatically summarized by the server based on the final draft of the work text, or may be the personality characteristics of the character annotated by the first object, or may include both the automatically summarized and the first object annotated, and no specific limitation is made here.

[0232] In this embodiment, the timbre information of the first character and the second character is automatically determined based on their respective personality traits, which not only improves efficiency but also enables generation of timbre exclusive to each character, thereby enhancing the personalized characteristics of the characters.

[0233] (2) The server determines the dialogue scenes and environmental elements of the multiple locations in the final draft of the work based on the final draft of the work text, and determines the sound effect information of the multiple locations based on the dialogue scenes and environmental elements of the multiple locations.

[0234] The server identifies the dialogue scene based on the final draft of the work text, and the dialogue scene may be a forest, a city, a supermarket, etc. Environmental factors are elements that exist in the dialogue scene. For example, if the dialogue scene is a forest, the environmental elements may include birds. Based on the dialogue scenes and environmental elements of the multiple locations, the sound effect information of the multiple locations is determined, and the sound effect information of each location corresponds to the dialogue scene and environmental elements of the location. If the dialogue scene is in a forest and the environmental elements include birds, the sound effect information may be bird calls. Furthermore, the sound effect information includes not only the type of sound effect, but also the duration and volume change information of the sound effect.

[0235] Optionally, there is a pre-established sound effect library in the server, which includes multiple sound effects. Furthermore, the multiple sound effects in the sound effect library are classified and managed, so as to facilitate retrieval and calling. It should be noted that for special or rare sound effects, which may not exist in the sound effect library, a generative model (such as a GAN model) can be used to automatically generate the sound effects.

[0236] In this embodiment, the sound effect information of each location is determined according to the dialogue scene and environmental elements of each location, and the insertion position, duration and volume change of the sound effect are intelligently arranged based on the plot progression, so that the sound effect of the work is more comprehensive and more effective, which can provide users with an immersive experience and thus improve the quality of the work.

[0237] In some embodiments, in order to improve the selectivity of sound effects, the server can also directly call the authorized online open source sound effect library to enrich the sound effect resources. Further, a sound effect adding interface can be provided to allow the first object to manually select and insert sound effects, so that the first object can customize the sound effects.

[0238] (3) The server determines the emotional information of multiple locations in the final draft of the work text based on the final draft of the work text, and determines the voice information of multiple locations based on the emotional information of the multiple locations.

[0239] The voice information is determined based on the emotional information of each position, that is, when the text content at the position is played, the corresponding voice corresponds to the emotional information at the position. Optionally, the emotional synthesis technology is used to make the character voice show corresponding emotional expression in different situations.

[0240] The emotional information of each position may be annotated by the first object, or may be automatically identified by the server based on the final draft of the work text, or may include both annotated by the first object and automatically identified. Furthermore, the first object also annotates a common speaking speed for the final draft of the work text, and the speaking speed in the soundtrack information is the common speaking speed. Alternatively, if the first object annotates different speaking speeds at different positions in the final draft of the work text, the speaking speed of the annotated position is used as the speaking speed of the position, and the common speaking speed is used as the speaking speed of the unannotated position.

[0241] In the disclosed embodiment, when generating music information, sound effect information, background music, timbre information, voice information, etc. can be generated at the same time; multiple configuration information can also be generated in a certain order. For example, the timbre information is generated first, then the voice information is generated, and finally the sound effect information is generated, and the generation of the music information in the latter order can also refer to the music information generated in the former order. For example, see Figure 7 , Figure 7 The figure is a flowchart of music processing according to an exemplary embodiment.

[0242] In some embodiments, the first object can also modify the music information. In response to the modification operation of the music information, the terminal displays the modified music information, and in response to the confirmation operation of the final work text and the modified music information, the terminal displays the work generated based on the final work text and the modified music information.

[0243] Among them, the soundtrack information displayed by the terminal can be directly edited and modified, that is, a visual editing interface for the soundtrack information is provided. In this embodiment, providing a visual editing interface allows the first object to personalize the soundtrack information, that is, allowing the first object to customize the soundtrack information, further improving the participation of the first object, making the soundtrack information more in line with the personalized needs of the first object, and then making the generated work more in line with the personalized needs of the first object, thereby improving the quality of the work.

[0244] In other embodiments, in response to an audition operation of any segment in the final draft of the work text, the terminal plays the segment based on the music information corresponding to the segment. In this embodiment, the first subject can audition any segment based on the music information, so that the first subject can actually feel the music effect, and then make modifications on this basis, which can improve the effectiveness and efficiency of the modifications.

[0245] It should be noted that the present disclosure can generate music information not only when generating the final draft of the work text, but also at any stage such as generating the work, generating the story outline, generating the first draft of the work text, etc. For example, in response to the work generation operation, the terminal displays the music information generated based on the dialogue information of the multi-round dialogue, and in response to the confirmation operation of the music information, the work is generated based on the dialogue information and the music information of the multi-round dialogue.

[0246] In the disclosed embodiment, the first object can modify the content generated in multiple stages, which meets the personalized creation needs of the first object. Optionally, the server records each modification, so as to facilitate subsequent query and restoration of the version before the modification, that is, to provide a version control function, further improving the convenience of interaction in the work generation process.

[0247] For example, see Figure 8 , Figure 8 The present invention is a flowchart of a text editing process provided according to an exemplary embodiment. The terminal provides a visual editing interface on which the text can be edited and adjusted, and a voice audition can be performed. After the editing and adjustment, a version record can be performed to implement version management.

[0248] In the disclosed embodiment, after the work is generated, the work can be converted into multiple formats to support users to download and share. In addition, the server provides a cloud storage function, and users can manage and access the work at any time, which can realize the storage and distribution of the work, thereby enhancing the dissemination of the work.

[0249] In the disclosed embodiment, the first object can add, delete and modify the content generated in multiple stages, that is, it provides an intelligent text editing function, and can also perform intelligent completion and real-time grammar style checking with one click. In addition, comprehensive role management is provided, not only can the attributes of the role be configured through the role list, but also the dialogue information and narration information of any role can be edited and added. In addition, the sound effects and background music can be edited, and a complete sound effect and background music editing tool is provided, which supports automatic recommendation and fine adjustment of sound effects and background music. In addition, content reorganization can also be performed, allowing the first object to adjust the order of paragraphs by dragging and dropping, copying and deleting content, and providing version control functions. In addition, timbre and voice parameter adjustment are supported, that is, the first object is allowed to customize the timbre of the role, adjust emotional expression, and edit tone and intonation, etc. In addition, multi-version management is supported, that is, each editing and modification operation is recorded, and version comparison and backtracking are supported. In addition, local generation can also be performed based on the dialogue content, that is, the first object can select a specific chapter or paragraph and regenerate it without reprocessing it from scratch. In addition, intelligent suggestions are also provided. The server can provide modification suggestions based on the modification of the first object, such as prompts on how to polish the language, adjust the plot, etc.

[0250] The method provided by the embodiment of the present disclosure brings beneficial effects including but not limited to the following aspects. First, it reduces the threshold for creation and production. Among them, through human-machine role-playing, users can create high-quality audio novels and other works without professional writing and audio production skills. In addition, the method provides full-process support, including content generation, audio synthesis, sound effect addition, etc., which simplifies the production process. Secondly, it improves user participation and creative experience. Among them, users deeply participate in the creation of works, interact with artificial intelligence characters, and jointly promote the development of the plot, which enhances the fun of creation. In addition, it supports multiple interactive methods and rich editing functions, making users' creation more free and personalized. Thirdly, personalized and high-quality audio novels are realized. Among them, according to the background and personality of the characters, exclusive and unique voices are automatically generated to enhance the uniqueness of the works and the recognition of the audience. In addition, automatic sound effect matching and generation provide an immersive auditory experience, enhance the appeal of the story, and make the works include complete plots, rich characters and realistic sound effects. Secondly, it improves production efficiency and content quality. Among them, automated content generation and audio processing greatly shorten the production cycle and reduce manpower and time costs. In addition, the application of artificial intelligence technology ensures the coherence, logic and language beauty of the work content, and improves the quality of the work. Finally, it has rich editing and customization functions. Among them, users can edit, rewrite and regenerate at any time during the creation process, which is convenient and fast and meets personalized needs. In addition, it provides intelligent editing suggestions and multi-version management, which is convenient for users to optimize their works and improve creation efficiency.

[0251] The disclosed embodiment provides a method for generating a work, wherein a terminal login object conducts multiple rounds of dialogue with a character controlled by artificial intelligence, and a work can be generated and displayed based on the dialogue information of the multiple rounds of dialogue, and the work includes a storyline generated by two dialogue characters and the dialogue information of the multiple rounds of dialogue, so that the work can be generated through dialogue, without the need for the terminal login object to perform various operations, thereby improving the efficiency of human-computer interaction. Moreover, this method not only lowers the threshold for the creation of works, but also enables the terminal login object to deeply participate in the creation of the works, so that on the basis of improving the efficiency of human-computer interaction, the generated works are more in line with the personalized needs of the terminal login object, thereby improving the quality of the works.

[0252] See also Fig. 9 , Fig. 9 It is a flowchart of another method for generating works according to an exemplary embodiment. The method is executed by a server and includes the following steps.

[0253] In step S901, the server obtains dialogue information sent by the first character on the dialogue interface, the dialogue interface is a dialogue interface between the first character and the second character, the first character is controlled by the first object, the first object is a terminal login object, and the second character is controlled by artificial intelligence.

[0254] In step S902, the server generates multiple rounds of dialogue between the first character and the second character based on the dialogue information of the first character.

[0255] In step S903, the server generates a work based on the dialogue information of the multiple rounds of dialogue, where the work includes a storyline generated by the first character, the second character and the dialogue information of the multiple rounds of dialogue.

[0256] In some embodiments, the process of the server generating a work based on the dialogue information of multiple rounds of dialogue includes the following steps: generating a story outline of the work based on the dialogue information of multiple rounds of dialogue; generating the work based on the dialogue information and story outline of multiple rounds of dialogue.

[0257] In some embodiments, the process by which the server generates a story outline of a work based on dialogue information from multiple rounds of dialogues includes the following steps: the server determines multiple target plots and emotional information in the dialogue information from multiple rounds of dialogues based on the dialogue information from multiple rounds of dialogues; the server generates a story outline based on the dialogue information from multiple rounds of dialogues, multiple target plots and emotional information.

[0258] In some embodiments, the process of the server generating a work based on the dialogue information and story outline of multiple rounds of dialogues includes the following steps: the server generates a draft text of the work based on the dialogue information and story outline of multiple rounds of dialogues, the draft text of the work including character dialogue text, narration information and environment description information generated from the dialogue information of multiple rounds of dialogues; and generates the work based on the draft text of the work.

[0259] In some embodiments, the process by which the server generates a first draft of the text of a work based on conversation information and story outlines from multiple rounds of conversations includes the following steps: based on the conversation information and story outlines from multiple rounds of conversations, expanding the conversation information from multiple rounds of conversations, and generating a first draft of the text of the work based on the expanded conversation information and story outlines.

[0260] In some embodiments, the process of generating a work based on the preliminary draft of the work text by the above-mentioned server includes the following steps: generating a final draft of the work text and music information based on the preliminary draft of the work text, the music information including timbre information of each of the two characters, background music information, and sound effect information and at least one of voice information at multiple locations in the final draft of the work text, the voice information including at least one of speech speed, intonation, tone and voice emotion; generating the work based on the final draft of the work text and the music information.

[0261] In some embodiments, the above process of generating the final draft of the work text and music information based on the preliminary draft of the work text includes the following steps: generating the final draft of the work text based on the preliminary draft of the work text; generating music information based on the final draft of the work text.

[0262] In some embodiments, the above process of generating music information based on the final draft of the work text includes at least one of the following implementation methods: determining the personality characteristics of the first character and the second character based on the final draft of the work text, and determining the timbre information of the first character and the second character based on the personality characteristics of the first character and the second character; determining the dialogue scenes and environmental elements of multiple positions in the final draft of the work text based on the final draft of the work text, and determining the sound effect information of the multiple positions based on the dialogue scenes and environmental elements of the multiple positions; determining the emotional information of multiple positions in the final draft of the work text based on the final draft of the work text, and determining the voice information of the multiple positions based on the emotional information of the multiple positions.

[0263] Among them, the specific implementation methods of each of the above embodiments refer to Figure 3 The description in the embodiments will not be repeated here.

[0264] The disclosed embodiment provides a method for generating works, wherein a terminal login object conducts multiple rounds of dialogues with a character controlled by artificial intelligence, and works can be generated and displayed based on dialogue information from the multiple rounds of dialogues, wherein the works include a storyline generated by two dialogue characters and dialogue information from the multiple rounds of dialogues. This method lowers the threshold for creating works while allowing the terminal login object to deeply participate in the creation of the works, so that the generated works are more in line with the personalized needs of the terminal login object, so that the works have personalized characteristics, thereby improving the quality of the works.

[0265] Fig.10 is a block diagram of a device for generating a work according to an exemplary embodiment. Fig.10 , the device comprises:

[0266] The interface display unit 1001 is configured to execute a dialogue interface between a first character and a second character in response to an initialization operation on the work, wherein the first character is controlled by a first object, which is a terminal login object, and the second character is controlled by artificial intelligence;

[0267] The dialogue unit 1002 is configured to execute a dialogue operation in response to the first object on the dialogue interface, display multiple rounds of dialogue between the first character and the second character on the dialogue interface, and obtain dialogue information of the multiple rounds of dialogue;

[0268] The work display unit 1003 is configured to execute in response to a work generation operation, and is configured to execute and display a work generated based on dialogue information of multiple rounds of dialogue, wherein the work includes a storyline generated by the first character, the second character and the dialogue information of multiple rounds of dialogue.

[0269] In some embodiments, the interface display unit 1001 is further configured to execute:

[0270] Displaying a configuration interface, where the configuration interface is used to configure the attribute information of the second role;

[0271] The dialog display unit is configured to perform:

[0272] In response to the dialogue operation of the first object on the dialogue interface, the dialogue information sent by the first character and the reply information sent by the second character are displayed on the dialogue interface, and the reply information corresponds to the attribute information of the second character.

[0273] In some embodiments, the work display unit 1003 is configured to execute:

[0274] In response to the work generation operation, displaying a story outline generated based on the dialogue information of the multiple rounds of dialogue;

[0275] In response to a confirmation operation on the story outline, a work generated based on the dialogue information of the multiple rounds of dialogue and the story outline is displayed.

[0276] In some embodiments, the work display unit 1003 is further configured to execute:

[0277] In response to the modification operation on the story outline, displaying the modified story outline;

[0278] In response to a confirmation operation on the modified story outline, a work generated based on the dialogue information of the multiple rounds of dialogue and the modified story outline is displayed.

[0279] In some embodiments, the work display unit 1003 is further configured to execute:

[0280] In response to the work generation operation, an editing interface for displaying the dialogue information of the multiple rounds of dialogue;

[0281] In response to an editing operation on the dialogue information of the multiple rounds of dialogue, displaying the edited dialogue information;

[0282] In response to a confirmation operation on the edited dialogue information, a story outline generated based on the edited dialogue information is displayed.

[0283] In some embodiments, the work display unit 1003 is further configured to execute:

[0284] Display multiple story outline templates, each of which is associated with the dialogue information of multiple rounds of dialogue;

[0285] In response to a selection operation of any story outline template, a work generated based on the dialogue information of multiple rounds of dialogue and the selected story outline template is displayed.

[0286] In some embodiments, the work display unit 1003 is further configured to execute:

[0287] In response to a confirmation operation on the story outline, displaying a first draft of the work text generated based on the dialogue information of the multiple rounds of dialogue and the story outline;

[0288] In response to a confirmation operation on the draft work text, a work generated based on the draft work text is displayed.

[0289] In some embodiments, the work display unit 1003 is further configured to execute:

[0290] In response to a modification operation on the draft text of the work, the modified draft text of the work is displayed, the draft text of the work includes character dialogue text, narration information and environment description information generated from dialogue information of multiple rounds of dialogue, and the modification operation includes at least one of an operation of adjusting the order of the character dialogue text, an operation of adding, an operation of deleting, an operation of modifying the narration information and an operation of modifying the environment description information;

[0291] In response to a confirmation operation on the modified draft text of the work, a work generated based on the modified draft text of the work is displayed.

[0292] In some embodiments, the apparatus further comprises:

[0293] A first information display unit is configured to display modification prompt information of the first draft of the work text in response to a confirmation operation on the story outline, wherein the modification prompt information is used to prompt a method for modifying the first draft of the work text;

[0294] The work display unit 1003 is configured to execute:

[0295] In response to a triggering operation on the modification prompt information, a first draft of the work text modified based on the modification prompt information is displayed.

[0296] In some embodiments, the work display unit 1003 is configured to execute:

[0297] In response to a confirmation operation on the draft text of the work, a final text of the work generated based on the draft text of the work and music information are displayed, the music information including timbre information of each of the two characters, background music information, and at least one of sound effect information and voice information at multiple locations in the final text of the work, and the voice information including at least one of speech speed, intonation, tone, and voice emotion;

[0298] In response to the confirmation operation of the final work text and the music matching information, the work generated based on the final work text and the music matching information is displayed.

[0299] In some embodiments, the apparatus further comprises at least one of the following:

[0300] The second information display unit is configured to display the modified music information in response to the modification operation on the music information, and display the work generated based on the final work text and the modified music information in response to the confirmation operation on the final work text and the modified music information;

[0301] The playback unit is configured to execute a listening operation on any segment in the final draft of the work text and play the segment based on the soundtrack information corresponding to the segment.

[0302] The disclosed embodiment provides a device for generating a work, in which a terminal login object conducts multiple rounds of dialogues with a character controlled by artificial intelligence, and a work can be generated and displayed based on the dialogue information of the multiple rounds of dialogues. The work includes a storyline generated by two dialogue characters and the dialogue information of the multiple rounds of dialogues. In this way, the work can be generated through dialogue, without the need for the terminal login object to perform various operations, thereby improving the efficiency of human-computer interaction.

[0303] Fig.11 is a block diagram of a device for generating a work according to an exemplary embodiment. Fig.11 , the device comprises:

[0304] The information acquisition unit 1101 is configured to execute acquisition of dialogue information sent by a first role on a dialogue interface, where the dialogue interface is a dialogue interface between the first role and the second role, where the first role is controlled by a first object, which is a terminal login object, and the second role is controlled by artificial intelligence;

[0305] The dialogue generation unit 1102 is configured to generate multiple rounds of dialogue between the first character and the second character based on the dialogue information of the first character;

[0306] The work generating unit 1103 is configured to generate a work based on the dialogue information of multiple rounds of dialogues, wherein the work includes a storyline generated by the first character, the second character and the dialogue information of multiple rounds of dialogues.

[0307] In some embodiments, the work generation unit 1103 is configured to execute:

[0308] Generate a story outline of the work based on the dialogue information of multiple rounds of dialogue;

[0309] Generate works based on the dialogue information and story outline of multiple rounds of dialogue.

[0310] In some embodiments, the work generation unit 1103 is configured to execute:

[0311] Based on the dialogue information of the multi-round dialogue, multiple target plots and emotional information in the dialogue information of the multi-round dialogue are determined;

[0312] Generate a story outline based on the dialogue information of multiple rounds of dialogue, multiple target plots and emotional information.

[0313] In some embodiments, the work generation unit 1103 is configured to execute:

[0314] Generate a draft of the work text based on the dialogue information and story outline of multiple rounds of dialogue, the draft of the work text includes character dialogue text, narration information and environment description information generated from the dialogue information of multiple rounds of dialogue;

[0315] Generate works based on the first draft of the work text.

[0316] In some embodiments, the work generation unit 1103 is configured to execute:

[0317] Based on the dialogue information and story outline of the multiple rounds of dialogue, the dialogue information of the multiple rounds of dialogue is expanded, and based on the expanded dialogue information and story outline, a first draft of the work text is generated.

[0318] In some embodiments, the work generation unit 1103 is configured to execute:

[0319] Based on the first draft of the work text, generate the final draft of the work text and music information, the music information includes the timbre information of the two characters, the background music information, and at least one of the sound effect information and voice information of multiple positions in the final draft of the work text, and the voice information includes at least one of the speech speed, intonation, tone and voice emotion;

[0320] Generate the work based on the final draft of the work text and the music information.

[0321] In some embodiments, the work generation unit 1103 is configured to execute:

[0322] Generate the final draft of the work text based on the first draft of the work text;

[0323] Generate music information based on the final draft of the work text.

[0324] In some embodiments, the work generation unit 1103 is configured to perform at least one of the following:

[0325] Based on the final draft of the work text, determine the personality characteristics of the first character and the second character respectively, and based on the personality characteristics of the first character and the second character respectively, determine the timbre information of the first character and the second character respectively;

[0326] Based on the final draft of the work text, determine the respective dialogue scenes and environmental elements of multiple locations in the final draft of the work text, and based on the respective dialogue scenes and environmental elements of the multiple locations, determine the respective sound effect information of the multiple locations;

[0327] Based on the final draft of the work text, the emotional information of multiple positions in the final draft of the work text is determined, and based on the emotional information of the multiple positions, the voice information of the multiple positions is determined.

[0328] The disclosed embodiment provides a device for generating a work, in which a terminal login object conducts multiple rounds of dialogues with a character controlled by artificial intelligence, and a work can be generated and displayed based on the dialogue information of the multiple rounds of dialogues. The work includes a storyline generated by two dialogue characters and the dialogue information of the multiple rounds of dialogues. In this way, the work can be generated through dialogue, without the need for the terminal login object to perform various operations, thereby improving the efficiency of human-computer interaction.

[0329] Regarding the device in the above embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0330] In some embodiments, the electronic device is provided as a terminal. Fig.12 The structure block diagram of a terminal 1200 provided by an exemplary embodiment of the present disclosure is shown. The terminal 1200 may be: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer or a desktop computer. The terminal 1200 may also be called a user device, a portable terminal, a laptop terminal, a desktop terminal or other names.

[0331] Typically, the terminal 1200 includes: a processor 1201 and a memory 1202 .

[0332] The processor 1201 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 1201 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 1201 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 1201 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1201 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0333] The memory 1202 may include one or more computer-readable storage media, which may be non-transitory. The memory 1202 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1202 is used to store at least one program code, which is used to be executed by the processor 1201 to implement the work generation method provided in the method embodiment of the present disclosure.

[0334] In some embodiments, the terminal 1200 may further optionally include: a peripheral device interface 1203 and at least one peripheral device. The processor 1201, the memory 1202 and the peripheral device interface 1203 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 1203 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 1204, a display screen 1205, a camera assembly 1206, an audio circuit 1207 and a power supply 1208.

[0335] The peripheral device interface 1203 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 1201 and the memory 1202. In some embodiments, the processor 1201, the memory 1202, and the peripheral device interface 1203 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1201, the memory 1202, and the peripheral device interface 1203 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0336] The radio frequency circuit 1204 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 1204 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 1204 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 1204 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 1204 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: a metropolitan area network, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 1204 may also include circuits related to NFC (Near Field Communication), which is not limited in the present disclosure.

[0337] The display screen 1205 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 1205 is a touch display screen, the display screen 1205 also has the ability to collect touch signals on the surface or above the surface of the display screen 1205. The touch signal can be input to the processor 1201 as a control signal for processing. At this time, the display screen 1205 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 1205 can be one, and the front panel of the terminal 1200 is set; in other embodiments, the display screen 1205 can be at least two, which are respectively set on different surfaces of the terminal 1200 or are folded; in some other embodiments, the display screen 1205 can be a flexible display screen, which is set on the curved surface or folded surface of the terminal 1200. Even, the display screen 1205 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 1205 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0338] The camera assembly 1206 is used to capture images or videos. Optionally, the camera assembly 1206 includes a front camera and a rear camera. Typically, the front camera is arranged on the front panel of the terminal, and the rear camera is arranged on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize the panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 1206 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0339] The audio circuit 1207 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 1201 for processing, or input them into the radio frequency circuit 1204 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal 1200. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 1201 or the radio frequency circuit 1204 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 1207 may also include a headphone jack.

[0340] The power supply 1208 is used to power various components in the terminal 1200. The power supply 1208 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 1208 includes a rechargeable battery, the rechargeable battery can support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0341] Those skilled in the art will understand that Fig.12 The structure shown in the figure does not constitute a limitation on the terminal 1200, and the terminal 1200 may include more or fewer components than those shown in the figure, or combine certain components, or adopt a different component arrangement.

[0342] Fig.13 It is a structural diagram of a server provided according to an embodiment of the present application. The server 1300 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 1301 and one or more memories 1302, wherein the memory 1302 is used to store executable program codes, and the processor 1301 is configured to execute the above executable program codes to implement the work generation methods provided by the above-mentioned various method embodiments. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The server may also include other components for implementing device functions, which will not be described in detail here.

[0343] In an exemplary embodiment, a computer-readable storage medium is also provided, and when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the above-mentioned work generation method. Optionally, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0344] In an exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program. When the computer program is executed by a processor, the above-mentioned work generation method is implemented.

[0345] In some embodiments, the computer program product involved in the embodiments of the present disclosure may be deployed and executed on one electronic device, or on multiple electronic devices located at one location, or on multiple electronic devices distributed at multiple locations and interconnected by a communication network. Multiple electronic devices distributed at multiple locations and interconnected by a communication network may constitute a blockchain system.

[0346] Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and embodiments are to be regarded as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims. All of the above optional technical solutions can be combined in any way to form optional embodiments of the present application, which will not be described one by one here.

[0347] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for generating a work, characterized in that: The method comprises: In response to an initialization operation on the work, a dialogue interface between a first character and a second character is displayed, wherein the first character is controlled by a first object, which is a terminal login object, and the second character is controlled by artificial intelligence; In response to the dialogue operation of the first object on the dialogue interface, displaying multiple rounds of dialogue between the first character and the second character on the dialogue interface to obtain dialogue information of the multiple rounds of dialogue; In response to a work generation operation, a work generated based on the dialogue information of the multiple rounds of dialogue is displayed, the work including a storyline generated by the first character, the second character, and the dialogue information of the multiple rounds of dialogue.

2. The work generation method according to claim 1, characterized in that: The method further comprises: Displaying a configuration interface, wherein the configuration interface is used to configure attribute information of the second role; In response to the dialogue operation of the first object on the dialogue interface, displaying multiple rounds of dialogues between the first character and the second character on the dialogue interface includes: In response to the dialogue operation of the first object on the dialogue interface, the dialogue information sent by the first character and the reply information sent by the second character are displayed on the dialogue interface, and the reply information corresponds to the attribute information of the second character.

3. The work generation method according to claim 1, characterized in that: The step of displaying, in response to the work generation operation, the work generated based on the dialogue information of the multiple rounds of dialogues comprises: In response to the work generation operation, displaying a story outline generated based on the dialogue information of the multiple rounds of dialogue; In response to a confirmation operation on the story outline, a work generated based on the dialogue information of the multiple rounds of dialogue and the story outline is displayed.

4. The method for generating works according to claim 3, characterized in that: The method further comprises: In response to a modification operation on the story outline, displaying the modified story outline; In response to a confirmation operation on the modified story outline, a work generated based on the dialogue information of the multiple rounds of dialogue and the modified story outline is displayed.

5. The method for generating works according to claim 3, characterized in that: In response to the work generation operation, displaying a story outline generated based on the dialogue information of the multiple rounds of dialogues includes: In response to the work generation operation, displaying an editing interface for the dialogue information of the multiple rounds of dialogue; In response to an editing operation on the dialogue information of the multiple rounds of dialogues, displaying the edited dialogue information; In response to a confirmation operation on the edited dialogue information, a story outline generated based on the edited dialogue information is displayed.

6. The work generation method according to claim 3, characterized in that: The displaying of a story outline generated based on the dialogue information of the multiple rounds of dialogues includes: Displaying a plurality of story outline templates, wherein the plurality of story outline templates are all associated with the dialogue information of the plurality of dialogue rounds; In response to the confirmation operation of the story outline, displaying the dialogue information of the multiple rounds of dialogue and the work generated by the story outline includes: In response to a selection operation of any story outline template, a work generated based on the dialogue information of the multiple rounds of dialogue and the selected story outline template is displayed.

7. The method for generating works according to claim 3, characterized in that: In response to the confirmation operation of the story outline, displaying the dialogue information of the multiple rounds of dialogue and the work generated by the story outline includes: In response to a confirmation operation on the story outline, displaying a draft of a work text generated based on the dialogue information of the multiple rounds of dialogue and the story outline; In response to a confirmation operation on the first draft of the work text, a work generated based on the first draft of the work text is displayed.

8. The method for generating works according to claim 7, characterized in that: The method further comprises: In response to a modification operation on the draft text of the work, displaying a modified draft text of the work, the draft text of the work includes character dialogue text, narration information and environment description information generated from the dialogue information of the multiple rounds of dialogue, the modification operation includes at least one of an operation of adjusting the order of the character dialogue text, an operation of adding, an operation of deleting, an operation of modifying the narration information and an operation of modifying the environment description information; In response to a confirmation operation on the modified draft text of the work, a work generated based on the modified draft text of the work is displayed.

9. The work generation method according to claim 8, characterized in that: The method further comprises: In response to the confirmation operation of the story outline, displaying modification prompt information of the first draft of the work text, wherein the modification prompt information is used to prompt a method for modifying the first draft of the work text; The method of displaying the modified draft text of the work in response to the modification operation on the draft text of the work includes: In response to a triggering operation on the modification prompt information, a first draft of the work text modified based on the modification prompt information is displayed.

10. The work generation method according to claim 7, characterized in that: In response to the confirmation operation on the draft text of the work, displaying the work generated based on the draft text of the work includes: In response to a confirmation operation on the draft text of the work, a final text of the work and music information generated based on the draft text of the work are displayed, wherein the music information includes timbre information of each of the two characters, background music information, and at least one of sound effect information and voice information at multiple locations in the final text of the work, wherein the voice information includes at least one of speech speed, intonation, tone, and voice emotion; In response to a confirmation operation on the final draft of the work text and the music information, a work generated based on the final draft of the work text and the music information is displayed.

11. The work generation method according to claim 10, characterized in that: The method further comprises at least one of the following: In response to a modification operation on the music information, the modified music information is displayed; in response to a confirmation operation on the final work text and the modified music information, a work generated based on the final work text and the modified music information is displayed; In response to an audition operation on any segment in the final draft of the work text, the segment is played based on the soundtrack information corresponding to the segment.

12. A method for generating a work, characterized in that: The method comprises: Acquire a dialogue message sent by a first character on a dialogue interface, wherein the dialogue interface is a dialogue interface between the first character and a second character, the first character is controlled by a first object, the first object is a terminal login object, and the second character is controlled by artificial intelligence; Based on the dialogue information of the first character, generating multiple rounds of dialogues between the first character and the second character; A work is generated based on the dialogue information of the multiple rounds of dialogue, wherein the work includes a storyline generated by the first character, the second character, and the dialogue information of the multiple rounds of dialogue.

13. The work generation method according to claim 12, characterized in that: The generating of works based on the dialogue information of the multiple rounds of dialogues includes: Generating a story outline of the work based on the dialogue information of the multiple rounds of dialogue; The work is generated based on the dialogue information of the multiple rounds of dialogue and the story outline.

14. The work generation method according to claim 13, characterized in that: The generating of the story outline of the work based on the dialogue information of the multiple rounds of dialogues includes: Based on the dialogue information of the multiple rounds of dialogue, determining multiple target plots and emotion information in the dialogue information of the multiple rounds of dialogue; The story outline is generated based on the dialogue information of the multiple rounds of dialogue, the multiple target plots and the emotion information.

15. The method for generating works according to claim 13, characterized in that: The generating the work based on the dialogue information of the multiple rounds of dialogue and the story outline includes: Based on the dialogue information of the multiple rounds of dialogue and the story outline, a preliminary draft of the work text is generated, wherein the preliminary draft of the work text includes character dialogue text, narration information, and environment description information generated from the dialogue information of the multiple rounds of dialogue; The work is generated based on the first draft of the work text.

16. The work generation method according to claim 15, characterized in that: The generating a first draft of the work text based on the dialogue information of the multiple rounds of dialogue and the story outline includes: Based on the dialogue information of the multiple rounds of dialogue and the story outline, the dialogue information of the multiple rounds of dialogue is expanded, and based on the expanded dialogue information and the story outline, a first draft of the work text is generated.

17. The work generation method according to claim 15, characterized in that: Generating the work based on the first draft of the work text includes: Based on the draft text of the work, a final draft text of the work and music information are generated, wherein the music information includes timbre information of each of the two characters, background music information, and at least one of sound effect information and voice information at multiple locations in the final draft text of the work, wherein the voice information includes at least one of speech speed, intonation, tone, and voice emotion; The work is generated based on the final draft of the work text and the soundtrack information.

18. The method for generating a work according to claim 17, characterized in that: The generating of the final draft of the work text and the music information based on the first draft of the work text includes: Based on the first draft of the work text, generating the final draft of the work text; The music information is generated based on the final draft of the work text.

19. The work generation method according to claim 18, characterized in that: The generating the music information based on the final draft of the work text includes at least one of the following: Determining the personality characteristics of the first character and the second character based on the final draft of the work text, and determining the timbre information of the first character and the second character based on the personality characteristics of the first character and the second character; Based on the final draft of the work text, determining the dialogue scenes and environmental elements of each of the multiple positions in the final draft of the work text, and based on the dialogue scenes and environmental elements of each of the multiple positions, determining the sound effect information of each of the multiple positions; Based on the final draft of the work text, the emotional information of each of the multiple positions in the final draft of the work text is determined, and based on the emotional information of each of the multiple positions, the voice information of the multiple positions is determined.

20. A work generating device, characterized in that: The device comprises: An interface display unit is configured to execute, in response to an initialization operation on the work, a display of a dialogue interface between a first character and a second character, wherein the first character is controlled by a first object, which is a terminal login object, and the second character is controlled by artificial intelligence; a dialogue display unit, configured to execute a dialogue operation of the first object on the dialogue interface, display multiple rounds of dialogue between the first character and the second character on the dialogue interface, and obtain dialogue information of the multiple rounds of dialogue; A work display unit is configured to execute a work generation operation in response to the work generation operation, and is configured to execute the display of the work generated based on the dialogue information of the multiple rounds of dialogue, wherein the work includes a storyline generated by the first character, the second character and the dialogue information of the multiple rounds of dialogue.

21. A work generating device, characterized in that: The device comprises: an information acquisition unit, configured to acquire dialogue information sent by a first role on a dialogue interface, wherein the dialogue interface is a dialogue interface between the first role and a second role, the first role is controlled by a first object, the first object is a terminal login object, and the second role is controlled by artificial intelligence; a dialogue generating unit, configured to generate multiple rounds of dialogue between the first character and the second character based on the dialogue information of the first character; A work generation unit is configured to generate a work based on the dialogue information of the multiple rounds of dialogues, wherein the work includes a storyline generated by the first character, the second character and the dialogue information of the multiple rounds of dialogues.

22. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the work generation method as described in any one of claims 1 to 11 or the work generation method as described in any one of claims 12 to 19.

23. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the work generation method described in any one of claims 1 to 11 or the work generation method described in any one of claims 12 to 19.

24. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method for generating a work as claimed in any one of claims 1 to 11 or the method for generating a work as claimed in any one of claims 12 to 19 is implemented.

Images