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

Abstract

The present disclosure relates to a content generation method, device, electronic device, storage medium and program product, and relates to the field of computer technology. The content generation method of the present disclosure includes: displaying a generation instruction input by a user in an interactive interface between a user and an intelligent agent, wherein the generation instruction includes description information of a target content; displaying one or more creative information in the interactive interface according to the generation instruction, wherein the one or more creative information is generated according to the semantic understanding of the description information of the target content; in response to a user's selection operation of a target creative information in the one or more creative information, calling one or more intelligent tools according to the type of the target creative information and the target content to generate the target content; and displaying the target content in the interactive interface.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a content generation method, device, electronic device, storage medium and program product. Background Art

[0002] With the development of artificial intelligence (AI) technology, users can already use some applications to automatically generate content such as images, music, and even videos. These applications can receive instructions input by users and generate content corresponding to the instructions based on generative artificial intelligence technology. Summary of the invention

[0003] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0004] According to some embodiments of the present disclosure, a content generation method is provided, comprising: displaying generation instructions input by a user in an interaction interface between a user and an intelligent agent, wherein the generation instructions include description information of a target content; displaying one or more pieces of creative information in the interaction interface according to the generation instructions, wherein the one or more pieces of creative information are generated based on a semantic understanding of the description information of the target content; in response to a user's selection operation of target creative information in the one or more pieces of creative information, calling one or more intelligent tools according to the types of the target creative information and the target content to generate the target content; and displaying the target content in the interaction interface.

[0005] According to some other embodiments of the present disclosure, there is provided a content generating device, comprising: a first display module, configured to display a generating instruction input by a user in an interaction interface between the user and an intelligent agent, wherein the generating instruction includes description information of a target content; a second display module, configured to display one or more pieces of creative information in the interaction interface according to the generating instruction, wherein the one or more pieces of creative information are generated according to a semantic understanding of the description information of the target content; a generating module, configured to generate a target content by calling one or more intelligent tools according to the types of the target creative information and the target content in response to a user's selection operation of a target creative information in the one or more pieces of creative information; and a third display module, configured to display the target content in the interaction interface.

[0006] According to some further embodiments of the present disclosure, an electronic device is provided, including: a processor; and a memory coupled to the processor, for storing instructions, which, when executed by the processor, causes the processor to execute the content generation method of any embodiment of the present disclosure.

[0007] According to some further embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the program is executed by a processor, the content generating method of any embodiment of the present disclosure is implemented.

[0008] According to still some embodiments of the present disclosure, a computer program product is provided, comprising instructions, which, when executed by a processor, cause the processor to execute the content generating method according to any embodiment of the present disclosure.

[0009] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The drawings described herein are used to provide a further understanding of the present disclosure. Each of the drawings together with the following detailed description is included in this specification and forms a part of the specification, and is used to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and do not constitute a limitation on the present disclosure. In the drawings:

[0011] Figure 1 A schematic diagram showing a flow chart of a content generation method according to some embodiments of the present disclosure;

[0012] Figure 2 A schematic diagram showing an interactive interface in some embodiments of the present disclosure;

[0013] Figure 3 Schematic diagrams showing interaction interfaces of other embodiments of the present disclosure;

[0014] Figure 4 Schematic diagrams showing interaction interfaces of yet other embodiments of the present disclosure;

[0015] Figure 5 A schematic diagram showing the structure of a content generating device according to some embodiments of the present disclosure;

[0016] Figure 6 A schematic diagram showing the structure of an electronic device according to some embodiments of the present disclosure;

[0017] Figure 7 A schematic diagram showing the structure of a computer system according to some embodiments of the present disclosure.

[0018] It should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not necessarily drawn according to the actual proportional relationship. The same or similar reference numerals are used in the various drawings to represent the same or similar parts. Therefore, once an item is defined in one drawing, it may not be further discussed in subsequent drawings. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure, but it is obvious that the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. The following description of the embodiments is actually only illustrative and is by no means intended to limit 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.

[0020] It should be understood that the various steps recorded in the method embodiments of the present disclosure can be performed in different orders, and / or performed in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown in the execution. The scope of the present disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values ​​of the parts and steps set forth in these embodiments should be interpreted as being merely exemplary and do not limit the scope of the present disclosure.

[0021] The term "include" and its variations used in the present disclosure mean an open term that includes at least the following elements / features but does not exclude other elements / features, that is, "including but not limited to". In addition, the term "include" and its variations used in the present disclosure mean an open term that includes at least the following elements / features but does not exclude other elements / features, that is, "including but not limited to". Therefore, include is synonymous with include. The term "based on" means "based at least in part on".

[0022] References throughout this specification to "one embodiment," "some embodiments," or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; and the term "some embodiments" means "at least some embodiments." Furthermore, the appearances of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout this specification do not necessarily all refer to the same embodiment, but may do so.

[0023] It should be noted that the concepts of "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. Unless otherwise specified, the concepts of "first", "second", etc. are not intended to imply that the objects described in this way must be in a given order in time, space, ranking, or any other manner.

[0024] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0025] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0026] The embodiments of the present disclosure are described in detail below in conjunction with the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. In addition, in one or more embodiments, specific features, structures or characteristics can be combined in any suitable manner that will be clear from the present disclosure by a person of ordinary skill in the art.

[0027] At present, applications based on generative artificial intelligence technology can use generative models to generate corresponding content according to user instructions. Usually, users need to enter clear instructions to generate more accurate content for users. For example, if a user wants to generate an image, he needs to describe what is contained in the image in order to get an image that is more in line with expectations. If the user only enters vague and unclear instructions, such as "generate a Children's Day poster", then the final generated image is likely to not meet user needs, be of low quality, or even contain errors.

[0028] In order to generate more accurate generated content for users and facilitate their use, the present disclosure proposes a content generation method. Figures 1 to 4 Give a description.

[0029] The content generation method of the disclosed embodiment can be performed by a content generation device, and the content generation device can be implemented in hardware and / or software. For example, the content generation device is an agent, a robot, an interactive application, etc. The user can have a human-computer dialogue with the content generation device. For example, the user can use oral natural language input (i.e., speech) to provide commands and / or requests to the content generation device, which in some cases can be converted into text and then processed, and / or by providing text (e.g., typing) natural language input.

[0030] The content generation device may have a generation function based on generative artificial intelligence technology. For example, the content generation device may be configured with a corresponding generative model, or it may cooperate with other intelligent tools with generation functions to provide users with generation functions during the interaction process. The present disclosure does not impose any restrictions on this.

[0031] Figure 1Flowcharts of some embodiments of the method for generating content of the present disclosure. Figure 1 As shown, the method of this embodiment includes: steps S102 to S108.

[0032] In step S102, a generation instruction input by the user is displayed in an interaction interface between the user and the agent, wherein the generation instruction includes description information of the target content.

[0033] The content generation device may include one or more intelligent agents (which may be implemented by software or a combination of software and hardware), and may also include other intelligent tools other than intelligent agents, such as plug-ins, functional modules, and other tools that implement specific functions. The intelligent agent may be a type of intelligent tool. The user may interact with the intelligent agent, and the generation instructions input by the user are displayed in the interactive interface. The generation instructions may only include simple description information of the target content, such as "generate a Children's Day poster".

[0034] In step S104, one or more creative information is displayed in the interactive interface according to the generation instruction.

[0035] One or more creative information is generated based on the semantic understanding of the description information of the target content. By understanding and processing the description information of the target content in natural language, one or more creative information can be automatically generated. The one or more creative information 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, higher quality content can be generated compared to the description information of the target content input by the user.

[0036] In step S106, in response to the user's selection operation on target creative information among the one or more creative information, one or more intelligent tools are called according to the types of the target creative information and the target content to generate the target content.

[0037] The type of target content may include the media type of the target content, such as text, image, audio, video, etc., without limitation to the examples cited. Different types may correspond to different intelligent tools. Intelligent tools may be tools such as intelligent entities and plug-ins that can implement specific functions. For example, an intelligent tool may be an intelligent entity for generating music, an intelligent tool may be a plug-in for adding special effects to images, and the like. One or more intelligent tools include generative tools, and corresponding generative models may be configured. The target content may require multiple intelligent tools to collaborate and generate. One or more required intelligent tools may be determined based on the target creative information and the type of the target content, and then one or more intelligent tools may be called to generate the target content.

[0038] The intelligent agent cooperates with one or more intelligent tools to finally generate the target content. Since the target creative information can describe the target content in a more detailed and accurate manner, the target content finally generated is more accurate and of higher quality.

[0039] In step S108, the target content is displayed in the interactive interface.

[0040] The target content generated by one or more intelligent tools is called and returned to the intelligent agent, and the target content is displayed in the interactive interface.

[0041] In the method of the above embodiment, the user inputs a generation instruction during the interaction with the intelligent agent, and the generation instruction includes the description information of the target content. One or more creative information is automatically generated through the 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 creative information, one or more intelligent tools are called according to the type of the target creative information and the target content to generate the target content. In the method of the above embodiment, the entire generation process of the target content is completed by the cooperation of the intelligent agent and one or more intelligent tools, and is divided into two stages: creative generation and target content generation. First, the generation instruction is understood and processed in natural language to simulate the conception of humans during creation, so as to obtain creative information that describes the target content in more detail and accuracy. After the user selects the target creative information, one or more intelligent tools are called to generate the target content. Compared with directly generating the target content using the generative model according to the generation instruction input by the user, the target content obtained is more accurate, more in line with the user's intention, and has higher quality. In addition, by automatically providing the user with one or more creative information, the user does not need to input detailed creative information, which can improve the accuracy of the generation of the target content while improving the generation efficiency.

[0042] The following describes how to display one or more creative information in an interactive interface according to a generation instruction in conjunction with some embodiments.

[0043] In some embodiments, a machine learning model corresponding to the intelligent agent is called to generate and display one or more creative messages according to generation instructions.

[0044] The machine learning model corresponding to the agent is, for example, a large language model, a generative model, etc., but is not limited to the examples given. After the user generates instructions through interactive input with the agent, the machine learning model corresponding to the agent can be directly used to understand the generated instructions and generate one or more creative information.

[0045] Other intelligent tools may also be used to generate one or more creative information. In some embodiments, semantic understanding is performed on the generation instruction to determine one or more intelligent tools; a first intelligent tool among the one or more intelligent tools is called to generate one or more creative information according to the generation instruction; one or more creative information returned by the first intelligent tool is received; and one or more creative information is displayed in the interactive interface.

[0046] The machine learning model corresponding to the intelligent agent can be called first, the generation instruction can be semantically understood, and one or more intelligent tools required to generate the target content can be determined. For example, the generation instruction can be semantically understood, the type of the target content can be determined, and one or more intelligent tools can be determined according to the type of the target content. The first intelligent tool among the one or more intelligent tools has the function of generating creative information, and the intelligent agent can send the generation instruction or the description information of the target content to the first intelligent tool, and the first intelligent tool generates one or more creative information and returns it to the intelligent agent. The function of generating creative information can be partially or fully configured in one or more intelligent tools. In the case where multiple intelligent tools need to be called and multiple intelligent tools are configured with the function of generating creative information, the first intelligent tool called will be used as the first intelligent tool in the order of calling the intelligent tools required to generate the target content.

[0047] In some embodiments, a semantic understanding is performed on the generation instruction to determine whether to call a second intelligent tool, wherein the second intelligent tool is different from 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 creative information according to the generation instruction; the one or more creative information returned by the second intelligent tool is received; and the one or more creative information is displayed in an interactive interface.

[0048] The machine learning model corresponding to the intelligent agent can be called first to perform semantic understanding of the generation instruction and determine whether it is necessary to call the second intelligent tool to generate one or more creative information. The second intelligent tool can be a tool dedicated to generating creative information. If the generation instruction itself has described the characteristics of the target content in sufficient detail, it is not necessary to generate one or more creative information, and the target content can be generated directly according to the generation instruction. If it is necessary to call the second intelligent tool, 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 will generate one or more creative information and return it to the intelligent agent.

[0049] 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, it can interact with other intelligent tools that have the function of generating creative information to obtain one or more creative information and display them to the user.

[0050] Regardless of whether the creative information is generated by an intelligent agent or by other intelligent tools, the specific method is similar and is described below in conjunction with some embodiments.

[0051] In some embodiments, semantic understanding is performed on the description information of the target content to determine the subject information and type of the target content; based on the subject information and type of the target content, one or more creative information associated with the subject information and matching the type is generated, wherein different creative information includes different feature description information of the target content; and one or more creative information is displayed in an interactive interface.

[0052] For example, if the description information of the target content is "Children's Day poster", semantic understanding can be used to determine that the theme information of the target content is "Children's Day" and the type is image. Then, machine learning models (large language models, generative models, etc.) can be used to generate one or more creative information associated with the theme information and matching the type. For example, a creative information generated is "The background is a dreamy starry sky with twinkling stars and meteors streaking across the sky. Under the starry sky is a large amusement park illuminated by gorgeous lights. The outlines of amusement facilities such as roller coasters and Ferris wheels are clearly visible, and there is colorful smoke around them..."

[0053] By understanding the subject and type of the target content, the accuracy of the generated creative information can be improved and more in line with the user's intention.

[0054] In some embodiments, in response to the target content including an image, one or more creative information includes description information of the picture features of the image; and / or in response to the target content including music, one or more creative information includes description information of at least one feature of the music's style, keywords, and lyrics.

[0055] For target content including images, one or more creative information can be used to more clearly and in detail describe various image-related features such as objects, people, colors, light, background, etc. For target content including music, one or more creative information can be used to more clearly and in detail describe the style of the music (which may include melody, rhythm, instruments, etc.).

[0056] When generating creative information, historical interaction information and historical generated content may also be referenced. In some embodiments, in 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 the existence of historical generated content related to the generation instruction, one or more creative information is displayed in the interactive interface according to the generation instruction and the historical generated content.

[0057] The preset number of historical interaction information 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 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 sent a generation instruction "Can you help me create some music suitable for playing at the 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, namely "Children's Day poster", and it can be understood that the user is likely to want the music to match the poster. It will be more accurate to generate one or more creative information based on the generation instruction and the historical generated content.

[0058] In the case where the first smart tool or the second smart tool needs to be called to generate one or more creative information, the intelligent agent may send historical interaction information or historical generated content to the first smart tool or the second smart tool.

[0059] In some embodiments, determining whether there is historical generated content related to the generation instruction includes: semantically understanding the description information of the target content to determine the subject information of the target content; determining the subject 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 based on the subject information of one or more historical generated content and the subject information of the target content.

[0060] The subject information of the historical generated content can be determined based on the historical generated content, the creative information corresponding to the historical generated content, or the generation instruction corresponding to the historical generated content. For example, if the subject of the historical generated content and the target content are both related to Children's Day, it can be determined that there is historical generated content related to the current generation instruction.

[0061] By understanding and matching the subject information of the target content and the historical generated content, it can be more accurately determined whether there is historical generated content related to the generation instruction.

[0062] In some embodiments, displaying one or more pieces of creative information in an interactive interface based on generation instructions and historically generated content includes: generating one or more pieces of creative information based on subject information and type of target content and creative information of historically generated content, wherein the one or more pieces of creative information are associated with the subject information of the target content and the creative information of historically generated content, and match the type; and displaying one or more pieces of creative information in the interactive interface.

[0063] For example, the creative information of historically generated content can be semantically understood, and key information can be extracted to generate 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", and "Ferris wheel" can be extracted to generate one or more pieces of creative information. The generated one or more pieces of creative information are associated with the creative information of historically generated content and conform to the theme and type of the target content. For example, a piece of creative information generated is "Let's create a piece of music about an amusement park, a roller coaster, and a Ferris wheel that is lively and cheerful, with brisk drum beats and smart melodies."

[0064] The method of the above embodiment generates one or more pieces of creative information that are associated with the creative information of historically generated content and conform to the subject and type of the target content, thereby improving the accuracy of the one or more pieces of creative information and being more in line with the user's intention, thereby improving the accuracy and quality of subsequently generated target content.

[0065] The method for generating one or more creative information in each of the above embodiments may be executed on the intelligent agent side or on other intelligent tools side.

[0066] When displaying one or more creative information, guidance information can be displayed to reply to the user's generation instruction, which is more in line with the expression logic of natural language. For example, the guidance information is "OK, there are two poster ideas for you to choose from", which is not limited to the examples given.

[0067] After one or more creative information are generated and displayed, the user can select target creative information from them. In some embodiments, the selection operation of the target creative information from the one or more creative information includes: selecting an item of the target creative information, triggering a control corresponding to the target creative information, or inputting indication information indicating the selection of the target creative information.

[0068] The user may select target creative information in a variety of ways, not limited to the above examples.

[0069] The following describes how to call one or more intelligent tools to generate target content according to target creative information and the type of target content in conjunction with some embodiments.

[0070] In some embodiments, one or more smart tools and the execution order of one or more smart tools are determined based on target creative information, the type of target content and the function of each smart tool in multiple smart tools; and one or more smart tools are called to generate target content based on the execution order of one or more smart tools and the target creative information.

[0071] By analyzing the types of target creative information and target content, the execution order of one or more intelligent tools that need to be called can be determined. For example, to generate an audio picture book, it may be necessary to call an image generation tool and an audio generation tool to generate images and audio respectively, and then call a tool to integrate images and audio.

[0072] When multiple smart tools need to collaborate to generate the target content, each smart tool generates the target content portion generated by each smart tool according to its own execution order. If the current smart tool needs to use the generation result of the previous smart tool, the previous smart tool sends the generation result to the current smart tool.

[0073] When multiple smart tools collaborate to generate target content, the execution order of each smart tool is first determined by analyzing the target creative information and the type of target content, and then each smart tool is called according to the execution order, which can improve the accuracy of the generated target content.

[0074] In some embodiments, calling one or more smart tools to generate target content includes: generating prompt information for one or more smart tools according to the execution order and target creative information of the one or more smart tools; inputting the prompt information into the one or more smart tools, and having one or more second machine learning models corresponding to the one or more smart tools generate the target content according to the prompt information.

[0075] Prompt information (Prompt) for each smart tool can be generated based on the execution order and target creative information of one or more smart tools, and the prompt information of each smart tool can be input into the machine learning model corresponding to each smart tool. The machine learning model corresponding to each smart tool generates the part of the target content generated by each smart tool based on the prompt information.

[0076] Furthermore, 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 and the execution order of each intelligent tool.

[0077] Each intelligent tool generates the part of the target content generated by each intelligent tool in the execution order and according to the corresponding prompt information, which can improve the accuracy of the target content generation.

[0078] In some embodiments, one or more smart tools are multiple smart tools, and generating prompt information for one or more smart tools according to the execution order of the one or more smart tools and target creative information includes: dividing the target creative information into creative information corresponding to each smart tool in the multiple smart tools according to the functions of the multiple smart tools and the execution order of the one or more smart tools; generating prompt information for each smart tool according to the creative information corresponding to each smart tool.

[0079] In some cases, the target creative information may include creative information for generating different parts of the target content. For example, if the target content is a video, the target creative information includes description information of the video screen and description information of the soundtrack. The description information of the screen and the description information of the soundtrack can be separated to generate prompt information for the image generation tool and description information for the music generation tool respectively. If each intelligent tool needs to refer to all the target creative information, it is not necessary to divide it, but it needs to be done according to the target creative information.

[0080] By dividing the target creative information, prompt information can be generated more accurately for each intelligent tool, so that each intelligent tool can more accurately generate the part of the target content generated by each intelligent tool.

[0081] After selecting the target creative information, the user can modify the target creative information to obtain more accurate target creative information. In some embodiments, before calling one or more intelligent tools to generate the target content according to the type of the target creative information and the target content, the target creative information is updated in response to the user's modification operation on the target creative information.

[0082] For example, in response to a user triggering an operation on a modification control of the target creative information, or in response to a user's specific operation on the target creative information triggering the modification of the target creative information, the target creative information can be displayed in an interactive interface between the user and the intelligent agent, in a new page, floating layer, window, panel, or any other form of interface, and the target creative information can be updated by receiving user input, deletion, modification, and other operations, and subsequently generating target content based on the updated target creative information.

[0083] It is also possible to display updated creative information in response to a user's modification operation on any creative information in one or more creative information, and to call one or more intelligent tools to generate target content according to the types of the target creative information and target content in response to a user's selection operation on target creative information in one or more creative information.

[0084] The user can modify any creative information first, and then select the modified creative information as the target creative information.

[0085] The generated one or more creative information can be used to provide inspiration for users, and by providing users with the function of modification, users can modify one or more creative information to better suit their intentions, thereby making the generated target content more accurate and of higher quality.

[0086] The user can also modify the generated target content. In some embodiments, in response to the user's modification operation on the target content, the target content is updated.

[0087] For example, in response to a modification instruction input by a user, the target content is modified. The modification instruction may include a feature description of the part to be modified. For example, if the modification instruction input by the user is "change the roller coaster to a merry-go-round", the Children's Day poster can be regenerated according to the modification instruction, and the roller coaster therein is changed to a merry-go-round.

[0088] 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 the user's triggering 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.

[0089] For example, feedback controls include “like” and “dislike” controls. Based on user feedback information, the machine learning model used to generate target content can be adjusted to enable more accurate target content to be generated subsequently.

[0090] If the user is not satisfied with the generated target content, the regeneration function can be triggered. In some embodiments, a regeneration control corresponding to the target content is displayed in the interactive interface, and in response to the user's triggering operation on the regeneration control, one or more intelligent tools are called according to the target creative information and the type of the target content to regenerate and display the target content.

[0091] Users can trigger the regeneration of controls to obtain satisfactory target content.

[0092] Combine the following Figures 2~4 Some embodiments of the interactive interface corresponding to the content generation method of the present disclosure are described.

[0093] like Figure 2 The interactive interface between the user and agent A is shown. The user inputs a generating instruction 201 "help me generate a poster for Children's Day", and agent A then responds with two generated creative messages 202. The user can select one of the two creative messages as the target creative message. For example, Figure 2As shown, the user inputs indication information 203 indicating the selection of target creative information, "The second one is good". The user may also select the target creative information by clicking on an item of the target creative information, or a control corresponding to each piece of creative information may be displayed, and the user may 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, indication information 204 for generating target content may be displayed. The generated target content may also be directly displayed.

[0094] like Figure 3 As shown, multiple images (target contents) 301 can be generated and displayed, and the user can select a satisfactory image to save, download, etc. The user can continue to input a generation instruction 302 "Can you help me create music suitable for the Children's Day party?". Since there is a generated historical generated content related to the generation instruction 302, that is, the generated image 301, the creative information 303 generated according to the generation instruction 302 is associated with the creative information of the generated image and conforms to the theme and music type of the Children's Day party. If there is only one creative information, the target content can be directly generated without the user's selection or confirmation operation.

[0095] like Figure 4 As shown, the generated multiple music 401, that is, the generated multiple target contents, can be displayed. The user can download, save, forward, etc. one or more music 401, which is not limited to the examples given.

[0096] The present disclosure also provides a content generation device, Figure 5 Give a description.

[0097] Figure 5 FIG. 1 is a structural diagram of some embodiments of the content generation device of the present disclosure. Figure 5 As shown, the content generating device 50 of this embodiment includes: a first display module 510 , a second display module 520 , a generating module 530 , and a third display module 540 .

[0098] The first display module 510 is configured to display a generation instruction input by a user in an interaction interface between the user and the agent, wherein the generation instruction includes description information of the target content.

[0099] The second display module 520 is configured to display one or more pieces of creative information in the interactive interface according to the generation instruction, wherein the one or more pieces of creative information are generated according to the semantic understanding of the description information of the target content.

[0100] The generation module 530 is configured to, in response to a user's selection operation on target creative information among one or more pieces of creative information, call one or more intelligent tools to generate target content according to the types of the target creative information and target content.

[0101] The third display module 540 is configured to display the target content in the interactive interface.

[0102] In some embodiments, the second display module 520 is configured to perform semantic understanding of the description information of the target content to determine the subject information and type of the target content; based on the subject information and type of the target content, generate one or more creative information associated with the subject information and matching the type, wherein different creative information includes different feature description information of the target content; and display one or more creative information in the interactive interface.

[0103] In some embodiments, the second display module 520 is configured to determine whether there is historical generated content related to the generation instruction in the historical interaction information before the generation instruction; in response to the existence of historical generated content related to the generation instruction, one or more creative information is displayed in the interactive interface according to the generation instruction and the historical generated content.

[0104] In some embodiments, the second display module 520 is configured to perform semantic understanding on the description information of the target content to determine the subject information of the target content; determine the subject information of one or more historical generated content in the historical interaction information; and determine whether there is historical generated content related to the generation instruction based on the subject information of one or more historical generated content and the subject information of the target content.

[0105] In some embodiments, the second display module 520 is configured to generate one or more pieces of creative information based on the subject information and type of the target content and the creative information of the historically generated content, wherein the one or more pieces of creative information are associated with the subject 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.

[0106] In some embodiments, the second display module 520 is configured to perform semantic understanding of the generation instruction and determine one or more intelligent tools; call the first intelligent tool among the one or more intelligent tools to generate one or more creative information according to the generation instruction; receive one or more creative information returned by the first intelligent tool; and display one or more creative information in the interactive interface.

[0107] In some embodiments, the second display module 520 is configured to perform semantic understanding of the generation instruction to determine whether to call a second intelligent tool, wherein the second intelligent tool is different from one or more intelligent tools; in response to determining to call the second intelligent tool, call the second intelligent tool to generate one or more creative information according to the generation instruction; receive one or more creative information returned by the second intelligent tool; and display one or more creative information in the interactive interface.

[0108] In some embodiments, the generation module 530 is configured to determine one or more intelligent tools and the execution order of one or more intelligent tools based on the target creative information, the type of target content and the function of each intelligent tool in multiple intelligent tools; and call one or more intelligent tools to generate the target content based on the execution order of one or more intelligent tools and the target creative information.

[0109] In some embodiments, the one or more smart tools are multiple smart tools, and the generation module 530 is configured to divide the target creative information into creative information corresponding to each of the multiple smart tools according to the functions of the multiple smart tools and the execution order of the one or more smart tools; and generate prompt information for each smart tool according to the creative information corresponding to each smart tool.

[0110] In some embodiments, the generation module 530 is configured to input the prompt information of each intelligent tool 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 and the execution order of each intelligent tool.

[0111] In some embodiments, the content generation device 50 also includes a first modification module 550, which is configured to update the target creative information in response to the user's modification operation on the target creative information before calling one or more intelligent tools to generate the target content based on the type of the target creative information and the target content; and / or a second modification module 560, which is configured to update the target content in response to the user's modification operation on the target content.

[0112] In some embodiments, the third display module 540 is also configured to display a feedback control corresponding to the target content in the interactive interface, and in response to a user triggering the feedback control, obtain feedback information corresponding to the feedback control, wherein the feedback control includes at least one of a positive feedback control and a negative feedback control; and / or display a regeneration control corresponding to the target content in the interactive interface, and in response to a user triggering the regeneration control, call one or more intelligent tools according to the target creative information and the type of target content to regenerate and display the target content.

[0113] In some embodiments, in response to the target content including an image, one or more creative information includes description information of the picture features of the image; and / or in response to the target content including music, one or more creative information includes description information of at least one feature of the music's style, keywords, and lyrics.

[0114] In some embodiments, the selection operation on target creative information among the one or more creative information includes: a selection operation on an item of the target creative information, a trigger operation on a control corresponding to the target creative information, or inputting indication information indicating the selection of the target creative information.

[0115] It should be noted that the above-mentioned units (modules) are only logical modules divided according to the specific functions they implement, and are not used to limit the specific implementation methods. For example, they can be implemented in software, hardware, or a combination of software and hardware. In actual implementation, the above-mentioned units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.). In addition, the above-mentioned units are shown with dotted lines in the drawings to indicate that these units may not actually exist, and the operations / functions they implement can be implemented by the processing circuit itself.

[0116] In addition, although not shown, the device may also include a memory, which may store various information generated by the device, various units contained in the device during operation, programs and data for operation, data to be sent by the communication unit, etc. The memory may be a volatile memory and / or a non-volatile memory. For example, the memory may 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), and a flash memory. Of course, the memory may also be located outside the device. Optionally, although not shown, the device may also include a communication unit, which may be used to communicate with other devices. In one example, the communication unit may be implemented in an appropriate manner known in the art, such as including communication components such as an antenna array and / or a radio frequency link, various types of interfaces, communication units, etc. It will not be described in detail here. In addition, the device may also include other components not shown, such as a radio frequency link, a baseband processing unit, a network interface, a processor, a controller, etc. It will not be described in detail here.

[0117] Some embodiments of the present disclosure also provide an electronic device. Figure 6Block diagrams of some embodiments of the electronic device of the present disclosure are shown. For example, in some embodiments, the electronic device 60 can be various types of devices, for example, can include but are not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. For example, the electronic device 60 can include a display panel for displaying data and / or execution results used in the scheme of the present disclosure. For example, the display panel can be in various shapes, such as a rectangular panel, an elliptical panel, or a polygonal panel, etc. In addition, the display panel can be not only a flat panel, but also a curved panel, or even a spherical panel.

[0118] like Figure 6 As shown, 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 Figure 6 The components of the electronic device 60 shown are only exemplary and non-limiting. The electronic device 60 may also have other components according to actual application requirements. The processor 62 may control other components in the electronic device 60 to perform desired functions.

[0119] In some embodiments, the memory 61 is used to store one or more computer-readable instructions. When the processor 62 is used to execute 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 the specific implementation of each step of the method and the related explanation content, please refer to the above embodiments, and the repetition will not be repeated here.

[0120] For example, the processor 62 and the memory 61 may communicate with each other directly or indirectly. For example, the processor 62 and the memory 61 may communicate with each other through a network. The network may 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 may also communicate with each other through a system bus, which is not limited by the present disclosure.

[0121] For example, the processor 62 may be embodied as various appropriate processors, processing devices, etc., such as a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The central processing unit (CPU) may be an X86 or ARM architecture, etc. For example, the memory 61 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The memory 61 may include, for example, a system memory, which may store, for example, an operating system, an application, a boot loader (Boot Loader), a database, and other programs. Various applications and various data may also be stored in the storage medium.

[0122] 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 be transmitted from a storage medium or a network to a computer system having a dedicated hardware structure, such as Figure 7 The computer system (or electronic device) 70 shown is installed with the programs constituting the software, and when the various programs are installed, the computer system can execute various functions, including the functions described above. Figure 7 is a block diagram showing an example structure of a computer system that can be employed in an embodiment according to the present disclosure.

[0123] exist Figure 7 In the embodiment, a central processing unit (CPU) 701 performs various processes according to 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 performs various processes, etc., is also stored as needed. The central processing unit is merely exemplary, and it may also be other types of processors, such as the various processors described above. The ROM 702, the RAM 703, and the storage section 708 may be various forms of computer-readable storage media, as described below. It should be noted that although Figure 7 ROM 702, RAM 703 and storage section 708 are shown separately in FIG. 7 , but one or more of them may be combined or located in the same or different memory or storage modules.

[0124] The CPU 701, the ROM 702, and the RAM 703 are connected to one another via a bus 704. An input / output interface 705 is also connected to the bus 704.

[0125] The following components are connected to the input / output interface 705: an input portion 706, such as a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output portion 707, including a display, such as a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage portion 708, including a hard disk, a magnetic tape, etc.; and a communication portion 709, including a network interface card such as a LAN card, a modem, etc. The communication portion 709 allows communication processing to be performed via a network such as the Internet. It is easy to understand that although Figure 7 The various devices or modules in the computer system 70 are shown to communicate via a bus 704, but they may also communicate via a network or other means, wherein the network may include a wireless network, a wired network, and / or any combination of wireless networks and wired networks.

[0126] A drive 710 is also connected to the input / output interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like is mounted on the drive 710 as needed so that a computer program read therefrom is installed into the storage section 708 as needed.

[0127] In the case where the above-described series of processing is implemented by software, a program constituting the software can be installed from a network such as the Internet or a storage medium such as the removable medium 711 .

[0128] According to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, or installed from the storage part 708, or installed from the ROM 702. When the computer program is executed by the CPU 701, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0129] It should be noted that in the context of the present disclosure, a computer-readable medium may be a tangible medium that may contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. A computer-readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by an instruction execution system, device or device or used in combination with it. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0130] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0131] In some embodiments, a computer program is further provided, comprising: instructions, which, when executed by a processor, cause the processor to execute any of the methods in the above embodiments. For example, the instructions may be embodied as computer program codes.

[0132] In embodiments of the present disclosure, computer program codes for performing the operations of the present disclosure may be written in one or more programming languages ​​or combinations thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In situations involving a remote computer, the remote computer may be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet).

[0133] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0134] The modules, components or units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the names of the modules, components or units do not, in some cases, limit the modules, components or units themselves.

[0135] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0136] According to some embodiments of the present disclosure, a content generation method is provided, comprising: displaying generation instructions input by a user in an interaction interface between a user and an intelligent agent, wherein the generation instructions include description information of a target content; displaying one or more pieces of creative information in the interaction interface according to the generation instructions, wherein the one or more pieces of creative information are generated based on a semantic understanding of the description information of the target content; in response to a user's selection operation of target creative information in the one or more pieces of creative information, calling one or more intelligent tools according to the types of the target creative information and the target content to generate the target content; and displaying the target content in the interaction interface.

[0137] In some embodiments, according to the generation instruction, displaying one or more creative information in the interactive interface includes: semantically understanding the description information of the target content to determine the subject information and type of the target content; based on the subject information and type of the target content, generating one or more creative information associated with the subject information and matching the type, wherein different creative information includes different feature description information of the target content; and displaying one or more creative information in the interactive interface.

[0138] In some embodiments, displaying one or more pieces of creative information in an interactive interface according to a generation instruction includes: determining whether there is historical generation content related to the generation instruction in historical interaction information before the generation instruction; in response to the existence of historical generation content related to the generation instruction, displaying one or more pieces of creative information in the interactive interface according to the generation instruction and the historical generation content.

[0139] In some embodiments, determining whether there is historical generated content related to the generation instruction includes: semantically understanding the description information of the target content to determine the subject information of the target content; determining the subject 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 based on the subject information of one or more historical generated content and the subject information of the target content.

[0140] In some embodiments, displaying one or more pieces of creative information in an interactive interface based on generation instructions and historically generated content includes: generating one or more pieces of creative information based on subject information and type of target content and creative information of historically generated content, wherein the one or more pieces of creative information are associated with the subject information of the target content and the creative information of historically generated content, and match the type; and displaying one or more pieces of creative information in the interactive interface.

[0141] In some embodiments, displaying one or more creative information in an interactive interface according to a generation instruction includes: semantically understanding the generation instruction to determine one or more intelligent tools; calling a first intelligent tool among the one or more intelligent tools to generate one or more creative information according to the generation instruction; receiving one or more creative information returned by the first intelligent tool; and displaying one or more creative information in the interactive interface.

[0142] In some embodiments, displaying one or more creative information in an interactive interface according to a generation instruction includes: semantically understanding 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 one or more creative information according to the generation instruction; receiving one or more creative information returned by the second intelligent tool; and displaying one or more creative information in the interactive interface.

[0143] In some embodiments, calling one or more intelligent tools to generate target content based on target creative information and the type of target content includes: determining one or more intelligent tools and the execution order of the one or more intelligent tools based on the target creative information, the type of target content and the function of each of the multiple intelligent tools; calling one or more intelligent tools to generate target content based on the execution order of the one or more intelligent tools and the target creative information.

[0144] In some embodiments, calling one or more smart tools to generate target content includes: generating prompt information for one or more smart tools according to the execution order and target creative information of the one or more smart tools; inputting the prompt information into the one or more smart tools, and having one or more machine learning models corresponding to the one or more smart tools generate the target content according to the prompt information.

[0145] In some embodiments, one or more smart tools are multiple smart tools, and generating prompt information for one or more smart tools according to the execution order of the one or more smart tools and target creative information includes: dividing the target creative information into creative information corresponding to each smart tool in the multiple smart tools according to the functions of the multiple smart tools and the execution order of the one or more smart tools; generating prompt information for each smart tool according to the creative information corresponding to each smart tool.

[0146] In some embodiments, prompt information is input into one or more intelligent tools, and one or more machine learning models corresponding to the one or more intelligent tools generate target content according to the prompt information, including: inputting prompt information of each intelligent tool 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 and the execution order of each intelligent tool.

[0147] In some embodiments, the content generation method further includes: before calling one or more intelligent tools to generate the target content based on the target creative information and the type of the target content, updating the target creative information in response to a user's modification operation on the target creative information; and / or updating the target content in response to a user's modification operation on the target content.

[0148] In some embodiments, the content generation method also includes: displaying a feedback control corresponding to the target content in an interactive interface, and obtaining feedback information corresponding to the feedback control in response to a user triggering the feedback control, wherein the feedback control includes at least one of a positive feedback control and a negative feedback control; and / or displaying a regeneration control corresponding to the target content in the interactive interface, and in response to a user triggering the regeneration control, calling one or more intelligent tools according to the target creative information and the type of the target content to regenerate and display the target content.

[0149] In some embodiments, in response to the target content including an image, one or more creative information includes description information of the picture features of the image; and / or in response to the target content including music, one or more creative information includes description information of at least one feature of the music's style, keywords, and lyrics.

[0150] In some embodiments, the selection operation on target creative information among the one or more creative information includes: a selection operation on an item of the target creative information, a trigger operation on a control corresponding to the target creative information, or inputting indication information indicating the selection of the target creative information.

[0151] According to some other embodiments of the present disclosure, a content generation device 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 intelligent agent, wherein the generation instruction includes description information of a 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 based on a semantic understanding of the description information of the target content; a generation module, configured to generate a target content by calling one or more intelligent tools according to the types of the target creative information and the target content in response to a user's selection operation of a target creative information in the one or more creative information; and a third display module, configured to display the target content in the interaction interface.

[0152] According to some further embodiments of the present disclosure, an electronic device is provided, including: a processor; and a memory coupled to the processor, for storing instructions, which, when executed by the processor, causes the processor to execute the content generation method of any embodiment of the present disclosure.

[0153] According to some further embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the content generating method of any embodiment of the present disclosure is executed.

[0154] According to some further embodiments of the present disclosure, a computer program product is provided, including: instructions, which implement the content generating method of any embodiment of the present disclosure when the instructions are executed by a processor.

[0155] According to some further embodiments of the present disclosure, a computer program is provided, comprising: instructions, which implement the content generating method of any embodiment of the present disclosure when the instructions are executed by a processor.

[0156] The above descriptions are only some embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but 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, a technical solution formed by replacing the above features with the technical features with similar functions disclosed in the present disclosure (but not limited to).

[0157] In the description provided herein, many specific details are set forth. However, it is understood that embodiments of the present invention can be implemented without these specific details. In other cases, well-known methods, structures, and techniques are not presented in detail in order not to obscure the understanding of the description.

[0158] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0159] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A content generation method, comprising: In the interaction interface between the user and the agent, displaying the generation instruction input by the user, wherein the generation instruction includes description information of the target content; According to the generating instruction, displaying one or more pieces of creative information in the interactive interface includes: semantically understanding the description information of the target content, determining the subject information and type of the target content, and generating the one or more pieces of creative information associated with the subject information and matching the type according to the subject information and type of the target content, wherein different creative information includes different feature description information of the target content, and the one or more pieces of creative information include keywords related to the type of the target content; in response to the user's selection operation of the target creative information in the one or more pieces of creative information, and in response to the user's modification operation of the target creative information, updating the target creative information; Invoke one or more intelligent tools to generate the target content according to the target creative information and the type of the target content; The target content is displayed in the interactive interface.

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

3. The content generation method according to claim 2, wherein: The determining whether there is historical generated content related to the generation instruction comprises: Performing semantic understanding on the description information of the target content to determine the subject information of the target content; Determine subject information of one or more historical generated contents in the historical interaction information; It is determined whether there is any historical generated content related to the generation instruction according to the subject information of the one or more historical generated contents and the subject information of the target content.

4. The content generation method according to claim 3, wherein: The displaying one or more creative information in the interactive interface according to the generation instruction and the historical generation content includes: generating the one or more pieces of creative information according to the subject information and type of the target content and the creative information of the historically generated content, wherein the one or more pieces of creative information are associated with the subject information of the target content and the creative information of the historically generated content and match the type; One or more creative information are displayed in the interactive interface.

5. The content generation method according to claim 1, wherein: The displaying one or more creative information in the interactive interface according to the generating instruction includes: Performing semantic understanding on the generation instruction to determine the one or more intelligent tools; Invoking a first intelligent tool among the one or more intelligent tools to generate the one or more creative information according to the generating instruction; receiving the one or more pieces of creative information returned by the first smart tool; One or more creative information are displayed in the interactive interface.

6. The content generation method according to claim 1, wherein: The displaying one or more creative information in the interactive interface according to the generating instruction includes: 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 creative information according to the generation instruction; receiving the one or more pieces of creative information returned by the second smart tool; One or more creative information are displayed in the interactive interface.

7. The content generation method according to claim 1, 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 smart tools and the execution order of the one or more smart tools according to the target creative information, the type of the target content, and the function of each smart tool in the plurality of smart tools; According to the execution order of the one or more intelligent tools and the target creative information, one or more intelligent tools are called to generate the target content.

8. The content generation method according to claim 7, wherein: The step of calling one or more intelligent tools according to the execution order of the one or more intelligent tools and the target creative information to generate the target content 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 creative information; The prompt information is input into the one or more intelligent tools, and one or more machine learning models corresponding to the one or more intelligent tools generate the target content according to the prompt information.

9. The content generation method according to claim 8, wherein: The one or more intelligent tools are a plurality of intelligent tools, and 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 includes: According to the functions of the multiple smart tools and the execution order of the one or more smart tools, dividing the target creative information into creative information corresponding to each smart tool in the multiple smart tools; Prompt information for each smart tool is generated according to the creative information corresponding to each smart tool.

10. The content generation method according to claim 8, wherein: The inputting the prompt information into the one or more intelligent tools, and using one or more machine learning models corresponding to the one or more intelligent tools to generate the target content according to the prompt information comprises: The prompt information of each smart tool is input into each smart tool, and the machine learning model corresponding to each smart tool generates the part of the target content generated by each smart tool according to the prompt information of each smart tool and the execution order of each smart tool.

11. The content generation method according to any one of claims 1 to 10, further comprising: In response to the user's modification operation on the target content, the target content is updated.

12. The content generation method according to any one of claims 1 to 10, further comprising: Displaying a feedback control corresponding to the target content in the interactive interface, and acquiring feedback information corresponding to the feedback control in response to a triggering operation of the feedback control by the user, wherein the feedback control includes at least one of a positive feedback control and a negative feedback control; and / or A regeneration control corresponding to the target content is displayed in the interactive interface, and in response to the user's triggering operation on the regeneration control, the one or more intelligent tools are called according to the target creative information and the type of the target content to regenerate and display the target content.

13. The content generation method according to any one of claims 1 to 10, wherein: In response to the target content including an image, the one or more creative information includes 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 the music: style, keywords, and lyrics.

14. The content generation method according to any one of claims 1 to 10, wherein: The selection operation on the target creative information among the one or more creative information includes: 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.

15. A content generating device, comprising: A first display module is configured to display the generation instruction input by the user in an interaction interface between the user and the agent, wherein the generation instruction includes description information of the target content; The second display module is configured to display one or more creative information in the interactive interface according to the generating instruction, including: semantically understanding the description information of the target content, determining the subject information and type of the target content, and generating the one or more creative information associated with the subject information and matching the type according to the subject information and type of the target content, wherein different creative information includes different feature description information of the target content, and the one or more creative information includes keywords related to the type of the target content; A first modification module is configured to update the target creative information in response to the user's selection operation on the target creative information among the one or more creative information and in response to the user's modification operation on the target creative information; A generating module, configured to call one or more intelligent tools to generate the target content according to the target creative information and the type of the target content; The third display module is configured to display the target content in the interactive interface.

16. An electronic device comprising: processor; as well as A memory coupled to the processor, for storing instructions, wherein when the instructions are executed by the processor, the processor executes the content generation method according to any one of claims 1 to 14.

17. A computer-readable storage medium having a computer program stored thereon, wherein: When the program is executed by a processor, the content generating method according to any one of claims 1 to 14 is implemented.

18. A computer program product comprising instructions, which, when executed by a processor, cause the processor to perform the content generation method according to any one of claims 1 to 14.

Images