Content generation method and device, computing device, medium, system and program product

Abstract

The invention provides a content generation method and device, a computing device, a medium, a system and a program product. The content generation method comprises the following steps: displaying a user interaction interface, wherein the user interaction interface comprises a canvas area; providing at least one element box in the canvas area; receiving first user intention information input in the first element box by a user; in response to a running operation of a user for the first element box, acquiring a first content material according to the first user intention information by utilizing a preset intelligent agent corresponding to the first user intention information; and generating target content according to the first content material. According to the content generation method and device, the computing device, the medium and the system disclosed by the invention, the problem that the content generation requirements of some complex scenes cannot be met due to single-line dialogue between the user and the intelligent agent is solved, and the interactivity between the user and the intelligent agent can be improved so as to meet the requirements of more application scenes.

Description

Technical Field

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

[0002] With the development of computer technology, some automated auxiliary systems can be used to help people improve the efficiency of content writing. For example, a variety of copywriting content can be generated, and the copywriting can include elements in different formats such as text, pictures, tables, symbols, etc.

[0003] In the related art, the required content can be generated through a dialogue between a user and an agent based on artificial intelligence (AI) (for example, a large language model). However, in this dialogue process, the degree of user intervention is very limited, and the user can only rely on a unilinear dialogue with the current agent, which may not be able to meet the content generation needs of some complex scenarios. Summary of the invention

[0004] Exemplary embodiments of the present disclosure may solve at least the above problems.

[0005] According to a first aspect of the present disclosure, a content generation method is provided, the content generation method comprising: displaying a user interaction interface, the user interaction interface comprising a canvas area; providing at least one element box in the canvas area, wherein the element box is used to interact with a pre-set intelligent agent, the at least one element box comprising a first element box; receiving first user intention information input by a user in the first element box; in response to the user's running operation on the first element box, using a pre-set intelligent agent corresponding to the first user intention information, obtaining first content material according to the first user intention information; generating target content according to the first content material.

[0006] Optionally, providing at least one element frame in the canvas area includes: in response to a user's operation of adding a first element frame in the canvas area, providing the first element frame in the canvas area.

[0007] Optionally, the method also includes: displaying a run control at a predetermined position near the first element frame; in response to the user's run operation on the first element frame, using a pre-set intelligent entity corresponding to the first user intention information, and obtaining the first content material according to the first user intention information, including: in response to the user's click operation on the run control, using a pre-set intelligent entity corresponding to the first user intention information, and obtaining the first content material according to the first user intention information.

[0008] Optionally, after acquiring the first content material, the method further comprises: displaying the acquired first content material at a predetermined position near the first element frame, and displaying an association relationship between the first element frame and the acquired first content material.

[0009] Optionally, the first user intention information includes target agent information, and the target agent is used to obtain the first content material.

[0010] Optionally, generating the target content according to the first content material includes: providing a robot dialogue window, in which a dialog box is provided; receiving a content generation instruction input by a user through the dialog box; and generating the target content according to the first content material based on the content generation instruction.

[0011] Optionally, the canvas area includes multiple acquired first content materials; generating the target content according to the first content materials based on the content generation instruction includes: if the content generation instruction specifies a first content material specifically introduced by the user for generating the target content among the multiple first content materials, generating the target content according to the first content material specifically introduced by the user; or, if the content generation instruction does not specify a first content material specifically introduced by the user for generating the target content among the multiple first content materials, generating the target content according to all first content materials in the canvas area.

[0012] Optionally, providing at least one element box in the canvas area includes: in response to a user's instruction to introduce a target template, displaying the target template in the canvas area, wherein the target template includes multiple element boxes, and the multiple element boxes include the first element box and the second element box; generating the target content according to the first content material includes: receiving a content generation instruction input by the user in the second element box; in response to the user's running operation on the second element box, generating the target content according to the first content material using a pre-set intelligent agent corresponding to the content generation instruction.

[0013] Optionally, in the target template, a predetermined position near each element box displays user operation prompt information corresponding to the element box.

[0014] Optionally, the use of a pre-set intelligent entity corresponding to the first user intention information to obtain the first content material according to the first user intention information includes: using a pre-set intelligent entity corresponding to the first user intention information to obtain multiple data resources according to the first user intention information, and displaying the multiple data resources in the canvas area; in response to a user's selection operation of a target data resource among the multiple data resources, using the selected target data resource as the first content material.

[0015] Optionally, the first user intention information includes target workflow information, the target workflow is used to obtain the first content material, and the target workflow includes multiple sub-tasks and a sequential execution relationship between the multiple sub-tasks; wherein, obtaining the first content material according to the first user intention information using a pre-set intelligent agent corresponding to the first user intention information includes: using a pre-set intelligent agent corresponding to the target workflow to run the target workflow to execute corresponding sub-tasks according to the sequential execution relationship of the sub-tasks in the target workflow to generate the first content material.

[0016] Optionally, the target workflow is run by using a pre-set intelligent agent corresponding to the target workflow to execute corresponding subtasks in accordance with the sequential execution relationship of the subtasks in the target workflow, and the generation of the first content material includes: generating the first content material by performing at least one subtask execution operation, wherein the subtask execution operation includes: providing a current element box; receiving current user intention information input by a user, wherein the current user intention information is associated with the content material acquired in the last operation; in response to the user's running operation on the current element box, obtaining and displaying the current content material according to the current user intention information and the content material acquired in the last operation by using a pre-set intelligent agent corresponding to the current user intention information, wherein when executing the first subtask, the current element box is the first element box, the current user intention information is the first user intention information, and the content material acquired in the last operation is empty; when executing the last subtask, the current content material is the first content material.

[0017] Optionally, the content generation method also includes: providing a third element box in the canvas area; receiving a program interface of a target program input by a user in the third element box; displaying an interface of the target program in the third element box in response to a user's running operation on the third element box; loading content in the target program into the canvas area, or uploading content in the canvas area to the target program, in response to a user's access operation to the target program in the third element box.

[0018] Optionally, the content generating method further includes: generating second target content according to the content in the target program.

[0019] Optionally, after acquiring the first content material, the content generation method further includes: acquiring second content material based on the first content material; and generating target content according to the first content material includes: generating the target content according to the second content material.

[0020] Optionally, after acquiring the first content material, the content generation method further includes: displaying the first content material at a predetermined position near the first element box, and displaying the association relationship between the first element box and the first content material; acquiring the second content material based on the first content material includes: providing a fourth element box in the canvas area in response to a user's fourth element box addition instruction; connecting the fourth element box with the first content material in response to a user's association operation on the fourth element box and the first content material; receiving second user intention information input by the user in the fourth element box; in response to a user's running operation on the fourth element box, acquiring and displaying the second content material according to the first content material using a pre-set intelligent agent corresponding to the second user intention information, and displaying the association relationship between the fourth element box and the acquired second content material, so as to present the information flow of acquiring the second content material.

[0021] Optionally, the content generation method further includes: in response to a user's editing operation on the information flow, adjusting the association relationship, user intent information or content material information in the information flow based on the editing operation; and / or, in response to a user's deletion operation on the information flow, deleting the information flow.

[0022] Optionally, the content generation method further includes: in response to a user's detail display operation on a target element box in the canvas area, displaying relevant data and / or deduction logic corresponding to the target element box.

[0023] Optionally, the content generation method also includes: in response to a user's operation of adding one or more element boxes in the canvas area, providing the one or more element boxes in the canvas area; receiving a first editing operation of the user on the one or more element boxes themselves and / or a second editing operation on the association relationship between the element boxes; and in response to a user's instruction to create a template, saving the one or more element boxes as a template for generating content.

[0024] According to a second aspect of the present disclosure, a content generating device is provided, comprising: a display unit, configured to display a user interaction interface, the user interaction interface comprising a canvas area; a providing unit, configured to provide at least one element box in the canvas area, wherein the element box is used to interact with a pre-set intelligent agent, and the at least one element box comprises a first element box; a receiving unit, configured to receive first user intention information input by a user in the first element box; an acquiring unit, configured to acquire first content material according to the first user intention information by utilizing a pre-set intelligent agent corresponding to the first user intention information in response to a user's running operation on the first element box; and a generating unit, configured to generate target content according to the first content material.

[0025] Optionally, the providing unit is further configured to: in response to a user's operation of adding a first element frame in the canvas area, provide the first element frame in the canvas area.

[0026] Optionally, the content generating device further includes a display unit, which is configured to: display a running control at a predetermined position near the first element frame; the acquisition unit is further configured to: respond to a user's click operation on the running control, utilize a pre-set intelligent entity corresponding to the first user intention information, and acquire the first content material according to the first user intention information.

[0027] Optionally, the content generating device further includes a relationship display unit, which is further configured to display the acquired first content material at a predetermined position near the first element frame after the acquisition unit acquires the first content material, and to display an association relationship between the first element frame and the acquired first content material.

[0028] Optionally, the first user intention information includes target agent information, and the target agent is used to obtain the first content material.

[0029] Optionally, the generating unit is further configured to: provide a robot dialogue window, in which a dialog box is provided; receive a content generating instruction input by a user through the dialog box; and generate the target content according to the first content material based on the content generating instruction.

[0030] Optionally, the canvas area contains multiple acquired first content materials; wherein the generation unit is further configured to: if the content generation instruction specifies a first content material specifically introduced by the user among the multiple first content materials for generating the target content, generate the target content according to the first content material specifically introduced by the user; or, if the content generation instruction does not specify a first content material specifically introduced by the user among the multiple first content materials for generating the target content, generate the target content according to all the first content materials in the canvas area.

[0031] Optionally, the providing unit is further configured to: in response to a user's instruction to introduce a target template, display the target template in the canvas area, wherein the target template includes multiple element boxes, and the multiple element boxes include the first element box and the second element box; wherein the generating unit is further configured to: receive a content generation instruction input by the user in the second element box; in response to the user's running operation on the second element box, generate the target content according to the first content material by using a pre-set intelligent agent corresponding to the content generation instruction.

[0032] Optionally, in the target template, a predetermined position near each element box displays user operation prompt information corresponding to the element box.

[0033] Optionally, the acquisition unit is further configured to: utilize a pre-set intelligent agent corresponding to the first user intention information, acquire multiple data resources according to the first user intention information, and display the multiple data resources in the canvas area; in response to the user's selection operation of a target data resource among the multiple data resources, use the selected target data resource as the first content material.

[0034] Optionally, the first user intention information includes target workflow information, the target workflow is used to obtain the first content material, the target workflow includes multiple subtasks and a sequential execution relationship between the multiple subtasks; wherein the acquisition unit is further configured to: utilize a pre-set intelligent agent corresponding to the target workflow to run the target workflow to execute corresponding subtasks according to the sequential execution relationship of the subtasks in the target workflow to generate the first content material.

[0035] Optionally, the acquisition unit is further configured to: generate the first content material by performing at least one subtask execution operation, wherein the subtask execution operation includes: providing a current element box; receiving current user intention information input by a user, wherein the current user intention information is associated with the content material acquired in the last operation; in response to the user's running operation on the current element box, using a pre-set intelligent agent corresponding to the current user intention information, according to the current user intention information and the content material acquired in the last operation, acquire and display the current content material, wherein, when executing the first subtask, the current element box is the first element box, the current user intention information is the first user intention information, and the content material acquired in the last operation is empty; when executing the last subtask, the current content material is the first content material.

[0036] Optionally, the content generating device also includes a program access unit, which is configured to: provide a third element box in the canvas area; receive a program interface of a target program input by a user in the third element box; display an interface of the target program in the third element box in response to a user's running operation on the third element box; load the content in the target program into the canvas area, or upload the content in the canvas area to the target program in response to a user's access operation to the target program in the third element box.

[0037] Optionally, the generating unit is further configured to: generate second target content according to the content in the target program.

[0038] Optionally, the acquisition unit is further configured to acquire second content material based on the first content material after acquiring the first content material; wherein the generation unit is further configured to generate the target content according to the second content material.

[0039] Optionally, the content generating device further comprises a relationship display unit, which is configured to: after the acquisition unit acquires the first content material, display the first content material at a predetermined position near the first element box, and display the association relationship between the first element box and the first content material; wherein the acquisition unit is further configured to: in response to a user's instruction to add a fourth element box, provide a fourth element box in the canvas area; in response to a user's association operation on the fourth element box and the first content material, connect the fourth element box with the first content material; receive second user intention information input by the user in the fourth element box; in response to a user's operation on the fourth element box, acquire and display the second content material according to the first content material using a pre-set intelligent agent corresponding to the second user intention information, and display the association relationship between the fourth element box and the acquired second content material, so as to present the information flow of acquiring the second content material.

[0040] Optionally, the content generating device further includes an information flow editing unit, which is configured to: in response to a user's editing operation on the information flow, adjust the association relationship, user intent information or content material information in the information flow based on the editing operation; and / or, in response to a user's deletion operation on the information flow, delete the information flow.

[0041] Optionally, the content generating device further includes a detail display unit, and the detail display unit is configured to: in response to a user's detail display operation on a target element box in the canvas area, display relevant data and / or deduction logic corresponding to the target element box.

[0042] Optionally, the content generating device also includes a template generating unit, which is configured to: in response to a user's operation of adding one or more element boxes in the canvas area, provide the one or more element boxes in the canvas area; receive a first editing operation of the user on the one or more element boxes themselves and / or a second editing operation on the association relationship between the element boxes; and in response to a user's instruction to create a template, save the one or more element boxes as a template for generating content.

[0043] According to a third aspect of the present disclosure, a computing device is provided, comprising: a processor; and a memory for storing instructions executable by the processor, wherein the processor executable instructions, when executed by the processor, cause the processor to execute the content generation method according to an embodiment of the present disclosure.

[0044] According to a fourth aspect of the present disclosure, a computer-readable storage medium storing instructions is provided. When the instructions are executed by at least one computing device, the at least one computing device is prompted to execute the content generation method according to the embodiment of the present disclosure.

[0045] According to a fifth aspect of the present disclosure, a system is provided comprising at least one computing device and at least one storage device storing instructions, wherein when the instructions are executed by the at least one computing device, the at least one computing device is prompted to execute the content generation method according to the embodiment of the present disclosure.

[0046] According to a sixth aspect of the present disclosure, a computer program product is provided, comprising instructions, which, when executed by at least one computing device, prompt the at least one computing device to execute the content generation method as described in the embodiments of the present disclosure.

[0047] According to the content generation method and device, computing device, medium and system of the exemplary embodiments of the present disclosure, it is possible to provide at least one element box in the canvas area of ​​the user interaction interface, receive first user intention information input by the user in the first element box, and in response to the user's operation on the first element box, use the corresponding intelligent agent to generate first content material according to the first user intention information, so as to generate target content according to the first content material. In this way, the user can generate content material related to the user's intention by first interacting with the first element box, and then use such content material to complete the generation of the target content, thereby improving the interactivity between the user and the intelligent agent, avoiding the content generation process being too limited due to a single linear dialogue interaction, and improving the flexibility of the content generation process to meet the needs of more application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] These and / or other aspects and advantages of the present disclosure will become clear and more easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0049] Figure 1 is a flowchart illustrating a content generation method according to an exemplary embodiment of the present disclosure.

[0050] Figure 2 is a schematic diagram illustrating a user interaction interface in a content generating method according to an exemplary embodiment of the present disclosure.

[0051] Figure 3 and Figure 4 is a schematic diagram illustrating the introduction of a target template in a content generating method according to an exemplary embodiment of the present disclosure.

[0052] Figure 5is a schematic diagram illustrating a target template in a content generating method according to an exemplary embodiment of the present disclosure.

[0053] Figure 6 2 is a schematic diagram showing inputting target agent information and target workflow information in a content generating method according to an exemplary embodiment of the present disclosure.

[0054] Figure 7 2 is a schematic diagram illustrating generating a picture in a content generating method according to an exemplary embodiment of the present disclosure.

[0055] Figure 8 is a schematic diagram illustrating generating text in a content generating method according to an exemplary embodiment of the present disclosure.

[0056] Fig. 9 is a schematic diagram showing presentation data resources in a content generation method according to an exemplary embodiment of the present disclosure.

[0057] FIG. 10A to FIG. 10G is a schematic diagram illustrating generating target content based on a target workflow in a content generating method according to an exemplary embodiment of the present disclosure.

[0058] Fig.11 It is a schematic diagram showing the marking of data resources in the content generation method according to an exemplary embodiment of the present disclosure.

[0059] Fig.12 is a schematic diagram illustrating a content generation instruction in a content generation method according to an exemplary embodiment of the present disclosure.

[0060] Fig.13A and Fig. 13B FIG. 4 is a schematic diagram illustrating obtaining a second content material in a content generating method according to an exemplary embodiment of the present disclosure.

[0061] Fig.14 is a schematic diagram illustrating accessing a target program in a content generating method according to an exemplary embodiment of the present disclosure.

[0062] Fig.15 is a schematic diagram illustrating an editing operation on an information stream in a content generating method according to an exemplary embodiment of the present disclosure.

[0063] Fig.16 is a schematic diagram of a presentation interface showing a detail presentation operation in a content generation method according to an exemplary embodiment of the present disclosure.

[0064] Fig.17 is a schematic diagram illustrating prediction information in a content generating method according to an exemplary embodiment of the present disclosure.

[0065] Fig.18is a block diagram illustrating a content generating apparatus according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0066] The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of the embodiments of the present disclosure as defined by the claims and their equivalents. Various specific details are included to assist in understanding, but these details are considered to be exemplary only. Therefore, one of ordinary skill in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known functions and structures are omitted for clarity and brevity.

[0067] It should be noted that the phrase "at least one of the items" in the present disclosure includes three types of parallel situations: "any one of the items", "a combination of any number of the items", and "all of the items". For example, "including at least one of A and B" includes the following three parallel situations: (1) including A; (2) including B; (3) including A and B. Another example is "executing at least one of step 1 and step 2" which means the following three parallel situations: (1) executing step 1; (2) executing step 2; (3) executing step 1 and step 2.

[0068] The following describes a content generation method, a content generation device, a computing device, a computer-readable storage medium, and a system including at least one computing device and at least one storage device storing instructions according to exemplary embodiments of the present disclosure with reference to the accompanying drawings.

[0069] In a first aspect, exemplary embodiments of the present disclosure provide a content generation method to solve at least one of the problems in the related art.

[0070] The execution subject of the content generation method according to the exemplary embodiment of the present disclosure may be any type of computing device capable of performing content generation, for example, the computing device may be loaded with a content generation platform, and the user may interact with the content generation platform to generate target content according to the content generation method described in the exemplary embodiment of the present disclosure. The above computing device may be, but is not limited to, a desktop computer, a laptop computer, a tablet computer, a personal digital assistant, a smart phone, or other device capable of performing content generation.

[0071] Figure 1 is a flow chart showing a method for generating content according to an exemplary embodiment of the present disclosure. Figure 1 As shown, the content generation method may include:

[0072] In step S110 , a user interaction interface may be displayed, where the user interaction interface includes a canvas area.

[0073] In step S120 , at least one element frame may be provided in the canvas area.

[0074] Here, the canvas area can be used for users to interact with the agent, and can display the interaction information between the user and the agent. The element box can be used to interact with the pre-set agent, such as receiving instructions or information input by the user, displaying the content or materials produced by the agent to the user, etc. In addition, the position of the element box in the canvas area can be adjusted by the user, and the user can move the element box to any position in the canvas area by dragging. In addition, the agent described in this article can be obtained based on agent architectures such as but not limited to AutoGPT, Camel, MetaGPT, etc.

[0075] As an example, the element box can receive instructions or information input by the user, and in response to the user's Run operation on the element box, the agent can perform a corresponding task according to the user's input in the element box. As an example, in response to the agent completing a corresponding task according to the user's input, a new element box can be generated in the canvas area to display the content or materials produced by the agent.

[0076] Here, the element box may also be referred to as a container, which may be, for example, a rich media picture frame. The element box may contain one or more blocks, and the data types of the blocks in the element box may be different. The data types of the blocks may include, for example, but are not limited to, plain text, lightweight markup language (markdown), files in formats such as Excel, PDF, CSV, MP4, etc., pictures, codes, links, Hypertext Markup Language (HTML) pages, etc.

[0077] In an embodiment of the present disclosure, the element box in the canvas area may include a first element box. The first element box may be used to receive first user intention information input by a user. Several examples of providing the first element box are given below.

[0078] In one example, in step S120 , in response to a user's operation of adding a first element frame in the canvas area, a first element frame may be provided in the canvas area.

[0079] For example, Figure 2 An example of a user interaction interface according to an embodiment of the present disclosure is shown, Figure 2 As shown, the user interaction interface may include a canvas area 210 and a toolbar 220. The toolbar 220 may include an element frame generation control 221. In response to the user triggering the element frame generation control 221 in the toolbar 220, a first element frame may be added in the canvas area, for example Figure 2 231. It is understood that Figure 2The user interaction interface is only an example, and the styles of the toolbar 220 and the element box generation control 221 in the actual product are not limited.

[0080] Here, in response to the user's operation of adding the first element frame multiple times, multiple first element frames may be provided in the canvas area, and these element frames may be independently operated by the user, for example, run independently.

[0081] In another example, step S120 may include: in response to the user's instruction to introduce the target template, displaying the target template in the canvas area, wherein the target template may include multiple element boxes, the multiple element boxes include the first element box and the second element box, and thus, the first element box may be provided in the target template. Here, the second element box may be used to receive the content generation instruction input by the user (described in detail below).

[0082] Here, the target template can be a pre-set content generation template. Each template can be preset with an element box for generating content. Different templates can be used to generate different types of content. Therefore, the number of element boxes, functions, associations between element boxes, etc. contained in different templates may be different.

[0083] For example, Figure 3 and Figure 4 An example interface of introducing a template according to an embodiment of the present disclosure is shown, Figure 3 As shown, the user interaction interface may further include a management option bar 240, which may include a document management option 241, a template management option 242, etc. The document management option 241 may be used to query and manage historical documents, such as generated content materials, generated content, documents created or uploaded by users, etc. The template management option 242 may be used to query and manage pre-set content generation templates. In response to a user's selection operation on the template management option 242, such as Figure 4 As shown, the preset content generation template can be displayed in the user interaction interface; in response to the user's selection operation of the target template in the preset content generation template, as shown in FIG. Figure 5 As shown, the target template can be displayed in the canvas area, and a first element frame can be provided in the target template, for example Figure 5 Elements in box 232.

[0084] Although several examples of providing the first element box are given above, the embodiments of the present disclosure are not limited thereto, and the first element box may be provided in other ways. For example, the first element box may be provided by the user by selecting or dragging a graphic in the canvas area, or the first element box may be generated in the canvas area by an agent during a conversation between the user and an agent (such as the conversational robot described below).

[0085] In addition, as an example, the content generation device further includes: in response to a user's operation of adding one or more element boxes in the canvas area, providing one or more element boxes in the canvas area; receiving a user's first editing operation on the one or more element boxes themselves and / or a second editing operation on the association relationship between the element boxes; in response to a user's instruction to create a template, saving the one or more element boxes as a template for generating content. In this way, the user can freely create a template form for subsequent introduction, thereby generating relevant content more quickly.

[0086] Return to reference Figure 1 In step S130, first user intention information input by the user in the first element box may be received.

[0087] Here, the first user intention information may be information related to content material or target content that the user desires to generate.

[0088] The first user intention information may include user-defined content. Specifically, the user-defined content may include, but is not limited to, keywords related to the content material or target content that the user desires to generate, sentences expressing the user's intention, etc.

[0089] As an example, the first user intention information may also include at least one of target agent information, target workflow information, and pre-generated content material information. The target agent information, target workflow information, or pre-generated content material information may form the first user intention information together with the user-defined content.

[0090] The target agent information can be used to specify any agent among the preset agents, and the target agent can be used to obtain the first content material.

[0091] As an example, multiple agents may be preset, each of which may perform different tasks. The user may input information of a target agent that can perform the current task in the first element box according to needs.

[0092] For example, the target agent information can be input in the following manner: in response to the user's insert operation on the first element box, the preset agent information is displayed in the first element box, and in response to the user's selection operation on the agent, the target agent information is input in the first element box.

[0093] The target workflow information may be used to specify any workflow in the preset workflows, and the target workflow may be used to obtain the first content material.

[0094] As an example, multiple workflows may be preset, each workflow may execute different tasks respectively, and the user may input information of a target workflow that can execute the current task in the first element box according to the requirements.

[0095] Similar to inputting the target agent information, the target workflow information can be input in the following manner: in response to the user's insert operation on the first element box, the information of the preset workflow is displayed in the first element box, and in response to the user's selection operation on the workflow, the target workflow information is input in the first element box.

[0096] For example, Figure 6 As shown, the user can perform an insert operation by, for example, right-clicking the area in the first element frame. In response to the insert operation, for example, the selectable preset agent and preset workflow information can be displayed in the first element frame in a downward expansion manner, for example, Figure 6 In the program, selectable preset agents may include a search agent for flower-head images, a picture search agent, a picture generation agent, an upstream and downstream word agent, a tagging agent, etc., and selectable preset workflows may include an inspiration card workflow (workflow), a screening expert workflow, etc.

[0097] The user can perform a selection operation by clicking on the target agent or target workflow, and in response to the user's selection operation, the target agent information or target workflow information is input in the first element box.

[0098] The target agent information may include, for example, an introduction prompt and an agent identifier. The introduction prompt is used to indicate the introduction of an agent, and may be, for example, a preset symbol such as "@"; the agent identifier is used to indicate the introduced agent, and may be, for example, the name of the agent. Figure 6 For example, the target agent information entered in the first element box may be “@picture generation”. Similarly, the target workflow information may include an import prompt and a workflow identifier, where the workflow identifier is used to indicate the imported workflow, such as the name of the workflow. Figure 6 Taking the inspiration card workflow in as an example, the target workflow information entered in the first element box can be, for example, “@inspiration card workflow”.

[0099] The pre-generated content material information may be content material or content generated before executing the current target content generation process. In an embodiment of the present disclosure, the content material generated in the intermediate process of generating content and the target content finally generated are stored as documents, which can be found and managed in the document management option 241 described above, for example.

[0100] For example, the target agent information may be input in the following manner: in response to the user's insert operation on the first element frame, the information of the generated content material is displayed at the first element frame, and in response to the user's selection operation on the generated content material, the generated content material information is input in the first element frame. The generated content material information may include, for example, an introduction prompt and a content material identifier.

[0101] In step S140, in response to the user's running operation on the first element frame, the first content material can be acquired according to the first user intention information by using a pre-set intelligent agent corresponding to the first user intention information.

[0102] Here, the user's running operation on the first element frame can be used to trigger the corresponding agent to execute the step of acquiring the first content material according to the first user intention information.

[0103] As an example, the content generation method further includes: displaying a run control at a predetermined position near the first element frame. In this example, step S140 may include: in response to a user clicking operation on the run control, using a pre-set agent corresponding to the first user intention information, and acquiring the first content material according to the first user intention information.

[0104] For example, in response to a user clicking on the first element frame, a run control may be displayed near the first element frame, and after the user clicks on the run control, a pre-set agent corresponding to the first user intention information may be triggered to obtain the first content material. Figure 2 As shown, in response to the user clicking on the first element frame 231, a component bar including a run control 271 may be displayed; in response to the user clicking on the run control 271, the intelligent agent may be triggered to obtain the first content material.

[0105] However, the user's running operation on the first element frame is not limited to the above examples. For example, the user may also display the running control by hovering the cursor in the area of ​​the first element frame; for another example, the running operation may also be triggered by double-clicking the first element frame.

[0106] In this step S140, the agent corresponding to the first user intention information may refer to an agent that can identify the first user intention information and obtain the corresponding first content material. Taking the example of the first user intention information as an example, when the first user intention information includes target agent information or target workflow information, the agent corresponding to the first user intention information may be the target agent or an agent related to the target workflow; when the first user intention information does not include target agent information and target workflow information, but only includes user-defined content, the agent corresponding to the first user intention information may be a preset default agent. Here, the target agent, the agent related to the target workflow, and the preset default agent may be the same or different.

[0107] The above-mentioned intelligent agent can obtain the first content material according to the first user intention information. Several examples of using the intelligent agent to obtain the first content material will be given below.

[0108] In one example, when the first user intention information includes user-defined content and target agent information, the target agent can be used to execute a preset task corresponding to the target agent for the user-defined content to obtain the first content material. Figure 7 As shown, an intelligent agent can be generated using pictures to generate pictures related to the user-defined content "generate a picture of a car in a 4S store, photo level".

[0109] In another example, when the first user intention information includes user-defined content, pre-generated content material information, and target agent information, the target agent can be used to execute a preset task corresponding to the target agent for the user-defined content and the pre-generated content material to obtain the first content material. Figure 8 As shown, the research report can be used to generate an intelligent agent to generate text related to the pre-generated content material "mena search demonstration" and user-defined content "What does this document talk about, summarize in two sentences" for asking questions about the content material.

[0110] As an example, after acquiring the first content material, the content generation method may further include: displaying the acquired first content material at a predetermined position near the first element frame, and displaying an association relationship between the first element frame and the acquired first content material.

[0111] Specifically, in response to the agent generating the first content material, a new element frame may be displayed at a predetermined position near the first element frame to display the first content material (eg, Figure 7 Pictures or Figure 8), and the first element box and the element box can be connected by graphics such as arrows or connecting lines to show the relationship between the first element box and the first content material.

[0112] In this way, the information flow can be displayed in a visual manner, allowing users to intuitively and quickly locate the relationship between the user intention of their input and the content of the agent's response.

[0113] The above describes an example of directly using the content material acquired by the agent as the first content material. In an embodiment of the present disclosure, after the agent acquires the content material, it can also receive the interaction between the user and the content material to determine the final first content material.

[0114] As an example, the step of obtaining the first content material may include: utilizing a pre-set intelligent agent corresponding to the first user intention information, obtaining multiple data resources according to the first user intention information, and displaying the multiple data resources in a canvas area; in response to a user's selection operation of a target data resource among the multiple data resources, using the selected target data resource as the first content material.

[0115] For example, in Figure 5 In the example of generating target content based on a target template shown in FIG. 1 , in response to a user inputting first user intent information, such as the keyword “camping”, in the first element box 232, since the user intent information does not specify a target agent, a preset default agent (such as an information collection agent) may search for data resources related to the keyword “camping”, and as shown in FIG. Fig. 9 In response to the user's selection operation on the target data resource, for example, checking Fig. 9 Some of the data resources in the content can be used as the first content material.

[0116] In this way, after the intelligent agent obtains preliminary content materials, the user can be allowed to further interact and participate in the selection process of the first content material, so that the final first content material is closer to the user's needs, so as to better generate target content that meets the user's intentions.

[0117] Although the above describes an example process of displaying data resources for user selection by taking a target template as an example, the embodiments of the present disclosure are not limited thereto. For example, data resources may be displayed and selected during a process in which a user specifies a target workflow to generate target content.

[0118] The process of acquiring the first content material based on the target workflow will be described in detail below. As described above, the first user intention information may include target workflow information, and the target workflow may include multiple subtasks and sequential execution relationships between the multiple subtasks, where the subtasks may be pre-set.

[0119] In the example of obtaining the first content material based on the target workflow, obtaining the first content material may include: utilizing a pre-set intelligent agent corresponding to the first user intention information to run the target workflow to execute corresponding subtasks according to the sequential execution relationship of the subtasks in the target workflow to generate the first content material.

[0120] Specifically, executing corresponding subtasks according to the sequential execution relationship of subtasks in the target workflow to generate the first content material may include: generating the first content material by executing at least one subtask execution operation.

[0121] Here, the subtask execution operation may include: providing a current element frame; receiving current user intention information input by the user, the current user intention information being associated with the content material acquired in the last operation; in response to the user's running operation on the current element frame, utilizing a pre-set intelligent agent corresponding to the current user intention information, acquiring and displaying the current content material based on the current user intention information and the content material acquired in the last operation.

[0122] When executing the first subtask, the current element frame may be the first element frame, the current user intent information may be the first user intent information, and the content material obtained in the last operation is empty. In response to the user's operation on the first element frame, the pre-set intelligent agent corresponding to the current user intent information may be used to obtain and display the content material of the first operation according to the first user intent information. In each subsequent subtask execution operation, the content material of the current operation may be obtained and displayed based on the content material obtained and displayed in the last subtask execution operation and the current user intent information. Here, the current user intent information may be associated with the content material obtained and displayed in the last subtask execution operation, such as the user's selection of the content material obtained and displayed in the last subtask execution operation.

[0123] FIG. 10A to FIG. 10D FIG. 2 shows an example process of acquiring the first content material based on the target workflow. Fig. 10A As shown, the user can enter the first user intention information in the first element box 233. The first user intention information can include, for example, the pre-generated content material "mena search demonstration" and the user-defined content "the target user is a young girl, and the theme is 'cars suitable for girls'". The pre-set keyword analysis agent can be used to obtain and display the initial content material related to the above user intention information, for example, in Fig. 10A Each keyword is displayed in the element box 234.

[0124] In response to obtaining and displaying the content material of the last subtask execution operation, such as the above-mentioned keywords, a current element frame of the current subtask execution operation, such as element frame 235, can be provided to receive the current user intention information, such as Fig. 10A As shown, the current user intent information may include the user's selection of keywords. In response to the user's operation on the current element frame 235, an agent corresponding to the current user intent information, such as an information collection agent, may be used to obtain and display the content material of this operation based on the current user intent information and the content material obtained in the previous operation, such as the user's selection and the selected keyword, for example. Fig. 10B As shown, data resources collected online can be obtained and displayed, such as public resources on online social platforms.

[0125] In response to obtaining and displaying the content material of the last subtask execution operation, such as the above-mentioned online collected data resources, a current element frame of the current subtask execution operation may be provided, such as Fig. 10C The element box 236 shown in the figure is used to receive the current user intention information, for example, the current user intention information may include the user's selection of data resources collected online. In response to the user's operation on the current element box 236, an agent corresponding to the current user intention information, such as a tagging agent, may be used to obtain and display the content material of this operation according to the current user intention information and the content material obtained in the previous operation, for example, according to the user's selection and the selected data resource, for example. Fig. 10D As shown, the labeled data resources can be obtained and displayed. Here, labeling can refer to adding labels to the data resources. The labeled data resources can be stored in the form of a table, such as an Excel file.

[0126] In this example, the marked data resource can be used as the first content material that is finally generated to generate the target content.

[0127] Through the above method, each subtask is executed one by one in the order of the target workflow, which can guide the user to complete the process of obtaining the first content material and generating the target content, so that even if the user does not understand the complete process of content material and content generation, he can quickly realize content generation under the guidance of the workflow.

[0128] In addition, it should be noted that any subtask in the above workflow can be executed as a separate content material generation process. The workflow can be considered as an orderly combination of agents that can perform various tasks to jointly complete the target content generation. Any agent that performs a task in the workflow can also be called separately to implement the corresponding function. For example, Fig.11 As shown, the user can call the marking agent to perform the above-mentioned data resource marking function by inputting the marking agent information, such as marking the generated data resources specified by the user.

[0129] In addition, in step S140, the user can add multiple first element boxes in the canvas area to allow the user to input different first user intention information in each first element box. In response to the user's operation on any target element box in the multiple first element boxes, the pre-set intelligent agent corresponding to the first user intention information in the target element box can be used to obtain the corresponding first content material according to the first user intention information.

[0130] Here, the interactions between the user and different first element frames are independent of each other. Accordingly, the information flows generated by the interactions between the user and different first element frames are also independent of each other. However, the user can edit and integrate the independent information flows, which will be described in detail below.

[0131] Return to reference Figure 1 In step S150, target content may be generated according to the first content material.

[0132] In this step, the target content may be one or more, for example, the target content may be displayed in an element frame, and in response to the user's selection of the target content, the target content selected by the user may be exported in batches.

[0133] In one example, the target content can be generated in the following manner: receiving a content generation instruction input by a user in a second element box; in response to the user's operation on the second element box, using a pre-set intelligent agent corresponding to the content generation instruction to generate the target content according to the first content material.

[0134] Here, the content generation instruction may include, but is not limited to, user-defined content, target agent information, pre-generated content material information, etc. For example, in an example where the first user intention information includes target template information, such as Figure 5As shown, the user can input content generation instructions in the second element box 238, such as inputting pre-generated content material information. In response to the user's operation on the second element box 238, the intelligent agent corresponding to the content generation instruction (such as the default intelligent agent) can generate target content, such as multiple product introduction copies, based on the first content material and the pre-generated content material specified in the content generation instruction.

[0135] In addition, as an example, in the target template, a predetermined position near each element box may display user operation prompt information corresponding to the element box to prompt the user of the function of each element box.

[0136] Through this method of preset content generation templates, the entire process of generating target content can be visually displayed, allowing users to quickly generate target content according to the instructions in the template. Users do not need to have an in-depth understanding of the complete interactive process. This is user-friendly and helps improve the efficiency of users in obtaining the desired target content.

[0137] In another example, in an example where the first user intention information includes target workflow information, as described above, the first content material may be acquired based on the target workflow. Here, target content may also be generated based on the target workflow and from the first content material.

[0138] Specifically, in the case where the first user intention information includes target workflow information, in response to obtaining the first content material based on the target workflow, for example Fig. 10D The marked data resource shown in , can provide a second element frame to receive the user's content generation instruction, such as Fig.10E As shown, the content generation instruction may include pre-generated content material information "mena search demonstration", and the first content material may include "tagged data resource.xlsx". In response to the user inputting the above content generation instruction, a pre-set intelligent agent corresponding to the content generation instruction, such as a copywriting generation intelligent agent, may be used to generate target content according to the first content material and the content material information specified in the content generation instruction, and the target content may be displayed, such as Fig.10F As shown, multiple copywriting is displayed. The user can select the desired target content (such as Figure 10G to export or save.

[0139] In another example, in an example where the first user intention information includes target agent information, as described above, the first content material can be acquired based on the target agent, where target content can be generated based on the first content material acquired based on one or more target agents according to user interaction.

[0140] Specifically, step S150 may include: providing a robot dialogue window, in which a dialog box is provided; receiving a content generation instruction input by a user through the dialog box; and generating target content according to the first content material based on the content generation instruction.

[0141] Here, the content generation instruction may be, for example, information related to the target content that the user wants to generate. The content generation instruction may include user-defined content. Specifically, the user-defined content may include, but is not limited to, keywords related to the target content that the user wants to generate, sentences expressing the user's intention, etc. As an example, the content generation instruction may also include at least one of target agent information, target workflow information, and pre-generated content material information. For example, the user may specify the target agent to generate the target content by inputting the target agent information.

[0142] For example, Figure 2 As shown, the user interaction interface may further include a robot dialogue window 250, in which a dialog box 251 is provided, and the dialog box 251 may receive a content generation instruction input by a user. Here, the robot dialogue window 250 may be displayed in parallel with the canvas area 210, for example. In addition, the user interaction interface may further include a dialogue window call-out button 260. In response to the user clicking the dialogue window call-out button 260, the robot dialogue window 250 may be displayed or hidden in the user interaction interface.

[0143] According to an embodiment of the present disclosure, a plurality of first content materials that have been acquired may be included in the canvas area. For example, the process of acquiring the first content material described above may be performed multiple times to generate a plurality of first content materials. In this case, based on the content generation instruction, the step of generating the target content according to the first content material may include: if the content generation instruction specifies the first content material specifically introduced by the user for generating the target content among the plurality of first content materials, generating the target content according to the first content material specifically introduced by the user; or, if the content generation instruction does not specify the first content material specifically introduced by the user for generating the target content among the plurality of first content materials, generating the target content according to all the first content materials in the canvas area.

[0144] Specifically, when the user specifies a specific first content material in the canvas area 210 in the content generation instruction, the user can import any first content material in the canvas area by inputting the first content material information (e.g., inputting the import prompt and the name of the first content material) in the dialog box, or can also import any first content material in the canvas area 210 by dragging it into the dialog box. In this example, the content generation instruction may also include user-defined content, such as questions about the specific content materials imported, such as "what are described in these materials?"

[0145] In the case where the user's content generation instruction does not specify a specific first content material, for example, Figure 2 As shown, the robot dialogue window 250 may further include a content generation component 252 , such as a component “start with this doc”. In response to a user triggering the content generation component 252 , target content may be generated based on all first content materials currently existing in the canvas area 210 .

[0146] As an example, in the case where the content generation instruction does not include target agent information and target workflow information, in the above process, the target content can be generated using a preset default agent. In the case where the content generation instruction includes target agent information or target workflow information, in the above process, the target content can be generated using a target agent or target workflow, for example, Fig.12 As shown, the content generation instruction may include the target agent information "@gpt" and the user-defined content "What this document talks about...".

[0147] In addition, as an example, in addition to generating the target content, the robot dialogue window 250 can also optimize the first content material generated in the canvas area. For example, in response to the user introducing the target first content material in the dialog box and entering the optimization intention information, the target first content material can be optimized according to the optimization intention information to generate the optimized content material. Here, in response to generating the optimized content material, the optimized content material can also be displayed in the robot dialogue window 250 and / or the canvas area 210.

[0148] By setting the robot dialogue window in the above manner, the user can generate the target content more flexibly, and the user can selectively introduce a part of the content material in the canvas area to generate the target content, thereby improving the flexibility and interactivity of content generation.

[0149] In another example, after acquiring the first content material, the content generation method may further include: acquiring the second content material based on the first content material. In this example, step S150 may include: generating target content according to the second content material.

[0150] For example, as described above, after the first content material is acquired, the first content material may be displayed at a predetermined position near the first element frame, and the association relationship between the first element frame and the first content material may be displayed.

[0151] In this case, the step of acquiring the second content material based on the first content material may include:

[0152] In response to a user's instruction to add a fourth element frame, providing a fourth element frame in the canvas area;

[0153] In response to a user's associating operation on the fourth element frame and the first content material, connecting the fourth element frame with the first content material;

[0154] Receiving second user intention information input by the user in the fourth element box;

[0155] In response to the user's running operation on the fourth element box, a pre-set intelligent entity corresponding to the second user intention information is used to obtain and display the second content material based on the first content material, and the association relationship between the fourth element box and the obtained second content material is displayed to present the information flow of obtaining the second content material.

[0156] Specifically, the fourth element box can be added to the canvas area in a similar manner to the above-described method of adding the first element box, for example: Fig.13A Elements in box 239.

[0157] The user's associating operation on the fourth element frame and the first content material may refer to forming a contextual relationship between the first content material and the fourth element frame, and performing corresponding processing on the first content material when the fourth element frame is running. As an example, the associating operation may include connecting the fourth element frame with the first content material through a graphic such as an arrow or a connecting line, such as Fig.13A As shown, the first content material can be connected to the fourth element box by adding an arrow.

[0158] The second user intention information may include, but is not limited to, user-defined content, target agent information, pre-generated content material information, etc. Fig.13A As shown, the second user intention information may include user-defined content "shorten the above text to within 100 words".

[0159] In response to the user's operation on the fourth element frame, the agent corresponding to the second user intention information can be used, for example, Fig.13AIn the example of , the user does not specify a target agent, and the default agent can be used to obtain and display the second content material based on the first content material, and to display the association relationship between the third element frame and the obtained second content material, so as to present the information flow of obtaining the second content material. Fig. 13B As shown, the second content material can be displayed in the new element frame 2310, and the association relationship between the fourth element frame and the acquired second content material (e.g., element frame 2310) can be represented by graphics such as arrows or connecting lines. In this way, target content can be further generated based on the second content material.

[0160] Through the above method, the user can add a new element box as needed after obtaining the first content material, so as to further generate the second content material based on the first content material, so that the generation of content material is more flexible, the user has a higher degree of freedom in operation, and the complete information flow can be visualized so that the user can intuitively understand the generation process of the content material.

[0161] In another example, the content generation method may further include:

[0162] Provide a third element frame in the canvas area;

[0163] A program interface of a target program receiving user input in a third element frame;

[0164] In response to the user's operation on the third element frame, displaying the interface of the target program in the third element frame;

[0165] In response to the user's access operation to the target program in the third element frame, the content in the target program is loaded into the canvas area, or the content in the canvas area is uploaded to the target program.

[0166] Specifically, if Fig.14 As shown, the program interface of the target program, such as the URL address of the program, can be entered in the third element box 2311; in response to the user triggering the running operation of the third element box, the interface of the target program can be displayed in the third element box to allow the user to access the target program through the element box in the current interactive interface.

[0167] As an example, the target program can be accessed through the element box in the current interactive interface in the following way: using parent-child page communication technology, the large model application is set as an inline frame for two-way communication in the interactive interface; through interface authorization, access and read permissions for the target program are obtained.

[0168] Specifically, in the embodiments of the present disclosure, the free canvas area supports registering any third-party tool / web page / application as a widget component (or data block) through a URL. Unlike the traditional embedded web page solution in the related art, the widget registered by the third-party tool / web page / application can be implemented as a component of the canvas area and can actually run in the workflow in the following two ways: on the one hand, a large model application of open source front-end code (such as dify) can be used, and the large model application can be packaged as an iframe component that can communicate bidirectionally in the interactive interface through the "parent-child page communication" technology; on the other hand, the access and reading permissions of third-party applications such as Feishu can be granted to the content generation platform through interface authorization, thereby realizing an iframe component that can communicate bidirectionally.

[0169] In this example, the second target content may be generated according to the content in the target program.

[0170] In this way, an access interface of a third-party program can be provided to upload local content to the third-party program or apply the content in the third-party program to the current content generation, thereby making the content generation more flexible. The above describes an example process of generating content material and target content using a canvas area. In the above process, the process of obtaining the first content material, obtaining the second content material, and generating the target content all form an information flow.

[0171] Specifically, information flow refers to the process of forming contextual information during the interaction between users and agents. Each information flow can include at least two element boxes. One or more information flows can be formed in the canvas area. Different information flows are independent of each other. When executing tasks in any information flow, the agent can only obtain the contextual information in the current information flow, but cannot obtain information in other information flows.

[0172] For the information flow in the canvas area, the content generation method may also include: in response to a user's editing operation on the information flow, adjusting the association relationship, user intent information or content material information in the information flow based on the editing operation; and / or, in response to a user's deletion operation on the information flow, deleting the information flow.

[0173] Specifically, in the embodiments of the present disclosure, the user is allowed to adjust the contextual relationship within the information flow, and the user is allowed to associate different information flows. As an example, the user's editing operation on the information flow may include but is not limited to: adjusting the association relationship between element boxes in the information flow; the content of each element box; inserting or deleting an element box at any position in the information flow.

[0174] For example, Fig.15As shown, the canvas area may include a first information stream and a second information stream in parallel. In response to a user's editing operation on the information stream, an element box 2312 in the first information stream and an element box 2313 in the second information stream may be associated with a new element box 2314. In response to a user's running operation on the element box 2314, target content may be generated based on the first information stream and the second information stream.

[0175] In the dialogue process of existing large models such as ChatGPT, only linear interaction or dialogue between users and agents is supported. If you are not satisfied with a certain answer or output of the agent, you can only re-execute the current dialogue, and you cannot freely edit, modify, or combine historical interactive information flows. For complex content generation tasks, this single linear planar information flow cannot meet the needs. In the above process, users can edit the information flow, such as modifying the association between element boxes within the information flow, inserting or deleting element boxes at any position in the information flow, etc. In this way, the linear interaction mode of the existing large model can be broken through, and two-dimensional editable information flow editing can be realized.

[0176] In addition, in an embodiment of the present disclosure, in response to a user's association operation on any two element boxes in the canvas area (including an element box that accepts user input and an element box that displays content materials or target content), an association relationship between the two element boxes can be established, and contextual information between the contents of the two element boxes can be formed.

[0177] In addition, in the embodiment of the present disclosure, all element boxes on the canvas support user wake-up for further interaction. For example, in response to the user's agent wake-up operation on the target element box, such as clicking Figure 2 The wakeup control 272 "Ask AI" shown in the figure can use the agent specified in the agent wakeup operation to perform an operation corresponding to the specified agent on the content in the target element box. As an example, the operation corresponding to the specified agent may include, but is not limited to, improving grammar, explaining the selected area content, translating, rewriting the tone, improving writing, expanding the copy, simplifying the copy, continuing the content, etc.

[0178] In addition, according to an embodiment of the present disclosure, the content generation method may further include: in response to a user's detail display operation on a target element box in the canvas area, displaying relevant data and / or deduction logic corresponding to the target element box.

[0179] Specifically, if Figure 2 As shown, the user can perform a detail display operation for any element box, for example, by clicking the preset operation control 273 "Show Detail", the relevant data and / or deduction logic corresponding to the target element box can be displayed. Here, the deduction logic can refer to the process or basis for obtaining the content in the target element box, for example Fig.16 As shown, the statistical data based on which the content is generated can be displayed.

[0180] Through the above method, users can understand the content logic and underlying data of the content generated by the intelligent agent to determine whether the content generated by the intelligent agent is consistent with the facts or whether it is close to current needs.

[0181] In addition, according to an embodiment of the present disclosure, the content generation method may further include: in response to a user's selection operation on a target element frame in the canvas area, displaying at least one prediction information corresponding to the target element frame at a preset position near the target element frame, the prediction information including the next operation that the user may perform on the target element frame or the question that the user may ask about the target element frame; in response to the user's selection operation on the prediction information, performing an operation corresponding to the prediction information selected by the user or answering the question corresponding to the prediction information selected by the user. Fig.17 As shown, the prediction information may include generating a mind map, and in response to the user selecting the prediction information, a mind map may be generated for the current element frame.

[0182] In addition, according to an embodiment of the present disclosure, the content generation method may further include: in response to another user's editing operation on the target element frame, updating the result of the editing operation in the canvas area of ​​the current user. Specifically, multiple users can access the same canvas area at the same time, and the editing operations of different users on the element frame can be synchronized. In this way, it is possible to support multiple people to collaborate online to generate target content.

[0183] According to the content generation method of the embodiment of the present disclosure, the freedom of interaction between users and intelligent agents can be improved, and users can interact with the output of the intelligent agent at any node in the content generation process, thereby improving and optimizing the generation of content materials so that the generation of target content is more in line with user expectations.

[0184] In a second aspect, an exemplary embodiment of the present disclosure provides a content generation device, such as Fig.18 As shown, the content generating device includes a display unit 1810 , a providing unit 1820 , a receiving unit 1830 , an acquiring unit 1840 and a generating unit 1850 .

[0185] The display unit 1810 is configured to display a user interaction interface, which includes a canvas area.

[0186] The providing unit 1820 is configured to provide at least one element box in the canvas area, wherein the element box is used to interact with a preset intelligent agent, and the at least one element box includes a first element box.

[0187] The receiving unit 1830 is configured to receive first user intention information input by the user in the first element box.

[0188] The acquisition unit 1840 is configured to respond to the user's running operation on the first element frame, use the pre-set intelligent agent corresponding to the first user intention information, and acquire the first content material according to the first user intention information.

[0189] The generating unit 1850 is configured to generate target content according to the first content material.

[0190] As an example, the providing unit 1820 is further configured to: in response to a user's operation of adding a first element frame in the canvas area, provide a first element frame in the canvas area.

[0191] As an example, the content generating device also includes a display unit, which is configured to: display a running control at a predetermined position near the first element frame; the acquisition unit is also configured to: respond to a user's click operation on the running control, utilize a pre-set intelligent entity corresponding to the first user intention information, and acquire the first content material according to the first user intention information.

[0192] As an example, the content generating device further includes a relationship display unit, which is further configured to display the acquired first content material at a predetermined position near the first element frame after the acquisition unit acquires the first content material, and to display the association relationship between the first element frame and the acquired first content material.

[0193] As an example, the first user intention information includes target agent information, and the target agent is used to obtain the first content material.

[0194] As an example, the generating unit 1850 is further configured to: provide a robot dialogue window in which a dialog box is provided; receive a content generating instruction input by a user through the dialog box; and generate target content according to the first content material based on the content generating instruction.

[0195] As an example, the canvas area includes multiple acquired first content materials; wherein the generation unit is further configured to: if the content generation instruction specifies a first content material specifically introduced by the user for generating the target content among multiple first content materials, generate the target content according to the first content material specifically introduced by the user; or, if the content generation instruction does not specify a first content material specifically introduced by the user for generating the target content among multiple first content materials, generate the target content according to all the first content materials in the canvas area.

[0196] As an example, the providing unit 1820 is also configured to: in response to a user's instruction to introduce a target template, display the target template in the canvas area, wherein the target template includes multiple element boxes, and the multiple element boxes include a first element box and a second element box; wherein the generating unit is also configured to: receive a content generation instruction input by the user in the second element box; in response to the user's running operation on the second element box, generate the target content according to the first content material by using a pre-set intelligent agent corresponding to the content generation instruction.

[0197] As an example, in the target template, a predetermined position near each element box displays user operation prompt information corresponding to the element box.

[0198] As an example, the acquisition unit 1840 is also configured to: utilize a pre-set intelligent agent corresponding to the first user intention information, acquire multiple data resources according to the first user intention information, and display the multiple data resources in the canvas area; in response to the user's selection operation of a target data resource among the multiple data resources, use the selected target data resource as the first content material.

[0199] As an example, the first user intention information includes target workflow information, the target workflow is used to obtain the first content material, the target workflow includes multiple subtasks and the sequential execution relationship between the multiple subtasks; wherein the acquisition unit 1840 is also configured to: use a pre-set intelligent agent corresponding to the target workflow to run the target workflow, so as to execute the corresponding subtasks according to the sequential execution relationship of the subtasks in the target workflow, and generate the first content material.

[0200] As an example, the acquisition unit 1840 is also configured to: generate a first content material by executing at least one subtask execution operation, wherein the subtask execution operation includes: providing a current element box; receiving current user intention information input by a user, the current user intention information being associated with the content material acquired in the last operation; in response to the user's running operation on the current element box, utilizing a pre-set intelligent agent corresponding to the current user intention information, to acquire and display the current content material based on the current user intention information and the content material acquired in the last operation, wherein, when executing the first subtask, the current element box is the first element box, the current user intention information is the first user intention information, and the content material acquired in the last operation is empty; when executing the last subtask, the current content material is the first content material.

[0201] As an example, the content generating device also includes a program access unit, which is configured to: provide a third element box in the canvas area; receive a program interface of a target program input by a user in the third element box; display the interface of the target program in the third element box in response to a user's running operation on the third element box; load the content in the target program into the canvas area, or upload the content in the canvas area to the target program in response to a user's access operation to the target program in the third element box.

[0202] As an example, the generating unit 1850 is further configured to: generate second target content according to the content in the target program.

[0203] As an example, the acquisition unit 1840 is further configured to acquire the second content material based on the first content material after acquiring the first content material; wherein the generation unit is further configured to generate the target content according to the second content material.

[0204] As an example, the content generation device also includes a relationship display unit, which is configured to: after the acquisition unit acquires the first content material, display the first content material at a predetermined position near the first element box, and display the association relationship between the first element box and the first content material; wherein the acquisition unit is further configured to: provide a fourth element box in the canvas area in response to the user's fourth element box addition instruction; connect the fourth element box with the first content material in response to the user's association operation on the fourth element box and the first content material; receive second user intention information input by the user in the fourth element box; in response to the user's operation on the fourth element box, acquire and display the second content material according to the first content material using a pre-set intelligent agent corresponding to the second user intention information, and display the association relationship between the fourth element box and the acquired second content material, so as to present the information flow of acquiring the second content material.

[0205] As an example, the content generating device also includes an information flow editing unit, which is configured to: in response to a user's editing operation on the information flow, adjust the association relationship, user intention information or content material information in the information flow based on the editing operation; and / or, in response to a user's deletion operation on the information flow, delete the information flow.

[0206] As an example, the content generation device also includes a detail display unit, which is configured to: in response to a user's detail display operation on a target element box in the canvas area, display relevant data and / or deduction logic corresponding to the target element box.

[0207] As an example, the content generating device also includes a template generating unit, which is configured to: provide one or more element boxes in the canvas area in response to a user's operation of adding one or more element boxes in the canvas area; receive a first editing operation of the user on the one or more element boxes themselves and / or a second editing operation on the association relationship between the element boxes; and save the one or more element boxes as a template for generating content in response to a user's instruction to create a template.

[0208] on the other hand, Fig.18 The various units shown may also be implemented by hardware, software, firmware, middleware, microcode, or any combination thereof. When implemented by software, firmware, middleware, or microcode, the program code or code segment for performing the corresponding operation may be stored in a computer-readable medium such as a storage medium, so that the processor may perform the corresponding operation by reading and running the corresponding program code or code segment.

[0209] According to a third aspect of the present disclosure, a computing device is provided, comprising: a processor; and a memory for storing processor-executable instructions, wherein the processor-executable instructions, when executed by the processor, cause the processor to execute a content generation method according to an embodiment of the present disclosure.

[0210] Specifically, the computing device can be deployed in a server or client, or can be deployed on a node device in a distributed network environment. In addition, the computing device can be a PC, a tablet device, a personal digital assistant, a smart phone, a web application, or other device capable of executing the above instruction set.

[0211] Here, the computing device is not necessarily a single computing device, but may also be any device or circuit collection that can execute the above instructions (or instruction sets) individually or jointly. The computing device may also be part of an integrated control system or system manager, or may be configured as a portable electronic device that is interconnected with a local or remote (e.g., via wireless transmission) interface.

[0212] In a computing device, a processor may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller, or a microprocessor. By way of example and not limitation, a processor may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.

[0213] According to the exemplary embodiment of the present disclosure, some operations described in the content generation method may be implemented by software, some operations may be implemented by hardware, and further, these operations may be implemented by a combination of software and hardware.

[0214] The processor may execute instructions or codes stored in one of the memories, which may also store data. Instructions and data may also be sent and received over a network via a network interface device, which may employ any known transmission protocol.

[0215] The memory may be integrated with the processor, for example, RAM or flash memory is arranged within an integrated circuit microprocessor or the like. In addition, the memory may include a separate device, such as an external disk drive, a storage array, or any other storage device that can be used by a database system. The memory and the processor may be operatively coupled, or may communicate with each other, such as through an I / O port, a network connection, etc., so that the processor can read files stored in the memory.

[0216] In addition, the computing device may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, a mouse, a touch input device, etc.) All components of the computing device may be connected to each other via a bus and / or a network.

[0217] The content generation method according to the exemplary embodiment of the present disclosure may be described as various interconnected or coupled functional blocks or functional diagrams. However, these functional blocks or functional diagrams may be equally integrated into a single logical device or operate according to non-precise boundaries.

[0218] Therefore, refer to Figures 1 to 17 The described content generation method may be implemented by a system including at least one computing device and at least one storage device storing instructions.

[0219] According to a fourth aspect of the present disclosure, a computer-readable storage medium storing instructions is provided. When the instructions are executed by at least one computing device, the at least one computing device is prompted to execute a content generation method according to an embodiment of the present disclosure.

[0220] According to an exemplary embodiment of the present disclosure, at least one computing device is a computing device for executing a content generation method according to an exemplary embodiment of the present disclosure, and a computer executable instruction set is stored in the storage device. When the computer executable instruction set is executed by the at least one computing device, the execution reference Figures 1 to 17 The described content generation method.

[0221] According to a fifth aspect of the present disclosure, a system is provided comprising at least one computing device and at least one storage device storing instructions, wherein when the instructions are executed by the at least one computing device, the at least one computing device is prompted to execute a content generation method according to an embodiment of the present disclosure.

[0222] According to a sixth aspect of the present disclosure, a computer program product is provided, comprising instructions, which, when executed by at least one computing device, prompt the at least one computing device to execute a content generation method as an embodiment of the present disclosure.

[0223] The above describes various exemplary embodiments of the present disclosure, and it should be understood that the above description is only exemplary and not exhaustive, and the present disclosure is not limited to the disclosed exemplary embodiments. Without departing from the scope and spirit of the present disclosure, many modifications and changes are obvious to those of ordinary skill in the art. Therefore, the scope of protection of the present disclosure should be based on the scope of the claims.

Claims

1. A content generation method, characterized in that: The content generation method comprises: Displaying a user interaction interface, wherein the user interaction interface includes a canvas area; Providing at least one element frame in the canvas area, wherein the element frame is used to interact with a preset intelligent agent, and the at least one element frame includes a first element frame; Receiving first user intention information input by the user in the first element box; In response to a user's operation on the first element frame, using a pre-set agent corresponding to the first user intention information, and acquiring a first content material according to the first user intention information; Generate target content according to the first content material.

2. The content generation method according to claim 1, characterized in that: Generating target content according to the first content material includes: Providing a robot dialogue window, wherein a dialog box is provided in the robot dialogue window; Receiving a content generation instruction input by a user through the dialog box; Based on the content generation instruction, the target content is generated according to the first content material.

3. The content generation method according to claim 2, characterized in that: The canvas area includes a plurality of first content materials that have been acquired; The generating the target content according to the first content material based on the content generating instruction includes: If the content generation instruction specifies a first content material specifically introduced by the user and used to generate the target content among the plurality of first content materials, generating the target content according to the first content material specifically introduced by the user; or, If the content generation instruction does not specify a first content material specifically introduced by the user among the plurality of first content materials for generating the target content, the target content is generated according to all the first content materials in the canvas area.

4. The content generation method according to claim 1, characterized in that: Providing at least one element frame in the canvas area includes: In response to a user's instruction to introduce a target template, displaying the target template in the canvas area, wherein the target template includes a plurality of element frames, and the plurality of element frames include the first element frame and the second element frame; Generating target content according to the first content material includes: Receiving a content generation instruction input by a user in the second element box; In response to the user's operation on the second element frame, the target content is generated according to the first content material by using a pre-set intelligent agent corresponding to the content generation instruction.

5. The content generation method according to claim 1, characterized in that: The first user intention information includes target workflow information, the target workflow is used to obtain the first content material, and the target workflow includes multiple subtasks and a sequential execution relationship between the multiple subtasks; The using a preset agent corresponding to the first user intention information to obtain the first content material according to the first user intention information includes: The target workflow is run by using a preset intelligent agent corresponding to the target workflow to execute corresponding subtasks according to the sequential execution relationship of the subtasks in the target workflow to generate the first content material.

6. The content generation method according to claim 1, characterized in that: The content generation method further includes: Providing a third element frame in the canvas area; Receiving a program interface of a target program input by a user in the third element frame; In response to a user's operation on the third element frame, displaying an interface of the target program in the third element frame; In response to a user's access operation to the target program in the third element frame, the content in the target program is loaded into the canvas area, or the content in the canvas area is uploaded to the target program.

7. The content generation method according to claim 1, characterized in that: After acquiring the first content material, the content generation method further includes: Based on the first content material, obtaining a second content material; Generating target content according to the first content material includes: The target content is generated according to the second content material.

8. A content generating device, characterized in that: The content generating device comprises: A display unit, configured to display a user interaction interface, wherein the user interaction interface includes a canvas area; A providing unit, configured to provide at least one element frame in the canvas area, wherein the element frame is used to interact with a preset intelligent agent, and the at least one element frame includes a first element frame; A receiving unit, configured to receive first user intention information input by a user in the first element box; an acquisition unit, configured to, in response to a user's operation on the first element frame, acquire a first content material according to the first user intention information by using a pre-set agent corresponding to the first user intention information; The generating unit is configured to generate target content according to the first content material.

9. A computing device, characterized in that: The computing device comprises: processor; a memory for storing instructions executable by the processor, When the processor executable instructions are executed by the processor, the processor is prompted to execute the content generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing instructions, characterized in that: When the instructions are executed by at least one computing device, the at least one computing device is prompted to perform the content generation method according to any one of claims 1 to 7.

Images