Content generation method and apparatus, and electronic device, storage medium and program product

Abstract

The present disclosure relates to the technical field of computers, and relates to a content generation method and apparatus, and an electronic device, a storage medium and a program product. The content generation method of the present disclosure comprises: displaying, in an interactive interface between a user and an agent, a generation instruction input by the user, wherein the generation instruction includes descriptive information of target content; displaying one or more pieces of creative information in the interactive interface on the basis of the generation instruction, wherein the one or more pieces of creative information are generated on the basis of semantic understanding of the descriptive information of the target content; in response to a selection operation of the user in respect of target creative information among the one or more pieces of creative information, calling one or more intelligent tools on the basis of the target creative information and the type of the target content, so as to generate the target content; and displaying the target content in the interactive interface.

Description

Content generation method and device, electronic device, storage medium and program product

[0001] Cross-reference to Related Applications

[0002] This application is based on and claims priority to the application with the Chinese application number 202411388358.6 and the filing date of September 30, 2024, the disclosure of which is hereby incorporated by reference in its entirety into this application. TECHNICAL FIELD

[0003] The present disclosure relates to the technical field of computer, and particularly relates to a content generation method and device, electronic device, storage medium and program product. BACKGROUND

[0004] With the development of artificial intelligence (AI) technology, users can already generate images, music and even videos and other content by using some applications. These applications can receive instructions input by the user, and generate content corresponding to the instructions based on generative artificial intelligence technology. SUMMARY

[0005] This summary is provided to introduce a selection of concepts, which are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used in limiting the scope of the claimed subject matter.

[0006] According to some embodiments of the present disclosure, a content generation method is provided, including: displaying a generation instruction input by a user in an interaction interface between the user and an agent, wherein the generation instruction includes description information of target content; displaying one or more pieces of creative information in the interaction interface according to the generation instruction, wherein the one or more pieces of creative information are generated according to semantic understanding of the description information of the target content; in response to a selection operation of the user on target creative information in the one or more pieces of creative information, generating the target content according to the target creative information and a type of the target content by invoking one or more intelligent tools; and displaying the target content in the interaction interface.

[0007] According to some embodiments of the present disclosure, a content generation apparatus is provided, comprising: a first display module configured to display a generation instruction input by a user in an interaction interface between the user and an agent, wherein the generation instruction comprises description information of target content; a second display module configured to display one or more pieces of creative information in the interaction interface according to the generation instruction, wherein the one or more pieces of creative information are generated according to semantic understanding of the description information of the target content; a generation module configured to, in response to a selection operation of the user on target creative information in the one or more pieces of creative information, generate the target content according to the target creative information and a type of the target content by invoking one or more intelligent tools; and a third display module configured to display the target content in the interaction interface.

[0008] According to some embodiments of the present disclosure, an electronic device is provided, comprising: a processor; and a memory coupled to the processor for storing instructions, which, when executed by the processor, cause the processor to perform the content generation method of any of the embodiments of the present disclosure.

[0009] According to some embodiments of the present disclosure, a computer readable storage medium is provided, having stored thereon a computer program, wherein the program, when executed by a processor, implements the content generation method of any of the embodiments of the present disclosure.

[0010] According to some embodiments of the present disclosure, a computer program product is provided, comprising instructions which, when executed by a processor, cause the processor to perform the content generation method of any of the embodiments of the present disclosure.

[0011] Other features and advantages of the present disclosure will be apparent from the following detailed description of exemplary embodiments of the present disclosure, taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0012] Preferred embodiments of the present disclosure are described herein below with reference to the accompanying drawings. The accompanying drawings, which are included to provide a further understanding based on the present disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the present disclosure and together with the detailed description serve to explain the present disclosure. It is to be understood that the drawings are only schematic and are used for purposes of the description of the embodiments only, and are not intended to limit the present disclosure. In the drawings:

[0013] FIG. 1 shows a flowchart of a content generation method according to some embodiments of the present disclosure;

[0014] FIG. 2 shows a schematic diagram of an interaction interface according to some embodiments of the present disclosure;

[0015] FIG. 3 shows a schematic diagram of an interaction interface according to some other embodiments of the present disclosure;

[0016] FIG. 4 shows a schematic diagram of an interaction interface according to some other embodiments of the present disclosure;

[0017] FIG. 5 shows a structural schematic diagram of a content generation apparatus according to some embodiments of the present disclosure;

[0018] FIG. 6 shows a structural schematic diagram of an electronic device according to some embodiments of the present disclosure;

[0019] FIG. 7 shows a structural schematic diagram of a computer system according to some embodiments of the present disclosure.

[0020] It should be understood that the dimensions of the various portions shown in the drawings are not necessarily to scale. Identical or similar reference numerals are used consistently throughout the several drawings to designate the same or similar components. Thus, where a component is described as being suitable for use in one drawing figure, it can also be suitable for use in another drawing figure. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only some of the embodiments of the present disclosure, but not all the embodiments. The description of the embodiments below is actually only illustrative, and should not be construed as any limitation on the present disclosure and its application or use. It should be understood that the present disclosure can be implemented in various forms, and should not be construed as being limited to the embodiments set forth herein.

[0022] It should be understood that the various steps recited in the method embodiments of the present disclosure can be executed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the execution of the steps shown. The scope of the present disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement of the components and steps set forth in these embodiments, numerical expressions, and numerical values should be interpreted as merely exemplary, and not limiting to the scope of the present disclosure.

[0023] The term "comprise" and variations thereof used in the present disclosure means an open term that includes at least the recited elements / features, but does not exclude other elements / features, i.e., "including, but not limited to". In addition, the term "include" and variations thereof used in the present disclosure means an open term that includes at least the recited elements / features, but does not exclude other elements / features, i.e., "including, but not limited to". Therefore, include and comprise are synonymous. The term "based on" means "at least partially based on".

[0024] Reference throughout this specification to "one embodiment", "an embodiment", or "embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrase "in one embodiment" or "in some embodiments" in various places in the specification are not necessarily all referring to the same embodiment, although it can. Furthermore, the term "a or an" or "one or more" followed by a plurlality of a feature is intended to mean that a feature, structure, or characteristic can be included one or more times in at least one embodiment or some embodiments of the application.

[0025] It should be noted that the terms "first", "second", and so on, mentioned in the present disclosure are only used to distinguish different apparatuses, modules or units, and are not intended to limit the order or interdependence of the functions performed by these apparatuses, modules or units. Unless otherwise specified, the terms "first", "second", and so on are not intended to imply a given order or any other manner of given order in time, space, ranking, or any other manner.

[0026] It should be noted that the modification of "one" or "multiple" mentioned in the present disclosure is illustrative rather than limiting, and those skilled in the art should understand that unless the context clearly indicates otherwise, it should be understood as "one or more".

[0027] The names of the messages or information exchanged between the plurality of apparatuses in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0028] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings, but the present disclosure is not limited to these specific embodiments. These specific embodiments below can be combined with each other, and the same or similar concepts or processes can not be described in some embodiments. In addition, in one or more embodiments, specific features, structures, or characteristics can be combined by any suitable manner from the present disclosure which will be clear to those skilled in the art.

[0029] At present, the application based on generative artificial intelligence technology can use a generative model to generate corresponding content according to the instructions of a user, and generally requires the user to input explicit instructions to generate relatively accurate content for the user. For example, a user wants to generate an image, and needs to describe what is specifically included in the image picture, so as to obtain an image that is more in line with the expectation. If the user only inputs vague and not very explicit instructions, for example, "generate a Children's Day poster", then the finally generated image is likely to not meet the user's needs, have low quality, or even have errors, etc.

[0030] In order to generate more accurate generative content for users and facilitate the use of users, the present disclosure proposes a content generation method, which is described below in conjunction with FIGS. 1-4.

[0031] The content generation method of the embodiments of the present disclosure can be executed by a content generation device, which can be implemented in the form of hardware and / or software. For example, the content generation device is an agent, a bot, an interactive application, etc. A user can have a human-computer dialogue with the content generation device. For example, the user can provide a command and / or request to the content generation device using spoken natural language input (i.e., utterance), which can be converted into text and then processed in some cases, and / or by providing text (e.g., typed) natural language input.

[0032] The content generation device can have a generation function, i.e., based on generative artificial intelligence technology. For example, the content generation device can correspond to a generative model, or can cooperate with other intelligent tools having a generation function to provide a generation function for users in an interactive process, which is not limited in the present disclosure.

[0033] FIG. 1 is a flowchart of some embodiments of the content generation method of the present disclosure. As shown in FIG. 1, the method of the embodiment includes steps S102-S108.

[0034] In step S102, a user input generation instruction is displayed in an interactive interface between the user and the agent, wherein the generation instruction includes description information of the target content.

[0035] The content generation device can include one or more agents (which can be implemented by software or a combination of software and hardware), and can also include other intelligent tools other than agents, such as plug-ins, function modules, etc. The agent can belong to a kind of intelligent tools. The user can interact with the agent, and the user input generation instruction is displayed in the interactive interface. The generation instruction can only include simple description information of the target content, such as “generate a children’s day poster”.

[0036] In step S104, one or more creative information is displayed in the interactive interface according to the generation instruction.

[0037] The one or more creative information is generated according to the semantic understanding of the description information of the target content. Through natural language understanding and processing of the description information of the target content, one or more creative information can be automatically generated, which is described in natural language and is an extension and supplement to the description information of the target content, including feature description information of the target content, which can describe the features of the target content in more detail and accurately. Based on the one or more creative information, content with higher quality can be generated relative to the user input description information of the target content.

[0038] In step S106, in response to the selection operation of the user on the target creative information in the one or more pieces of creative information, one or more intelligent tools are invoked according to the target creative information and the type of the target content to generate the target content.

[0039] The type of the target content can include a media type of the target content, for example, text, image, audio, video, etc., without being limited to the examples. Different types can correspond to different intelligent tools. The intelligent tools can be intelligent agents, plug-ins, etc., which can implement specific functions. For example, the intelligent tools can be intelligent agents for generating music, the intelligent tools can be plug-ins for adding special effects on images, etc. The one or more intelligent tools include generative tools, which can be configured with corresponding generative models. The target content can need multiple intelligent tools to cooperate to generate. According to the target creative information and the type of the target content, the one or more intelligent tools required can be determined, and then the one or more intelligent tools are invoked to generate the target content.

[0040] The intelligent agents cooperate with the one or more intelligent tools to finally generate the target content. Since the target creative information can more accurately describe the target content, the finally generated target content is more accurate and of higher quality.

[0041] In step S108, the target content is displayed in the interactive interface.

[0042] The target content generated by invoking the one or more intelligent tools is returned to the intelligent agents, and the target content is displayed in the interactive interface.

[0043] The method of the above embodiment, the user inputs a generation instruction in the process of interacting with the intelligent agent, the generation instruction includes description information of the target content, one or more pieces of creative information are automatically generated through semantic understanding of the description information of the target content, in response to the user's selection of the target creative information in the one or more pieces of creative information, one or more intelligent tools are invoked according to the target creative information and the type of the target content to generate the target content. The method of the above embodiment, the entire generation process of the target content is completed through cooperation of the intelligent agent and the one or more intelligent tools, and is divided into two stages of creative generation and target content generation. First, the generation instruction is subjected to natural language understanding and processing, simulating human thinking when creating, so as to obtain more detailed and accurate creative information for the description of the target content. After the user selects the target creative information, one or more intelligent tools are invoked to generate the target content, which is more accurate, more consistent with the user's intention, and of higher quality, compared with directly generating the target content by using a generative model according to the user's input generation instruction. And by automatically providing one or more pieces of creative information for the user, the user does not need to input detailed creative information, which can improve the generation efficiency while improving the accuracy of the generation of the target content.

[0044] The following describes how to display one or more pieces of creative information in the interactive interface according to the generation instruction in combination with some embodiments.

[0045] In some embodiments, the agent corresponding machine learning model is called to generate and display one or more pieces of creative information according to the generation instruction.

[0046] The agent corresponding machine learning model is, for example, a large language model (LLM), a generative model, etc., and is not limited to the examples. After the user inputs the generation instruction through the interaction with the agent, the agent corresponding machine learning model can be directly used to understand the generation instruction and generate one or more pieces of creative information.

[0047] Other intelligent tools can also be used to generate one or more pieces of creative information. In some embodiments, the generation instruction is semantically understood to determine one or more intelligent tools; a first intelligent tool of the one or more intelligent tools is called to generate one or more pieces of creative information according to the generation instruction; one or more pieces of creative information returned by the first intelligent tool is received; and the one or more pieces of creative information is displayed in the interactive interface.

[0048] The agent corresponding machine learning model can be first called to semantically understand the generation instruction and determine one or more intelligent tools required for generating the target content. For example, the generation instruction is semantically understood to determine the type of the target content, and one or more intelligent tools are determined according to the type of the target content. A first intelligent tool of the one or more intelligent tools has the function of generating creative information, and the agent can send the generation instruction or the description information of the target content to the first intelligent tool, so that the first intelligent tool generates one or more pieces of creative information and returns the one or more pieces of creative information to the agent. The one or more intelligent tools can be partially or entirely configured with the function of generating creative information. In the case where multiple intelligent tools need to be called and the multiple intelligent tools are all configured with the function of generating creative information, the first called intelligent tool is taken as the first intelligent tool according to the calling order of the intelligent tools required for generating the target content.

[0049] In some embodiments, the generation instruction is semantically understood to determine whether to call a second intelligent tool, wherein the second intelligent tool is different from the one or more intelligent tools; in response to determining to call the second intelligent tool, the second intelligent tool is called to generate one or more pieces of creative information according to the generation instruction; one or more pieces of creative information returned by the second intelligent tool is received; and the one or more pieces of creative information is displayed in the interactive interface.

[0050] The intelligent agent can first call the machine learning model corresponding to the intelligent agent to perform semantic understanding on the generation instruction and determine whether to call a second intelligent tool to generate one or more pieces of creative information. The second intelligent tool can be a tool specially used for generating creative information. If the generation instruction itself is detailed enough in describing the characteristics of the target content, one or more pieces of creative information can not be generated, and the target content can be directly generated according to the generation instruction. If the second intelligent tool needs to be called, the intelligent agent can send the generation instruction or the description information of the target content to the second intelligent tool, and the second intelligent tool can generate one or more pieces of creative information and return the one or more pieces of creative information to the intelligent agent.

[0051] If the intelligent agent has the function of generating creative information, the intelligent agent can directly generate the creative information. If the intelligent agent does not have the function of generating creative information, the intelligent agent can interact with other intelligent tools having the function of generating creative information to obtain one or more pieces of creative information and display the one or more pieces of creative information to the user.

[0052] Whether the intelligent agent generates the creative information or other intelligent tools generate the creative information, the specific method is similar, which will be described below in combination with some embodiments.

[0053] In some embodiments, the description information of the target content is subjected to semantic understanding to determine theme information and a type of the target content; one or more pieces of creative information associated with the theme information and matching the type are generated according to the theme information and the type of the target content, different creative information includes different characteristic description information of the target content; and the one or more pieces of creative information are displayed in an interactive interface.

[0054] For example, the description information of the target content is “a poster for Children’s Day”, and through semantic understanding, it can be determined that the theme information of the target content is “Children’s Day” and the type is an image. Then, one or more pieces of creative information associated with the theme information and matching the type can be generated by using a machine learning model (a large language model, a generative model, etc.). For example, one piece of creative information is “The background is a starry sky full of dreamy colors, with stars twinkling and a meteor flying across the sky. Under the starry sky is a large amusement park illuminated by colorful lights. The outlines of amusement facilities such as roller coasters and Ferris wheels are clearly visible, and colorful smoke is diffused around……” The one or more pieces of creative information can also include keywords related to the type of the target content. According to the keywords, the type of the target content can be determined.

[0055] Through understanding of the theme and the type of the target content, the accuracy of the generated creative information can be improved, and the generated creative information can be more consistent with the user’s intention.

[0056] In some embodiments, in response to the target content including an image, the one or more pieces of creative information include description information of a picture feature of the image; and / or in response to the target content including music, the one or more pieces of creative information include description information of at least one feature of a style, a keyword, and lyrics of the music.

[0057] For target content including an image, one or more pieces of creative information can be used to more clearly and specifically describe various features related to the image, such as objects, characters, colors, light, background, etc. included in the picture of the image. For target content including music, one or more pieces of creative information can be used to more clearly and specifically describe the style of the music (which can include melody, rhythm, musical instruments, etc.).

[0058] The historical interaction information and historical generated content can also be referred to when generating the creative information. In some embodiments, among the historical interaction information before the generation instruction, it is determined whether there is historical generated content related to the generation instruction; in response to there being historical generated content related to the generation instruction, one or more pieces of creative information are displayed in the interaction interface according to the generation instruction and the historical generated content.

[0059] The historical interaction information of a preset number before the generation instruction can be understood to determine whether there is historical generated content related to the generation instruction. Referring to the context of the user's interaction with the intelligent agent can more accurately understand the user's intention, thereby generating more accurate creative information. For example, after generating a "Children's Day poster", the user sends a generation instruction "Can you help me create some music suitable for playing at a Children's Day party?". By matching the generation instruction with the historical interaction information, it is determined that there is historical generated content related to the generation instruction, i.e., the "Children's Day poster", it can be understood that the user is likely to want the music to match the poster. Then, according to the generation instruction and the historical generated content, generating one or more pieces of creative information will be more accurate.

[0060] In the case where the first intelligent tool or the second intelligent tool needs to be called to generate one or more pieces of creative information, the intelligent agent can send the historical interaction information or the historical generated content to the first intelligent tool or the second intelligent tool.

[0061] In some embodiments, determining whether there is historical generated content related to the generation instruction includes: performing semantic understanding on description information of the target content to determine theme information of the target content; determining theme information of one or more pieces of historical generated content in the historical interaction information; and determining whether there is historical generated content related to the generation instruction according to the theme information of the one or more pieces of historical generated content and the theme information of the target content.

[0062] The theme information of the historical generation content can be determined according to the historical generation content, the creative information corresponding to the historical generation content, or the generation instruction corresponding to the historical generation content. For example, the theme of the historical generation content and the theme of the target content are both related to Children's Day, and it can be determined that there is historical generation content related to the current generation instruction.

[0063] By understanding and matching the theme information of the target content and the historical generation content, it can be more accurately determined whether there is historical generation content related to the generation instruction.

[0064] In some embodiments, according to the generation instruction and the historical generation content, displaying one or more pieces of creative information in the interactive interface includes: generating one or more pieces of creative information according to the theme information and the type of the target content, and the creative information of the historical generation content, wherein the one or more pieces of creative information are associated with the theme information of the target content and the creative information of the historical generation content, and match the type; displaying the one or more pieces of creative information in the interactive interface.

[0065] For example, the creative information of the historical generation content can be semantically understood, and key information can be extracted for generating one or more pieces of creative information. For example, for the creative information of generating a "Children's Day poster", key information such as "amusement park", "roller coaster", "ferris wheel" can be extracted for generating one or more pieces of creative information. The one or more pieces of creative information generated are associated with the creative information of the historical generation content, and conform to the theme and type of the target content. For example, one piece of creative information generated is "Let's create a song about the amusement park, roller coaster, and ferris wheel, and it is lively and cheerful, with light and lively drum beats and lively melodies."

[0066] The method of the above embodiments generates one or more pieces of creative information that are associated with the creative information of the historical generation content and conform to the theme and type of the target content, thereby improving the accuracy of the one or more pieces of creative information and more in line with the user's intention, thereby improving the accuracy and quality of the subsequent generated target content.

[0067] The method of generating one or more pieces of creative information in each of the above embodiments can be executed on the side of an intelligent agent or on the side of other intelligent tools.

[0068] When displaying one or more pieces of creative information, guiding information can be displayed to reply to the user's generation instruction, and more in line with the expression logic of natural language. For example, the guiding information is "OK, there are two poster ideas for you to choose from", which is not limited to the example.

[0069] After generating and displaying the one or more pieces of creative information, the user can select a target piece of creative information therefrom. In some embodiments, the selection operation on the target piece of creative information includes a selection operation on an item of the target piece of creative information, a triggering operation on a control corresponding to the target piece of creative information, or inputting indication information representing selection of the target piece of creative information.

[0070] The user can select the target piece of creative information in various ways, not limited to the above-described examples.

[0071] The following describes how to invoke one or more intelligent tools to generate the target content according to the type of the target piece of creative information and the target content, in combination with some embodiments.

[0072] In some embodiments, one or more intelligent tools and an execution order of the one or more intelligent tools are determined according to the target piece of creative information, the type of the target content, and a function of each intelligent tool in the plurality of intelligent tools; and the one or more intelligent tools are invoked to generate the target content according to the execution order of the one or more intelligent tools and the target piece of creative information.

[0073] Through analysis of the target piece of creative information and the type of the target content, the execution order of the one or more intelligent tools to be invoked can be determined. For example, to generate an audio picture book, an image generation tool and an audio generation tool can be invoked respectively to generate an image and audio, and a tool for integrating the image and the audio can be invoked.

[0074] In the case where the plurality of intelligent tools cooperate to generate the target content, each intelligent tool generates a part of the target content generated by the intelligent tool according to the execution order thereof. If the current intelligent tool needs to use the generation result of the previous intelligent tool, the previous intelligent tool sends the generation result to the current intelligent tool.

[0075] In the case where the plurality of intelligent tools cooperate to generate the target content, the execution order of each intelligent tool is first determined through analysis of the target piece of creative information and the type of the target content, and then each intelligent tool is invoked according to the execution order, which can improve the accuracy of the generated target content.

[0076] In some embodiments, invoking the one or more intelligent tools to generate the target content according to the execution order of the one or more intelligent tools and the target piece of creative information includes: generating prompt information of the one or more intelligent tools according to the execution order of the one or more intelligent tools and the target piece of creative information; and inputting the prompt information into the one or more intelligent tools, so that one or more second machine learning models corresponding to the one or more intelligent tools generate the target content according to the prompt information.

[0077] The prompt information of each intelligent tool can be generated according to the execution sequence of the one or more intelligent tools and the target creative information, and the prompt information of each intelligent tool is input into the machine learning model corresponding to each intelligent tool, so that the machine learning model corresponding to each intelligent tool generates the part of the target content generated by each intelligent tool according to the prompt information.

[0078] Further, in some embodiments, the prompt information of each intelligent tool is input into each intelligent tool, and the machine learning model corresponding to each intelligent tool generates the part of the target content generated by each intelligent tool according to the prompt information of each intelligent tool in the execution sequence of each intelligent tool.

[0079] Each intelligent tool generates the part of the target content generated by each intelligent tool according to the execution sequence and the corresponding prompt information, which can improve the accuracy of the target content generation.

[0080] In some embodiments, the one or more intelligent tools are a plurality of intelligent tools, and generating the prompt information of the one or more intelligent tools according to the execution sequence of the one or more intelligent tools and the target creative information includes: dividing the target creative information into creative information corresponding to each intelligent tool in the plurality of intelligent tools according to the functions of the plurality of intelligent tools and the execution sequence of the one or more intelligent tools; and generating the prompt information of each intelligent tool according to the creative information corresponding to each intelligent tool.

[0081] In some cases, the target creative information can include creative information for generating different parts of the target content. For example, the target content is a video, the target creative information includes description information of a picture in the video, and also includes description information of a music, the description information of the picture and the description information of the music can be divided and the prompt information of an image generation tool and the description information of a music generation tool can be generated respectively. If each intelligent tool needs to refer to all the target creative information, the division can not be performed, and needs to be performed according to the target creative information.

[0082] Through the division of the target creative information, the prompt information of each intelligent tool can be more accurately generated, so that each intelligent tool can more accurately generate the part of the target content generated by each intelligent tool.

[0083] The user can modify the target creative information after selecting the target creative information to obtain more accurate target creative information. In some embodiments, before the one or more intelligent tools are invoked to generate the target content according to the target creative information and the type of the target content, the target creative information is updated in response to a modification operation of the user on the target creative information.

[0084] For example, in response to a user triggering an operation on a modification control of the target creative information, or in response to the user triggering a modification of the target creative information through a specific operation on the target creative information, the target creative information can be displayed in an interactive interface between the user and the intelligent entity, a new page, a floating layer, a window, a panel, or any other form of interface, and the user's input, deletion, modification, and other operations can be received to update the target creative information, and the target content can be subsequently generated based on the updated target creative information.

[0085] In response to a user's modification operation on any of the one or more pieces of creative information, the updated creative information can be displayed, and in response to the user's selection operation on the target creative information from the one or more pieces of creative information, one or more intelligent tools can be invoked based on the type of the target creative information and the target content to generate the target content.

[0086] The user can first modify any creative information and then select the modified creative information as the target creative information.

[0087] The generated one or more pieces of creative information can provide inspiration to the user, and by providing the user with a modification function, the user can modify the one or more pieces of creative information to better meet their own intentions, thereby making the generated target content more accurate and of higher quality.

[0088] The user can also modify the generated target content. In some embodiments, in response to a user's modification operation on the target content, the target content is updated.

[0089] For example, in response to a user input modification instruction, the target content is modified. The modification instruction can include a feature description of the part that needs to be modified. For example, the user input modification instruction is "change the roller coaster to a carousel", and the children's festival poster can be regenerated according to the modification instruction to change the roller coaster to a carousel.

[0090] The user can provide feedback on the generated target content. In some embodiments, a feedback control corresponding to the target content is displayed in the interactive interface, and in response to a user triggering an operation on the feedback control, feedback information corresponding to the feedback control is obtained, wherein the feedback control includes at least one of a positive feedback control and a negative feedback control.

[0091] For example, the feedback control includes "like" and "dislike" controls. Based on the user's feedback information, the machine learning model used to generate the target content can be adjusted to generate more accurate target content in the future.

[0092] If the user is not satisfied with the generated target content, the user can trigger the re-generation function. In some embodiments, a re-generation control corresponding to the target content is displayed in the interactive interface, and in response to a triggering operation of the user on the re-generation control, one or more intelligent tools are invoked according to the target creative information and the type of the target content to re-generate and display the target content.

[0093] The user can trigger the re-generation control to obtain satisfactory target content.

[0094] Some embodiments of the interactive interface corresponding to the content generation method of the present disclosure are described below in conjunction with FIGS. 2-4.

[0095] As shown in FIG. 2, the interactive interface of the user and the intelligent agent A is shown. The user inputs a generation instruction 201 “Help me generate a poster for Children’s Day”, and the intelligent agent A replies with two pieces of creative information 202. The user can select one of the two pieces of creative information as the target creative information. For example, as shown in FIG. 2, the user inputs the indication information 203 “The second one is good” indicating the selection of the target creative information. The user can also select the target creative information by clicking the item of the target creative information or the like, or a control corresponding to each piece of creative information can be displayed, and the user can select the target creative information by triggering the control corresponding to the target creative information. In response to the user selecting the second piece of creative information, the generation instruction information 204 of the target content can be displayed. The generated target content can also be directly displayed.

[0096] As shown in FIG. 3, multiple images (target content) 301 can be generated and displayed, and the user can select a satisfactory image for saving, downloading, etc. The user can continue to input a generation instruction 302 “Can you help me create music suitable for a Children’s Day party?”. Since there is already generated historical generation content related to the generation instruction 302, i.e., the already generated images 301, the creative information 303 generated according to the generation instruction 302 is associated with the creative information of the already generated images and conforms to the theme and music type of the Children’s Day party. If there is only one piece of creative information, the user’s selection or confirmation operation can not be required, and the target content can be directly generated.

[0097] As shown in FIG. 4, multiple pieces of generated music 401, i.e., multiple pieces of generated target content, can be displayed. The user can download, save, forward, etc. one or more pieces of music 401, without being limited to the examples shown.

[0098] The present disclosure also provides a content generation device, which is described below in conjunction with FIG. 5.

[0099] FIG. 5 is a structural diagram of some embodiments of the content generation apparatus of the present disclosure. As shown in FIG. 5, the content generation apparatus 50 of the embodiment includes a first display module 510, a second display module 520, a generation module 530, and a third display module 540.

[0100] The first display module 510 is configured to display a generation instruction input by a user in an interaction interface between the user and an agent, wherein the generation instruction includes description information of target content.

[0101] The second display module 520 is configured to display one or more pieces of creative information in the interaction interface according to the generation instruction, wherein the one or more pieces of creative information are generated according to semantic understanding of the description information of the target content.

[0102] The generation module 530 is configured to, in response to a selection operation of a target piece of creative information in the one or more pieces of creative information by the user, call one or more intelligent tools according to the target piece of creative information and a type of the target content, and generate the target content.

[0103] The third display module 540 is configured to display the target content in the interaction interface.

[0104] In some embodiments, the second display module 520 is configured to perform semantic understanding on the description information of the target content, determine theme information and a type of the target content, generate one or more pieces of creative information associated with the theme information and matching the type according to the theme information and the type of the target content, wherein different pieces of creative information include different feature description information of the target content, and display the one or more pieces of creative information in the interaction interface.

[0105] In some embodiments, the second display module 520 is configured to determine, in historical interaction information before the generation instruction, whether there is historical generated content related to the generation instruction, and in response to the existence of the historical generated content related to the generation instruction, display one or more pieces of creative information in the interaction interface according to the generation instruction and the historical generated content.

[0106] In some embodiments, the second display module 520 is configured to perform semantic understanding on the description information of the target content, determine theme information of the target content, determine theme information of one or more pieces of historical generated content in the historical interaction information, and determine whether there is historical generated content related to the generation instruction according to the theme information of the one or more pieces of historical generated content and the theme information of the target content.

[0107] In some embodiments, the second display module 520 is configured to generate one or more pieces of creative information according to the theme information and the type of the target content and the creative information of the historically generated content, where the one or more pieces of creative information are associated with the theme information of the target content and the creative information of the historically generated content and match the type; and display the one or more pieces of creative information in the interactive interface.

[0108] In some embodiments, the second display module 520 is configured to perform semantic understanding on the generation instruction, determine one or more intelligent tools; invoke a first intelligent tool of the one or more intelligent tools to generate one or more pieces of creative information according to the generation instruction; receive the one or more pieces of creative information returned by the first intelligent tool; and display the one or more pieces of creative information in the interactive interface.

[0109] In some embodiments, the second display module 520 is configured to perform semantic understanding on the generation instruction, determine whether to invoke a second intelligent tool, where the second intelligent tool is different from the one or more intelligent tools; in response to determining to invoke the second intelligent tool, invoke the second intelligent tool to generate one or more pieces of creative information according to the generation instruction; receive the one or more pieces of creative information returned by the second intelligent tool; and display the one or more pieces of creative information in the interactive interface.

[0110] In some embodiments, the generation module 530 is configured to determine one or more intelligent tools and an execution order of the one or more intelligent tools according to the target creative information, the type of the target content, and a function of each intelligent tool of the plurality of intelligent tools; and invoke the one or more intelligent tools to generate the target content according to the execution order of the one or more intelligent tools and the target creative information.

[0111] In some embodiments, the one or more intelligent tools are a plurality of intelligent tools, and the generation module 530 is configured to divide the target creative information into creative information corresponding to each intelligent tool of the plurality of intelligent tools according to the function of the plurality of intelligent tools and the execution order of the one or more intelligent tools; and generate prompt information of each intelligent tool according to the creative information corresponding to each intelligent tool.

[0112] In some embodiments, the generation module 530 is configured to input the prompt information of each intelligent tool into each intelligent tool, and generate, by a machine learning model corresponding to each intelligent tool, a part of the target content generated by each intelligent tool according to the prompt information of each intelligent tool and in the execution order of each intelligent tool.

[0113] In some embodiments, the content generation apparatus 50 further comprises a first modification module 550 configured to, in response to a user's modification operation on the target creative information, update the target creative information before generating the target content according to the target creative information and the type of the target content by invoking one or more intelligent tools; and / or a second modification module 560 configured to, in response to a user's modification operation on the target content, update the target content.

[0114] In some embodiments, the third display module 540 is further configured to display, in the interactive interface, a feedback control corresponding to the target content, and in response to a user's triggering operation on the feedback control, acquire feedback information corresponding to the feedback control, wherein the feedback control comprises at least one of a positive feedback control and a negative feedback control; and / or display, in the interactive interface, a re-generation control corresponding to the target content, and in response to a user's triggering operation on the re-generation control, re-generate and display the target content according to the target creative information and the type of the target content by invoking one or more intelligent tools.

[0115] In some embodiments, in response to the target content comprising an image, the one or more pieces of creative information comprise description information of a picture feature of the image; and / or in response to the target content comprising music, the one or more pieces of creative information comprise description information of at least one feature of a style, a keyword, and lyrics of the music.

[0116] In some embodiments, the selection operation on the target creative information in the one or more pieces of creative information comprises a selection operation on an item of the target creative information, a triggering operation on a control corresponding to the target creative information, or input of indication information indicating selection of the target creative information.

[0117] It should be noted that each unit (module) described above is only a logical division according to the specific function it implements, and is not intended to limit the specific implementation manner, for example, it can be implemented in software, hardware or a combination of software and hardware. In actual implementation, each unit can be implemented as an independent physical entity, or can be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.). In addition, each unit is indicated by a dashed line in the drawings, indicating that these units can not actually exist, and the operations / functions they implement can be implemented by the processing circuit itself.

[0118] Further, although not shown, the device can also include a memory that can store various information generated by the device, the various units included in the device in operation, programs and data for operation, data to be transmitted by the communication unit, and the like. The memory can be a volatile memory and / or a non-volatile memory. For example, the memory can include, but is not limited to, a random access memory (RAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), a read only memory (ROM), a flash memory. Of course, the memory can also be located outside the device. Alternatively, although not shown, the device can also include a communication unit that can be used to communicate with other devices. In one example, the communication unit can be implemented in an appropriate manner known in the art, for example, including a communication component such as an antenna array and / or a radio frequency link, various types of interfaces, communication units, and the like. Here will not be described in detail. In addition, the device can also include other components not shown, such as radio frequency links, baseband processing units, network interfaces, processors, controllers, and the like. Here will not be described in detail.

[0119] Some embodiments of the present disclosure also provide an electronic device. FIG. 6 shows a block diagram of some embodiments of the electronic device of the present disclosure. For example, in some embodiments, the electronic device 60 can be various types of devices, for example, can include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), and the like, as well as fixed terminals such as digital TVs, desktop computers, and the like. For example, the electronic device 60 can include a display panel for displaying data and / or execution results utilized in the scheme according to the present disclosure. For example, the display panel can be various shapes, such as a rectangular panel, an oval panel, or a polygonal panel, and the like. In addition, the display panel can not only be a flat panel, but also a curved panel, or even a spherical panel.

[0120] As shown in FIG. 6, the electronic device 60 of this embodiment includes a memory 61 and a processor 62 coupled to the memory 61. It should be noted that the components of the electronic device 60 shown in FIG. 6 are only exemplary and are not limiting, and the electronic device 60 can also have other components according to actual application needs. The processor 62 can control other components in the electronic device 60 to perform the desired functions.

[0121] In some embodiments, the memory 61 is configured to store one or more computer readable instructions. When the processor 62 executes the computer readable instructions, the computer readable instructions are executed by the processor 62 to implement the method according to any of the above embodiments. For specific implementation of each step of the method and related explanations, please refer to the above embodiments, and the repeated parts will not be described here.

[0122] For example, the processor 62 and the memory 61 can communicate with each other directly or indirectly. For example, the processor 62 and the memory 61 can communicate through a network. The network can include a wireless network, a wired network, and / or any combination of a wireless network and a wired network. The processor 62 and the memory 61 can also communicate with each other through a system bus, and the present disclosure does not limit this.

[0123] For example, the processor 62 can be embodied as various appropriate processors, processing devices, etc., such as a central processing unit (CPU), a graphics processing unit (GPU), a network processing unit (NP), etc.; and can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component. The central processing unit (CPU) can be an X86 or ARM architecture, etc. For example, the memory 61 can include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The memory 61 may, for example, include a system memory, which stores, for example, an operating system, application programs, a boot loader, a database, and other programs, etc. Various application programs and various data, etc. can also be stored in the storage medium.

[0124] In addition, according to some embodiments of the present disclosure, various operations / processes according to the present disclosure, when implemented by software and / or firmware, can install programs constituting the software from a storage medium or a network to a computer system having a dedicated hardware structure, such as the computer system (or electronic device) 70 shown in FIG. 7, which, when various programs are installed, can perform various functions, including functions such as those described above, etc. FIG. 7 is a block diagram showing an example structure of a computer system that can be employed according to embodiments of the present disclosure.

[0125] In FIG. 7, a central processing unit (CPU) 701 executes various processes in accordance with a program stored in a read only memory (ROM) 702 or a program loaded from a storage section 708 to a random access memory (RAM) 703. In the RAM 703, data required when the CPU 701 executes various processes and the like is also stored as necessary. The central processing unit is merely exemplary, and can be other types of processors, such as the various processors described above. The ROM 702, the RAM 703, and the storage section 708 can be various forms of computer readable storage media, as described below. Note that, although the ROM 702, the RAM 703, and the storage section 708 are shown separately in FIG. 7, one or more of them can be combined or located in the same or different memory or storage modules.

[0126] The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output interface 705 is also connected to the bus 704.

[0127] The following components are connected to the input / output interface 705: an input section 706 including a touch panel, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, and the like; an output section 707 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, a vibrator, and the like; a storage section 708 including a hard disk, a magnetic tape, and the like; and a communication section 709 including a network interface card such as a LAN card, a modem, and the like. The communication section 709 allows communication processing to be performed via a network such as the Internet. It is easily understood that, although the various devices or modules in the computer system 70 are shown in FIG. 7 as communicating through the bus 704, they can also communicate through a network or other means, where the network can include a wireless network, a wired network, and / or any combination of a wireless network and a wired network.

[0128] A drive 710 is also connected to the input / output interface 705 as necessary. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is attached to the drive 710 as necessary, so that a computer program read therefrom is installed in the storage section 708 as necessary.

[0129] In the case where the above-described series of processes are implemented by software, the program constituting the software can be installed from a network such as the Internet or a storage medium such as the removable medium 711.

[0130] According to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication section 709, or installed from the storage section 708, or installed from the ROM 702. When the computer program is executed by the CPU 701, the above-described functions defined in the methods of the embodiments of the present disclosure are executed.

[0131] Note that, in the context of the present disclosure, a computer readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable medium can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as part of a carrier wave, in which the computer readable program code is carried. Such a propagated data signal can take any of a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wire, cable, RF (radio frequency), or any suitable combination thereof.

[0132] The above-described computer readable medium can be included in the above-described electronic device; or can exist separately from the electronic device and not be incorporated into the electronic device.

[0133] In some embodiments, a computer program including instructions which, when executed by a processor, causes the processor to carry out the method according to any of the embodiments described above is also provided. For example, the instructions can be embodied in a computer program code.

[0134] In an embodiment of the disclosure, computer program code to carry out operations of the disclosure described above can be written in one or more programming languages, or combinations thereof, including object oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0135] The flow diagrams and the block diagrams in the drawings are illustrations of possible architectures, functions, and operations for systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0136] The modules, components or units described in the embodiments of the present disclosure can be implemented by software or by hardware. In some cases, the name of the module, component or unit does not constitute a limitation on the module, component or unit itself.

[0137] The functionality described herein above can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, illustrative hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SOCs), complex programmable logic devices (CPLDs), etc.

[0138] According to some embodiments of the present disclosure, a content generation method is provided, including: displaying a generation instruction input by a user in an interaction interface between the user and an agent, wherein the generation instruction includes description information of target content; displaying one or more creative information in the interaction interface according to the generation instruction, wherein the one or more creative information is generated according to semantic understanding of the description information of the target content; in response to a selection operation of the user on target creative information in the one or more creative information, generating the target content according to the target creative information and a type of the target content by invoking one or more intelligent tools; and displaying the target content in the interaction interface.

[0139] In some embodiments, displaying the one or more creative information in the interaction interface according to the generation instruction includes: performing semantic understanding on the description information of the target content to determine theme information and the type of the target content; generating one or more creative information associated with the theme information and matching the type according to the theme information and the type of the target content, wherein different creative information includes different feature description information of the target content; and displaying the one or more creative information in the interaction interface.

[0140] In some embodiments, displaying the one or more creative information in the interaction interface according to the generation instruction includes: determining whether there is historical generated content related to the generation instruction in historical interaction information before the generation instruction; and in response to the existence of the historical generated content related to the generation instruction, displaying the one or more creative information in the interaction interface according to the generation instruction and the historical generated content.

[0141] In some embodiments, determining whether there is historical generated content related to the generation instruction includes: performing semantic understanding on the description information of the target content to determine theme information of the target content; determining theme information of one or more historical generated content in the historical interaction information; and determining whether there is historical generated content related to the generation instruction according to the theme information of the one or more historical generated content and the theme information of the target content.

[0142] In some embodiments, displaying the one or more pieces of creative information in the interactive interface according to the generation instruction and the historical generated content comprises: generating the one or more pieces of creative information according to the theme information and the type of the target content, and the creative information of the historical generated content, wherein the one or more pieces of creative information are associated with the theme information of the target content and the creative information of the historical generated content, and match the type; and displaying the one or more pieces of creative information in the interactive interface.

[0143] In some embodiments, displaying the one or more pieces of creative information in the interactive interface according to the generation instruction comprises: performing semantic understanding on the generation instruction to determine one or more intelligent tools; calling a first intelligent tool of the one or more intelligent tools to generate the one or more pieces of creative information according to the generation instruction; receiving the one or more pieces of creative information returned by the first intelligent tool; and displaying the one or more pieces of creative information in the interactive interface.

[0144] In some embodiments, displaying the one or more pieces of creative information in the interactive interface according to the generation instruction comprises: performing semantic understanding on the generation instruction to determine whether to call a second intelligent tool, wherein the second intelligent tool is different from the one or more intelligent tools; in response to determining to call the second intelligent tool, calling the second intelligent tool to generate the one or more pieces of creative information according to the generation instruction; receiving the one or more pieces of creative information returned by the second intelligent tool; and displaying the one or more pieces of creative information in the interactive interface.

[0145] In some embodiments, calling the one or more intelligent tools to generate the target content according to the target creative information and the type of the target content comprises: determining the one or more intelligent tools and an execution order of the one or more intelligent tools according to the target creative information, the type of the target content, and a function of each intelligent tool of the plurality of intelligent tools; and calling the one or more intelligent tools to generate the target content according to the execution order of the one or more intelligent tools and the target creative information.

[0146] In some embodiments, calling the one or more intelligent tools to generate the target content according to the execution order of the one or more intelligent tools and the target creative information comprises: generating prompt information of the one or more intelligent tools according to the execution order of the one or more intelligent tools and the target creative information; and inputting the prompt information into the one or more intelligent tools, so that one or more machine learning models corresponding to the one or more intelligent tools generate the target content according to the prompt information.

[0147] In some embodiments, the one or more intelligent tools are a plurality of intelligent tools, and generating the prompt information of the one or more intelligent tools according to the execution sequence of the one or more intelligent tools and the target creative information comprises: dividing the target creative information into creative information corresponding to each intelligent tool in the plurality of intelligent tools according to the functions of the plurality of intelligent tools and the execution sequence of the one or more intelligent tools; and generating the prompt information of each intelligent tool according to the creative information corresponding to the intelligent tool.

[0148] In some embodiments, inputting the prompt information into the one or more intelligent tools, and generating the target content by the one or more machine learning models corresponding to the one or more intelligent tools according to the prompt information comprises: inputting the prompt information of each intelligent tool into the intelligent tool, and generating the part of the target content generated by each intelligent tool according to the prompt information of the intelligent tool by the machine learning model corresponding to the intelligent tool in the execution sequence of each intelligent tool.

[0149] In some embodiments, the content generation method further comprises: before calling the one or more intelligent tools to generate the target content according to the target creative information and the type of the target content, updating the target creative information in response to a modification operation of the user on the target creative information; and / or updating the target content in response to a modification operation of the user on the target content.

[0150] In some embodiments, the content generation method further comprises: displaying a feedback control corresponding to the target content in the interactive interface, and obtaining feedback information corresponding to the feedback control in response to a triggering operation of the user on the feedback control, wherein the feedback control comprises at least one of a positive feedback control and a negative feedback control; and / or displaying a re-generation control corresponding to the target content in the interactive interface, and re-generating and displaying the target content according to the target creative information and the type of the target content in response to a triggering operation of the user on the re-generation control.

[0151] In some embodiments, in response to the target content comprising an image, the one or more pieces of creative information comprising description information of the screen features of the image; and / or in response to the target content comprising music, the one or more pieces of creative information comprising description information of at least one feature of the style, keywords, and lyrics of the music.

[0152] In some embodiments, the selection operation on the target creative information in the one or more pieces of creative information comprises: a selection operation on an item of the target creative information, a triggering operation on a control corresponding to the target creative information, or inputting indication information indicating the selection of the target creative information.

[0153] According to another embodiment of the present disclosure, a content generation apparatus is provided, comprising: a first display module configured to display a generation instruction input by a user in an interaction interface between the user and an agent, wherein the generation instruction comprises description information of target content; a second display module configured to display one or more creative information in the interaction interface according to the generation instruction, wherein the one or more creative information is generated according to semantic understanding of the description information of the target content; a generation module configured to, in response to a selection operation of the user on target creative information in the one or more creative information, generate the target content according to the target creative information and a type of the target content by invoking one or more intelligent tools; and a third display module configured to display the target content in the interaction interface.

[0154] According to still another embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory coupled to the processor, configured to store instructions, which, when executed by the processor, cause the processor to perform the content generation method of any embodiment of the present disclosure.

[0155] According to yet another embodiment of the present disclosure, a computer readable storage medium is provided, having stored thereon a computer program, which, when executed by a processor, performs the content generation method of any embodiment of the present disclosure.

[0156] According to still another embodiment of the present disclosure, a computer program product is provided, comprising: instructions, which, when executed by a processor, implement the content generation method of any embodiment of the present disclosure.

[0157] According to yet another embodiment of the present disclosure, a computer program is provided, comprising: instructions, which, when executed by a processor, implement the content generation method of any embodiment of the present disclosure.

[0158] The above description is merely some embodiments of the present disclosure and a description of the principles of the technology applied. Those skilled in the art should understand that the scope of the disclosure involved is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with each other to form technical solutions with similar functions disclosed in the present disclosure (but not limited to).

[0159] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application can be practiced without these specific details. In other instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

[0160] Moreover, while operations are depicted in a particular order, this should not be understood as requiring such an order nor imposing a sequential order of executed operations. In certain circumstances, multitasking and parallel processing can be advantageous. Likewise, while several specific implementation details are contained in the above discussion, these should not be taken as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments can also be implemented together in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination.

[0161] While certain aspects of the disclosure have been described with reference to particular embodiments, those skilled in the art will understand that the disclosure is illu- stative only and is not intended to be limiting. Many modifications and variations are possible in light of the above teachings. It is contemplated that, where any component or module is implemented in the embodiments described herein, there are a number of alternative ways to implement the same. The elements and acts of the various embodiments described above can be combined to provide further implementations. It is also contemplated that the components can be implemented using software, hardware, firmware, or combinations thereof that can be implemented in software and / or firmware. Additionally, one of ordinary skill will recognize that a plurality of hardware components can be implemented as software modules or components, or vice versa. Other structure and / or functionality can be combined, some can be split into separate components, and / or some can be omitted entirely. As such, non-limiting examples of the range of possible implementations have been set forth above. It is therefore contemplated to cover any and all modifications and variations of the present disclosure. It is further noted that some of the above described implementations can be adapted to any of the other implementations described herein. It is submitted with the understanding that the present disclosure will cover all such modifications and variations as can fall within the scope of the above description and following claims.

Claims

1. A content generation method, comprising: displaying, in an interaction interface between a user and an agent, a generation instruction input by the user, wherein the generation instruction comprises description information of target content; displaying, in the interaction interface, one or more creative information according to the generation instruction, wherein the one or more creative information is generated according to semantic understanding of the description information of the target content; in response to a selection operation of the user on target creative information in the one or more creative information, invoking one or more intelligent tools according to the target creative information and a type of the target content to generate the target content; displaying, in the interaction interface, the target content.

2. The content generation method of claim 1, wherein, The displaying, in the interaction interface, one or more creative information according to the generation instruction comprises: performing semantic understanding on the description information of the target content to determine theme information and a type of the target content; generating the one or more creative information associated with the theme information and matching the type according to the theme information and the type of the target content, wherein different creative information comprises different feature description information of the target content; displaying, in the interaction interface, the one or more creative information.

3. The content generation method according to claim 1 or 2, wherein The displaying, in the interaction interface, one or more creative information according to the generation instruction comprises: determining, in historical interaction information before the generation instruction, whether there is historical generation content related to the generation instruction; in response to the existence of the historical generation content related to the generation instruction, displaying, in the interaction interface, one or more creative information according to the generation instruction and the historical generation content.

4. The content generation method of claim 3, wherein, The determining whether there is historical generation content related to the generation instruction comprises: performing semantic understanding on the description information of the target content to determine theme information of the target content; determining theme information of one or more historical generation contents in the historical interaction information; determining whether there is historical generation content related to the generation instruction according to the theme information of the one or more historical generation contents and the theme information of the target content.

5. The content generation method of claim 4, wherein, The displaying, in the interaction interface, one or more creative information according to the generation instruction and the historical generation content comprises: generating the one or more creative information according to the theme information and the type of the target content, and creative information of the historical generation content, wherein the one or more creative information is associated with the theme information of the target content and the creative information of the historical generation content, and matches the type; displaying, in the interaction interface, the one or more creative information.

6. The content generation method according to any one of claims 1-5, wherein, The displaying, in the interaction interface, one or more creative information according to the generation instruction comprises: performing semantic understanding on the generation instruction to determine the one or more intelligent tools; invoking a first intelligent tool in the one or more intelligent tools to generate the one or more creative information according to the generation instruction; receiving the one or more creative information returned by the first intelligent tool; displaying, in the interaction interface, the one or more creative information.

7. The content generation method according to any one of claims 1-5, wherein, The displaying one or more pieces of creative information in the interactive interface according to the generation instruction comprises: performing semantic understanding on the generation instruction to determine whether to call a second intelligent tool, wherein the second intelligent tool is different from the one or more intelligent tools; in response to a determination that the second intelligent tool is called, calling the second intelligent tool to generate the one or more pieces of creative information according to the generation instruction; receiving the one or more pieces of creative information returned by the second intelligent tool; displaying the one or more pieces of creative information in the interactive interface.

8. The content generation method according to any one of claims 1-7, wherein, The calling one or more intelligent tools to generate the target content according to the target creative information and the type of the target content comprises: determining the one or more intelligent tools and an execution order of the one or more intelligent tools according to the target creative information, the type of the target content, and a function of each intelligent tool in the plurality of intelligent tools; calling one or more intelligent tools to generate the target content according to the execution order of the one or more intelligent tools and the target creative information.

9. The content generation method of claim 8, wherein, The calling one or more intelligent tools to generate the target content according to the execution order of the one or more intelligent tools and the target creative information comprises: generating prompt information of the one or more intelligent tools according to the execution order of the one or more intelligent tools and the target creative information; inputting the prompt information into the one or more intelligent tools, and generating the target content according to the prompt information by one or more machine learning models corresponding to the one or more intelligent tools.

10. The content generation method of claim 9, wherein, The one or more intelligent tools are a plurality of intelligent tools, and the generating prompt information of the one or more intelligent tools according to the execution order of the one or more intelligent tools and the target creative information comprises: dividing the target creative information into creative information corresponding to each intelligent tool in the plurality of intelligent tools according to the function of the plurality of intelligent tools and the execution order of the one or more intelligent tools; generating prompt information of each intelligent tool according to the creative information corresponding to each intelligent tool.

11. The content generation method according to claim 9 or 10, wherein The inputting the prompt information into the one or more intelligent tools, and generating the target content according to the prompt information by one or more machine learning models corresponding to the one or more intelligent tools comprises: inputting the prompt information of each intelligent tool into each intelligent tool, and generating a part of the target content generated by each intelligent tool according to the prompt information of each intelligent tool by a machine learning model corresponding to each intelligent tool in an execution order of each intelligent tool.

12. The content generation method of any one of claims 1-11, further comprising: updating the target creative information in response to a modification operation of the user on the target creative information before the calling one or more intelligent tools to generate the target content according to the target creative information and the type of the target content; and / or updating the target content in response to a modification operation of the user on the target content.

13. The content generation method of any of claims 1-12, further comprising: displaying, in the interactive interface, a feedback control corresponding to the target content, and in response to a triggering operation of the feedback control by the user, obtaining feedback information corresponding to the feedback control, wherein the feedback control comprises at least one of a positive feedback control and a negative feedback control; and / or displaying, in the interactive interface, a re-generation control corresponding to the target content, and in response to a triggering operation of the re-generation control by the user, invoking the one or more intelligent tools to re-generate and display the target content according to the target creative information and a type of the target content.

14. The content generation method of any of claims 1-13, wherein: in response to the target content comprising an image, the one or more pieces of creative information comprise description information of a picture feature of the image; and / or in response to the target content comprising music, the one or more pieces of creative information comprise description information of at least one of a style, a keyword, and lyrics of the music.

15. The content generation method of any one of claims 1-14, wherein, The selection operation of the target creative information from the one or more pieces of creative information comprises a selection operation of a piece of the target creative information, a triggering operation of a control corresponding to the target creative information, or input of indication information indicating selection of the target creative information.

16. A content generation apparatus, comprising: a first display module configured to display, in an interactive interface between a user and an intelligent agent, a generation instruction input by the user, wherein the generation instruction comprises description information of target content; a second display module configured to display, in the interactive interface, one or more pieces of creative information according to the generation instruction, wherein the one or more pieces of creative information are generated according to semantic understanding of the description information of the target content; a generation module configured to, in response to a selection operation of target creative information from the one or more pieces of creative information by the user, invoke one or more intelligent tools to generate the target content according to the target creative information and a type of the target content; a third display module configured to display, in the interactive interface, the target content.

17. An electronic device, comprising: a processor; and a memory coupled to the processor for storing instructions, which when executed by the processor, cause the processor to perform the content generation method of any of claims 1-15. The program, when executed by a processor, implements the content generation method of any of claims 1-15.

18. A computer readable storage medium having stored thereon a computer program, wherein, 19. A computer program product comprising instructions which, when executed by a processor, cause the processor to perform the content generation method of any of claims 1-15.

20. A computer program comprising instructions which, when executed by a processor, cause the processor to perform the content generation method of any of claims 1-15. ​

Images