Method and apparatus for content creation

Abstract

Embodiments of the present disclosure provide a method and apparatus for content creation, an electronic device, a medium, and a computer program product. The method comprises: during an editing operation performed by a user within a target application, displaying an interface element of a content creation tool for interacting with a generative model; on the basis of a user prompt word received on the interface element, acquiring answer content generated by the generative model; and inserting the answer content into the target application. In this way, the convenience and efficiency of users using AI tools to create content are significantly improved.

Description

Method and apparatus for content creation TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of computer, and more particularly, to a method, apparatus, electronic device, medium and computer program product for content creation. BACKGROUND

[0002] Artificial intelligence generated content (AIGC) refers to any content created or generated by an artificial intelligence system under the guidance of a human or in the case of participation. With the advancement of natural language processing (NLP), machine learning and deep learning algorithms, artificial intelligence is now able to generate various types of content, including text, images, videos, music, etc.

[0003] SUMMARY

[0004] To implement AI-assisted content creation, a user usually accesses an AI system with a generative model (e.g., via a browser or using a dedicated application). The user obtains answer content by asking questions to the AI system to help him / her with content creation. The inconvenience of this approach is that the user needs to switch back and forth between the browser or application that provides the answer content and the editing application in which he / she is creating content, e.g., copying the answer content into the editing application to complete the creation, or copying a piece of text from the editing application to ask questions to the AI system.

[0005] In view of this, a method, apparatus, electronic device, computer-readable storage medium and program product for content creation are provided, which can help users more conveniently interact with AI systems to help them with content creation.

[0006] According to a first aspect of the present disclosure, a method for content creation is provided, comprising displaying, during a user performing an editing operation in a target application, an interface element of a content creation tool for interacting with a generative model; obtaining answer content generated by the generative model based on a user prompt word received on the interface element; and inserting the answer content into the target application.

[0007] According to a second aspect of the present disclosure, an apparatus for content creation is provided, comprising a display unit configured to display, during a user performing an editing operation in a target application, an interface element of a content creation tool for interacting with a generative model; a content obtaining unit configured to obtain answer content generated by the generative model based on a user prompt word received on the interface element; and a content inserting unit configured to insert the answer content into the target application.

[0008] According to a third aspect of the present disclosure, there is provided an electronic device comprising: one or more processors; and memory storing one or more programs for execution by the one or more processors, which, when executed by the one or more processors, cause the one or more processors to implement the method according to the first aspect of the present disclosure.

[0009] According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method according to the first aspect of the present disclosure.

[0010] According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method according to the first aspect of the present disclosure.

[0011] The summary is provided to introduce a selection of concepts, in a simplified form, that are further described below in the DETAILED DESCRIPTION. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. BRIEF DESCRIPTION OF DRAWINGS

[0012] The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which like reference characters refer to like parts throughout the figures, and in which:

[0013] FIG. 1 shows a block diagram of a computing device capable of implementing multiple implementations of the present disclosure;

[0014] FIG. 2 shows a schematic flowchart of a method for content authoring according to an embodiment of the present disclosure;

[0015] FIGS. 3A to 3C show exemplary user interface diagrams for content authoring using a content authoring tool according to an embodiment of the present disclosure;

[0016] FIGS. 4A to 4I show exemplary user interface diagrams for content authoring using a content authoring tool according to an embodiment of the present disclosure; and

[0017] FIG. 5 shows a schematic block diagram of an apparatus for content authoring according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type of personal information involved in the present disclosure, the range of use, the scenario of use, etc. should be informed to the user and the authorization of the user should be obtained in a proper manner according to relevant laws and regulations.

[0019] The present disclosure will now be discussed with reference to several example implementations. It should be appreciated that these implementations are discussed solely for the purposes of exemplifying the present disclosure and to enable those of ordinary skill in the art to better understand and practice the present disclosure, and are not intended to limit the scope of the present disclosure in any way.

[0020] As used herein, the term "includes" and its variants are to be read to be synonymous with "including, but not limited to." The term "based on" is to be interpreted as "based, at least in part, on." The terms "one implementation" and "an implementation" are to be interpreted to mean "at least one implementation." The term "another implementation" is to be interpreted to mean "at least one other implementation." The terms "first," "second," etc. can refer to different or the same objects. Other explicit or implicit definitions can also be included below. It should be noted that any numerical values or numbers used in the present disclosure are exemplary and in no way limit the scope of the present disclosure.

[0021] Traditionally, to implement AI-assisted content creation, a user accesses an AI system through a browser or using a dedicated AI application. The user provides a prompt to the AI system, requesting the AI system to generate an answer to help the user with content creation. The user usually creates content in a specific editing application, for which, the user needs to switch back and forth between the browser or AI application and the editing application, e.g., copying the answer into the editing application to complete the creation, or copying a piece of text from the editing application to ask the AI system. On the other hand, the user can expect to get different styles of answers in different editing applications, which requires the user to write more complex prompts to the AI system. These issues bring much inconvenience to the user when using the AI system for content creation.

[0022] In view of this, embodiments of the present disclosure provide a content creation tool that interacts with an AI model and can be used across multiple editing applications, which is deployed in the operating system and associated with multiple editing applications. When the user performs an editing operation in a given editing application, the content creation tool can be activated and displayed (e.g., in the form of a floating window on top of the current editing application). After receiving a prompt input by the user in the tool, the answer generated by the AI model is obtained and presented to the user. The user can confirm the insertion of the content (e.g., clicking or touching a control on the floating window) in the content creation tool, so as to insert the content generated by the AI model into the current editing application as a whole.

[0023] The implementation details of the embodiments of the present disclosure are described in detail below with reference to FIGS. 1-5.

[0024] FIG. 1 illustrates a block diagram of a computing device 100 that can implement a number of implementations of the present disclosure. It should be understood that the computing device 100 illustrated in FIG. 1 is merely exemplary and should not be construed as limiting the functionality and scope of the implementations described herein. As shown in FIG. 1, components of the computing device 100 can include, but are not limited to, one or more processors or processing units 110, a memory 120, a storage device 130, one or more communication units 140, one or more input devices 150, and one or more output devices 160.

[0025] In some implementations, the computing device 100 can be implemented as various user terminals with computing capabilities. A user terminal such as any type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, station, unit, device, multimedia computer, multimedia tablet, Internet node, communicator, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, personal communication system (PCS) device, personal navigation device, personal digital assistants (PDAs), audio / video player, digital camera / camcorder, positioning device, television receiver, radio broadcast receiver, electronic book device, game device, or any combinations thereof, including accessories and peripherals of such devices, or any combinations thereof. It is also contemplated that the computing device 100 can support any type of interface to the user (such as "wearable" circuitry, etc.).

[0026] The processing unit 110 can be a real or virtual processor and capable of performing various processing according to programs stored in the memory 120. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of the computing device 100. The processing unit 110 can also be referred to as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor, a controller, a microcontroller.

[0027] The computing device 100 typically includes a plurality of computer storage media. Such media can be any available media that is accessible by the computing device 100 and includes both volatile and non-volatile media, removable and non-removable media. The memory 120 can be a volatile memory (e.g., register, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory), or some combination thereof. The memory 120 can include a content authoring tool 122 implemented as a program module, which can be configured to perform the content authoring methods described herein or implement the corresponding content authoring apparatus. The content authoring tool 122 can be accessed and run by the processing unit 110 to implement the corresponding functions.

[0028] The storage device 130 can be a removable or non-removable, volatile or non-volatile memory and can include a machine-readable medium that is used to store information and / or data and that is accessible by the computing device 100. The computing device 100 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 1, a disk drive and a disk controller that are used to read from and write to a removable, non-removable, volatile, or non-volatile disk can be provided. In these cases, each drive can be connected to the bus (not shown) by one or more data media interfaces.

[0029] The communication unit 140 enables communication with another computing device over a communication medium. Additionally, the functionality of the components of the computing device 100 can be implemented in a single computing cluster or multiple computing machines that are able to communicate over a communication connection. Thus, the computing device 100 can operate in a networked environment using logical connections to one or more other servers, personal computers (PCs), or another general network node.

[0030] The input device 150 can be one or more various input devices such as a mouse, a keyboard, a trackball, a voice input device, etc. The output device 160 can be one or more output devices such as a display, a speaker, a printer, etc. The computing device 100 can also communicate with one or more external devices (not shown) such as a storage device, a display device, etc. through the communication unit 140, as needed, a device that enables a user to interact with the computing device 100, or any device (e.g., a network card, a modem, etc.) that enables the computing device 100 to communicate with one or more other computing devices. Such communication can be enabled by an input / output (I / O) interface (not shown).

[0031] In some implementations, some or all of the components of computing device 100 can be provided in the form of a cloud computing architecture, in addition to being integrated on a single device. In a cloud computing architecture, the components can be arranged remotely and can work together to implement the functionality described in this disclosure. In some implementations, cloud computing provides computation, software, data access, and storage services that do not require end-user knowledge of the physical location or configuration of the system that delivers the services. In various implementations, cloud computing delivers services through a broad area network, such as the Internet, using appropriate protocols. For instance, cloud computing providers deliver applications through a web browser or any other computing component. The software or components of the cloud computing architecture, and the corresponding data, can be stored on servers at remote locations. Computing resources in a cloud computing environment can be consolidated at a remote data center location or they can be dispersed. Cloud computing infrastructures can provide services through shared data centers, even though they appear as a single point of access for the user. Thus, the components and functionality described herein can be provided from a service provider at a remote location using a cloud computing architecture. Alternatively, they can be provided from a traditional server, or they can be installed directly or otherwise on a client device.

[0032] With content authoring tool 122, computing device 100 can assist a user in content authoring according to various implementations of the disclosure. Content authoring tool 122 can be implemented at a level of an operating system of computing device 100 and associated to different editing applications, including but not limited to a text editing application, a graphic application, a video application, etc., such that it can be invoked within these editing applications. Content authoring tool 122 can be configured to provide interaction with an AI system having a generative model, e.g., providing a user inputted prompt 170 to the AI system, obtaining an AI system generated answer content. Content authoring tool 122 can also be configured to provide interaction with a user, e.g., receiving user input (e.g., prompt), presenting AI system generated answer content 180 to the user, and receiving user indication to insert the answer content into a current editing application, etc. In some implementations, content authoring tool 122 can also provide an interface for user to edit or modify the AI generated content. It is noted that the AI system can be implemented in the cloud (e.g., a server or a cluster), such that content authoring tool 122 of computing device 100 accesses the AI system via a network. In some implementations, some AI systems can also be implemented locally on computing device 100.

[0033] FIG. 2 illustrates a schematic flowchart of a method 200 for content authoring according to an embodiment of the present disclosure. The method 200 can be implemented by, for example, the computing device 100 shown in FIG. 1. More specifically, the method 200 can be implemented by the content authoring tool 122 of FIG. 1. It should be understood that the method 200 can also include additional actions not shown and / or can omit actions shown, and the scope of the present disclosure is not limited in this regard. For ease of description, the method 200 is described with reference to the interface diagrams shown in FIGS. 3A-3F.

[0034] As shown in FIG. 2, at block 210, interface elements of a content authoring tool for interacting with a generative model are displayed during a user’s performance of an editing operation within a target application. In this context, a generative model is a type of machine learning model that generates new instances of data based on a probability distribution of training data, including but not limited to text, images, videos, audio, or music, etc. The target application is any application that can have editing functionality, such as a text editing application, a graphic application, a video or audio application, etc., and the editing operation can include authoring textual content, audio content, video content, image content, etc. Details of embodiments of the present disclosure are set forth below with respect to authoring textual content as an example, but it should be understood that embodiments of the present disclosure are also applicable to other types of authoring.

[0035] The content authoring tool can be deployed at the level of an operating system and associated with multiple applications installed within the operating system. For example, the content authoring tool can be associated to applications that have editing authoring capabilities in a user-manual or pre-configured manner. As such, the content authoring tool can be invoked or enabled when the user is authoring content in these applications. In some embodiments, the user can also manually set the application scope of the content authoring tool, for example, to limit its use in a certain application or applications, or to globally stop using the content authoring tool.

[0036] FIG. 3A illustrates an example interface 300 of a target application that is currently being used by a user. As shown, the interface 300 includes a toolbar region 301 and an editing region 302 of the target application. It can be appreciated that the interface 300 shown in FIG. 3A is merely exemplary, and the interface of the target application can be different therefrom, for example, does not necessarily include the toolbar region 301, or can include more interface elements.

[0037] When the user intends to input content (e.g., text, image, video, audio, etc.) in the target application, interface elements 303 of the content authoring tool are displayed. The interface elements 303 at least include an input box for inputting a prompt word. The user can input a prompt word in the input box, desiring to author content with the help of a generative model. In some embodiments, when the user selects existing content within the target application, it indicates that the user can wish to generate information associated with the selected content, and the interface elements 303 of the content authoring tool can be displayed.

[0038] At block 220, based on the user prompt entered on the interface element, the answer content generated by the generative model is obtained. As shown in FIG. 3B, the user can enter the prompt 304 and select “Submit”, and the prompt in the input box will be provided to the generative model, and the answer content generated by the generative model.

[0039] The content creation tool provides the prompt to the generative model, for example, sends to the cluster or agent running the generative model via the network. The generative model can generate the answer content based on the prompt. In some embodiments, the generative model can also generate the answer content in combination with the user’s context or historical information. Then, the generative model provides the answer content to the content creation tool.

[0040] At block 230, the answer content is inserted into the target application. As shown in FIG. 3C, the answer content 305 is inserted into the editing area 302 of the target application. In some embodiments, the answer content 305 can be directly inserted into the target application, i.e., without the need for other operations after the user submits the prompt, the answer content 305 is directly inserted into the target application. In some embodiments, the user can give an insertion indication to manually insert the answer content into the target application. In some embodiments, the answer content can be displayed in an interface element or other window, so that the user can preview the answer content and edit as needed. Then, the user can give an insertion indication, for example, click or touch the insertion button on the indication interface, to insert the answer content into the target application. In some embodiments, the answer content can be inserted into the comment box of the target application. For example, when the content creation tool is triggered by selecting the existing content, the answer content can be inserted into the comment box corresponding to the selected content.

[0041] More embodiments of the present disclosure are described below in connection with exemplary user interface diagrams shown in FIGS. 4A-4I. As shown in FIG. 4A, the interface 400 includes a toolbar area 401 and an editing area 402 of the target application. It can be understood that the interface 300 shown in FIG. 3A is only exemplary, and the interface of the target application can be different from this, for example, does not necessarily include the toolbar area 301, or can include more interface elements.

[0042] In some embodiments, if the user is intending to input textual content or media content within the target application, an icon or toolbar for invoking the content creation tool can be displayed. For example, in response to the user activating an input box in the target application, an icon 410 for invoking the content creation tool is displayed for the user to select to trigger the use. Alternatively, the content creation tool can be loaded into the toolbar 401 for the user to manually select to trigger the use. Additionally or alternatively, if the user selects text or media content within the target application, it can mean that the user can want to query or generate related content, at which time the icon or toolbar 410 for invoking the content creation tool can also be displayed.

[0043] In response to the user selecting the icon 410, one or more functional menu items of the content creation tool are displayed. As shown in FIG. 4B, when the user clicks, touches, or hovers the cursor over the icon 410, the menu items 420 of “Help me write” or “Live translation” are displayed. “Help me write” means to use the generative model to generate the created content, for example, the user requests the model to generate more information on a certain topic, and “Live translation” means to use the generative model to generate the corresponding translation content as the user inputs text within the target application. Exemplary “Help me write” functions will be described below with reference to FIGS. 4C-4H, and exemplary “Live translation” functions will be described with reference to FIG. 3F. It can be understood that the content creation tool can have more functions, without being limited thereto.

[0044] If the user selects either of the “Help me write” function or the “Live translation”, interface elements of the content creation tool can be displayed, which can be displayed in the form of a suspended window above the layer of the target application. FIG. 4C shows the interface elements 430 after the user selects the “Help me write” function, which includes an input area 432 and a template recommendation area 433.

[0045] In some embodiments, a prompt word template can be used to generate a prompt word provided to the model. Specifically, a prompt word template to be used can be determined, and the user prompt word is added to the prompt word template to obtain a prompt word for the generative model. Then, by providing the obtained prompt word to the generative model, the answer content generated by the generative model is obtained. In this way, the user does not need to manually input the entire prompt word, but only needs to input the desired topic in the partially completed template. In this way, on the one hand, the amount of user input can be reduced, and on the other hand, using the prompt word template can have the content obtained more in line with the user’s expectations.

[0046] As mentioned above, the content creation tool can be associated with multiple editing applications, and different types of editing applications can have different characteristics of creating content. In some embodiments, multiple recommended prompt templates 434 can be displayed, each of which is associated with an editing application. As shown in FIG. 4C, template 1 associated with application 1, template 2 associated with application 2, and template 3 associated with application 3 are shown on interface element 430. The user can select one of the templates to use.

[0047] In some embodiments, the prompt template recommended for use can also be determined according to the category label of the target application currently being used. Each category label can be mapped to one or more prompt templates. For example, the template of an office application can be a template for generating table content, the template of a picture-text application can be a template for generating a combination of pictures and text, and so on. In some implementations, the category label can be divided into several levels, i.e., a first-level label, a second-level label, and so on, and each level of label is mapped to one or more templates.

[0048] Referring to FIG. 4D, in response to the user manually selecting template 1 or the content creation tool automatically selecting template 1 associated with the current target application (i.e., application 1), the fixed prompt of the template is automatically filled in the input area 432. As shown in FIG. 4D, the content of template 1 is: “Help me write a video script about

topic

topic

[0049] FIG. 4E shows the interface of submitting the prompt and obtaining the answer content, including the input area 432, which prompts the user whether to continue creating, the content area 440, which shows the answer content generated by the generative model, and the operation area, including “Insert” 442, “Copy”, “Regenerate”, “Adjust”, etc.

[0050] When the user clicks or touches “Insert” 442, the answer content in the content area 340 will be completely inserted into the target application. In some embodiments, the user can also click or touch “Adjust” to edit the answer content, and then click “Insert” to insert the edited content into the target application. In some embodiments, the answer content can be inserted into the editable area of the target application. As shown in FIG. 4F, the content 450 generated by the model is inserted into the editable area 402 of the target application. Alternatively, when the user triggers the content creation tool by selecting existing content, the answer content can also be inserted into the comment box corresponding to the content.

[0051] In some embodiments, the display position of the answer content can also be determined according to whether the target application has the ability to edit the generated answer content, that is, directly inserted into the target application or displayed in a floating window. If the target application has the ability to edit the answer content, the answer content can be directly inserted into the target application; if the target application does not have the ability to edit the answer content, the answer content is displayed in a floating window. Taking an image format as an example, if the current application has image editing capability, and the generated content includes an image, the generated content can be directly displayed because the user can directly edit within the current application. As shown in FIG. 4G, the image 460 generated by the model is directly inserted into the target application. If the current application is a consumer application and may not have editing capabilities, a floating window needs to be displayed first for the user to make secondary modifications and edits, etc., and then displayed in the interface of the current application. As shown in FIG. 4H, the image 460 generated by the model is displayed in the floating window 470, which also includes controls 462 for inserting the image into the target application and controls 464 for editing the image, etc. The floating window 470 can be embedded in the interface element 430 of the content creation tool, or it can be a separate floating window.

[0052] FIG. 4I shows an interface diagram for real-time content creation using a generative model according to embodiments of the present disclosure. For example, when the user selects the “real-time translation” menu item in the interface shown in FIG. 4B, the interface element of the content creation tool is presented as shown in FIG. 4I. In this case, the answer content generated by the generative model can be displayed in the content area 490 of the interface element 430 in real time based on the user input 480 (i.e., the prompt word) in the target application. It can be understood that the “real-time translation” menu item corresponds to a hidden prompt word template, which triggers the generative model to provide real-time translation content for the user input 480.

[0053] FIG. 5 shows a schematic block diagram of an apparatus 500 for content creation according to embodiments of the present disclosure. The apparatus 500 can be implemented by the computing device 100 shown in FIG. 1. As shown in FIG. 5, the apparatus 500 includes a display unit 510, a content obtaining unit 520, and a content inserting unit 530.

[0054] The display unit 510 is configured to display an interface element of a content creation tool for interacting with a generative model during editing operations performed by a user in a target application. The content obtaining unit 520 is configured to obtain answer content generated by a generative model based on a user prompt word received on the interface element. The content inserting unit 530 is configured to insert the answer content into the target application.

[0055] It should be noted that more actions or steps described with reference to FIGS. 1-4I can be implemented by the apparatus 500 shown in FIG. 5. For example, the apparatus 500 can include more modules or units to implement the actions or steps described above, or some units or modules shown in FIG. 5 can be further configured to implement the actions or steps described above. No further elaboration is made here.

[0056] The above describes the technical solutions of embodiments of the present disclosure for using generative models to help users with content creation with reference to FIGS. 1-5. Compared with traditional methods, the proposed technical solutions have the advantage that users can at any time invoke the window of the content creation tool in various editing applications of the operating system, and conveniently insert the content generated by the model into the editing application with the help of the tool. In some embodiments, a creation template is automatically recommended in the window according to the current editing application of the user, and after the user selects a suitable creation template or directly describes the content to be created, the creation content is generated by the generative model, and the user can one-click insert into the application. In this way, the convenience and efficiency of users using AI tools for content creation are significantly improved.

[0057] Some example implementations of the present disclosure are listed below.

[0058] In a first aspect, a method for content creation is provided. The method includes: displaying an interface element of a content creation tool for interacting with a generative model during a user performs an editing operation in a target application; obtaining answer content generated by the generative model based on a user prompt word received on the interface element; and inserting the answer content into the target application.

[0059] In some embodiments, the content creation tool is deployed at a level of an operating system, and the operating system is installed with a plurality of applications, and the content creation tool is callable in the plurality of applications.

[0060] In some embodiments, obtaining the answer content generated by the generative model includes: determining a prompt word template to be used; adding the user prompt word to the prompt word template to obtain a prompt word for the generative model; and obtaining the answer content generated by the generative model by providing the prompt word to the generative model.

[0061] In some embodiments, determining the prompt word template to be used includes: determining, based on a category label of the target application, a prompt word template associated with the category label as a recommended prompt word template to be used.

[0062] In some embodiments, determining the prompt word template to be used includes: displaying a plurality of prompt word templates, the plurality of prompt word templates including prompt word templates respectively associated with a plurality of target applications; and determining one of the plurality of prompt word templates as the prompt word template to be used based on a user selection.

[0063] In some embodiments, displaying the interface element of the content creation tool for interacting with the generative model includes: in response to the user intending to input text or media content within a target application, or in response to the user selecting text or media content within the target application, displaying an icon or toolbar for invoking the content creation tool; and based on a user input to the icon or toolbar, displaying the interface element, the interface element including a flyout window.

[0064] In some embodiments, the interface element includes at least one of: an input area for inputting a prompt word; a content area for displaying the answer content generated by the generative model; a toolbar for editing the answer content; and a control for causing the answer content to be inserted into the target application as a whole.

[0065] In some embodiments, inserting the answer content into the target application further includes: determining whether the target application has an ability to edit the answer content; in response to determining that the target application has the ability to edit the answer content, inserting the answer content directly into the target application; and in response to determining that the target application does not have the ability to edit the answer content, displaying the answer content in a floating window.

[0066] In some embodiments, obtaining the answer content generated by the generative model includes: displaying the answer content in the content area in real time based on a user input within the target application.

[0067] In some embodiments, inserting the answer content into the target application includes: in response to receiving an insertion indication, inserting the answer content into the target application, or in response to obtaining the answer content, inserting the answer content directly into the target application.

[0068] In some embodiments, inserting the answer content into the target application includes: inserting the answer content into an editable area or a comment box of the target application.

[0069] In some embodiments, the method further includes: limiting the use of the content creation tool in the target application or operating system.

[0070] In a second aspect, an apparatus for content creation is provided. The apparatus includes a display unit configured to display, during a user performing an editing operation within a target application, an interface element of a content creation tool for interacting with a generative model; a content obtaining unit configured to obtain, based on a user prompt received on the interface element, answer content generated by the generative model; and a content inserting unit configured to insert the answer content to the target application.

[0071] In a third aspect, an electronic device is provided. The electronic device includes at least one processor; at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions, when executed by the at least one processor, cause the electronic device to: display, during a user performing an editing operation within a target application, an interface element of a content creation tool for interacting with a generative model; obtain, based on a user prompt received on the interface element, answer content generated by the generative model; and insert the answer content to the target application.

[0072] In a fourth aspect, the present disclosure provides a computer-readable storage medium comprising machine executable instructions that, when executed by a device, cause the device to perform the method of the first aspect described above.

[0073] In a fifth aspect, the present disclosure provides a computer program product tangibly stored in a non-transitory computer storage medium and comprising machine executable instructions that, when executed by a device, cause the device to perform the method of the first aspect described above.

[0074] The functionality described above in this document can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0075] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, causes the machine to perform the functions / operations described in the flow diagrams and / or the block diagrams. The program code can execute entirely on a machine, partly on a machine, as a stand-alone software package, partly on a machine and partly on a remote machine or entirely on a remote machine or server.

[0076] In the context of this disclosure, a machine-readable medium can be a non-transitory tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0077] Furthermore, although the operations are described in a specific order, this should be understood as requiring that such operations be performed in the specific order shown or in sequential order, or requiring that all illustrated operations be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of a single implementation may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented individually or in any suitable sub-combination in multiple implementations.

[0078] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for content authoring, comprising: displaying, during a user performing an editing operation within a target application, an interface element of a content authoring tool for interacting with a generative model; obtaining, based on a user prompt received on the interface element, a reply content generated by the generative model; and inserting the reply content into the target application. The content authoring tool is deployed at a level of an operating system, and the operating system has installed a plurality of applications, the content authoring tool being callable in the plurality of applications.

2. The method of claim 1, wherein, Obtaining the reply content generated by the generative model comprises:

3. The method of claim 1, wherein, determining a prompt template to be used; adding the user prompt to the prompt template to obtain a prompt for the generative model; and obtaining the reply content generated by the generative model by providing the prompt to the generative model.

4. The method of claim 3, wherein determining the prompt template to be used comprises: determining, based on a category label of the target application, a prompt template associated with the category label as a recommended prompt template to be used.

5. The method of claim 3, wherein determining the prompt template to be used comprises: displaying a plurality of prompt templates, the plurality of prompt templates comprising prompt templates respectively associated with a plurality of target applications; and determining, based on a user selection, one of the plurality of prompt templates as the prompt template to be used. Displaying the interface element of the content authoring tool for interacting with the generative model comprises: in response to the user intending to input text or media content within a target application, or in response to the user selecting text or media content within the target application, displaying an icon or a toolbar for invoking the content authoring tool; and 6. The method of claim 1, wherein, based on a user input to the icon or the toolbar, displaying the interface element, the interface element comprising a flyout.

7. The method of claim 1, wherein the interface element comprises at least one of: an input area for inputting a prompt; a content area for displaying the reply content generated by the generative model; a toolbar for editing the reply content; and a control for causing the reply content to be inserted into the target application as a whole.

8. The method of claim 7, wherein inserting the reply content into the target application further comprises: determining whether the target application has a capability of editing the reply content; in response to determining that the target application has the capability of editing the reply content, inserting the reply content directly into the target application; and in response to determining that the target application does not have the capability of editing the reply content, displaying the reply content in a floating window.

9. The method of claim 7, wherein obtaining the reply content generated by the generative model comprises: displaying, based on a user input within the target application, the reply content in the content area in real time. Inserting the reply content into the target application comprises: in response to receiving an insertion indication, inserting the reply content into the target application, or ​ ​ 10. The method of claim 1, wherein, ​ ​ In response to obtaining the answer content, directly inserting the answer content into the target application.

11. The method of claim 1, wherein, Inserting the answer content into the target application includes: Inserting the answer content into an editable area or a comment box of the target application.

12. The method of claim 1, further comprising: By a settable manner, limiting the use of the content creation tool in the target application or operating system.

13. An apparatus for content creation, comprising: a display unit configured to display, during a user performing an editing operation in a target application, an interface element of a content creation tool for interacting with a generative model; a content obtaining unit configured to obtain, based on a user prompt word received on the interface element, answer content generated by the generative model; and a content inserting unit configured to, in response to receiving an inserting indication on the interface element, insert the answer content into the target application.

14. An electronic device, the electronic device comprising: one or more processors; and a memory for storing one or more programs, the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method according to any one of claims 1-11.

15. A computer-readable storage medium having stored thereon a computer program, the program, when executed by a processor, implements the method according to any one of claims 1-12.

16. A computer program product comprising a computer program, the computer program, when executed by a processor, implements the method according to any one of claims 1-12. ​

Images