Workflow processing method and device, electronic equipment and storage medium

By displaying guidance information in the target application and automatically jumping to the next work stage, the problem of cumbersome operations in traditional workflow processing is solved, and operations are simplified and efficiency is improved.

CN120704782APending Publication Date: 2025-09-26TENCENT TECHNOLOGY (SHENZHEN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510789868.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-12
Publication Date
2025-09-26

AI Technical Summary

Technical Problem

In traditional workflow processing, users need to spend time understanding the overall flow of guidance information, and the memory retention rate of operation steps is low, which makes the operation cumbersome and reduces processing efficiency.

Method used

By displaying guidance information in the target application, automatically jumping to the next work stage, and displaying guidance information in the current application until the workflow is completed, the operation process is simplified.

Benefits of technology

You can view guidance information without frequently switching applications, simplifying operations and improving workflow processing efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120704782A_ABST
    Figure CN120704782A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a workflow processing method and device, electronic equipment and a storage medium, and the method comprises the steps: responding to an operation of starting a workflow, jumping to a target application corresponding to a first working stage in the workflow, and processing each working stage of the workflow by the corresponding target application; guiding information is displayed in the currently-skipped target application, wherein the guiding information is used for indicating target operation to be executed when the currently-skipped target application processes the corresponding working stage; when it is detected that the target operation in the currently-skipped target application is all executed, skipping to the target application corresponding to the next working stage, displaying the guide information again in the currently-skipped target application, and executing the corresponding target operation until the workflow is ended, and when it is detected that the target operation in the currently-skipped target application is all executed, skipping to the target application corresponding to the next working stage, displaying the guide information again in the currently-skipped target application, according to the embodiment of the invention, the operation can be simplified, so that the workflow processing efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] At present, some complex tasks are often implemented in the form of workflows, which require the collaborative completion of multiple target applications. Traditional guidance information is usually published in the guidance application in the form of pictures, texts, or videos. Users need to spend time to understand the overall process of the guidance information first, and the memory retention rate of the operation steps is low. Accordingly, during the processing of the workflow, users need to switch to the corresponding target application according to the guidance information, and frequently return to the guidance application to view the guidance information, which makes the operation cumbersome and reduces the processing efficiency of the workflow. Summary of the Invention

[0003] The following is an overview of the subject matter described in detail in this disclosure. This overview is not intended to limit the scope of the claims.

[0004] The embodiments of the present disclosure provide a workflow processing method, apparatus, electronic device, and storage medium, which can simplify operations and thus improve workflow processing efficiency.

[0005] In one aspect, an embodiment of the present disclosure provides a workflow processing method, comprising:

[0006] In response to an operation of starting a workflow, jumping to a target application corresponding to a first work phase in the workflow, wherein the work phases of the workflow are respectively processed by the corresponding target application;

[0007] Displaying guidance information in the target application currently jumped to, wherein the guidance information is used to indicate a target operation to be performed by the target application currently jumped to when processing the corresponding working phase;

[0008] Whenever it is detected that the target operation in the target application currently jumped to has been completed, jump to the target application corresponding to the next work stage, display the guidance information again in the target application currently jumped to and execute the corresponding target operation until the workflow is completed.

[0009] On the other hand, the present disclosure also provides a workflow processing device, including:

[0010] A first processing module is configured to jump to a target application corresponding to a first work stage in the workflow in response to an operation of starting the workflow, wherein each work stage of the workflow is processed by the corresponding target application;

[0011] a second processing module, configured to display guidance information in the target application currently redirected, wherein the guidance information is used to indicate a target operation to be performed by the target application currently redirected when processing the corresponding working phase;

[0012] The third processing module is used to jump to the target application corresponding to the next work stage whenever it is detected that the target operation in the target application currently jumped to has been executed, and to display the guidance information again in the target application currently jumped to and execute the corresponding target operation until the workflow is completed.

[0013] Furthermore, the working phase includes a plurality of task nodes in order, and the second processing module is specifically used to:

[0014] Displaying a floating window in the target application currently jumped to, and displaying guidance information corresponding to the first task node in the floating window;

[0015] Whenever it is detected that the target operation corresponding to the current task node is completed, the guidance information in the floating window is updated to the guidance information corresponding to the next task node.

[0016] Furthermore, the second processing module is specifically configured to:

[0017] Performing page element detection on the target application page currently redirected to obtain a detection result;

[0018] Whenever the detection result indicates that the target page element is displayed in the application page, it is determined that the target operation corresponding to the current task node has been executed, and the guidance information in the floating window is updated to the guidance information corresponding to the next task node, and the target page element is the page element corresponding to the current task node.

[0019] Furthermore, the second processing module is specifically configured to:

[0020] Performing page element detection on the application page of the target application currently jumped to obtain a current element identifier of the current page element, where the current page element is a page element currently displayed on the application page;

[0021] The preset element identifier of the target page element is obtained, and the current element identifier is matched with the preset element identifier to obtain a detection result.

[0022] Furthermore, the second processing module is specifically configured to:

[0023] Performing consistency matching on the current element identifier and the preset element identifier to obtain a first matching result;

[0024] Obtaining current operation instruction information of a current operation, where the current operation is an operation triggered before generating the current target page element and after generating the previous target page element;

[0025] Obtaining preset operation instruction information of the target operation, performing consistency matching between the current operation instruction information and the preset operation instruction information to obtain a second matching result;

[0026] A logical judgment is performed based on the first matching result and the second matching result to obtain a detection result.

[0027] Furthermore, if the target application currently jumped to is a text generation application, the target operations corresponding to the multiple task nodes include, in sequence, a first input operation, a text generation operation, and a generation result copy operation, and the target page elements include a first prompt text, a generation result copy control, or a copy success prompt, the above-mentioned second processing module is specifically used to:

[0028] When the detection result indicates that the first prompt text is displayed on the application page, determining that the first input operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the text generation operation;

[0029] When the detection result indicates that the generation result copy control is displayed in the application page, determining that the text generation operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the generation result copy operation;

[0030] Furthermore, the third processing module is specifically configured to:

[0031] When the detection result indicates that the copy success prompt is displayed in the application page, it is determined that the target operations in the text generation application have been completed, and the process jumps to the target application corresponding to the next work stage. The guidance information is displayed again in the target application currently jumped to and the corresponding target operation is executed until the workflow is completed.

[0032] Furthermore, if the target application corresponding to the next work stage is an image generation application, the target operations corresponding to the multiple task nodes include, in sequence, a second input operation, an image generation operation, and a generation result saving operation, and the target page elements include a second prompt text generated by the text generation application, a generation result saving control, or a save success prompt, the third processing module is specifically configured to:

[0033] When the detection result indicates that the copy success prompt is displayed on the application page, determining that the target operations in the text generation application are all completed, and jumping to the image generation application;

[0034] When the detection result indicates that the second prompt text is displayed on the application page, determining that the second input operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the image generation operation;

[0035] When the detection result indicates that the generation result saving control is displayed on the application page, determining that the image generation operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the generation result saving operation;

[0036] When the detection result indicates that the save success prompt is displayed in the application page, it is determined that the target operations in the image generation application have been completed, and the process jumps to the target application corresponding to the next work stage. The guidance information is displayed again in the target application currently jumped to and the corresponding target operation is executed until the workflow is completed.

[0037] Furthermore, if the target application corresponding to the next work stage is a video generation application, the target operations corresponding to the multiple task nodes include, in sequence, a third input operation, a video generation operation, a cover setting operation, and a video export operation, and the target page elements include the third prompt text, a cover setting control, a cover image generated by the image generation application, or an export success prompt, the third processing module is specifically configured to:

[0038] When the detection result indicates that the save success prompt is displayed on the application page, determining that the target operations in the image generation application are all executed, and jumping to the video generation application;

[0039] When the detection result indicates that the third prompt text is displayed on the application page, determining that the third input operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the video generation operation;

[0040] When the detection result indicates that the cover setting control is displayed in the application page, determining that the video generation operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the cover setting operation;

[0041] When the detection result indicates that the cover image is inserted into the application page, determining that the cover setting operation corresponding to the currently displayed guide information is completed, and updating the guide information in the floating window to the guide information corresponding to the video export operation;

[0042] When the detection result indicates that the export success prompt is displayed in the application page, it is determined that all the target operations in the video generation application have been completed, and the workflow ends.

[0043] Furthermore, the workflow processing device further includes a text insertion module, which is specifically configured to:

[0044] In response to a triggering operation on a prompt text input box in the text generation application, displaying an input keyboard, and displaying a preset prompt text template on the input keyboard;

[0045] In response to a triggering operation on the prompt text template, the prompt text template is inserted into the prompt text input box as the first prompt text.

[0046] Furthermore, the first processing module is specifically configured to:

[0047] Running a workflow processing application, wherein the workflow processing application is provided with a workflow start control;

[0048] In response to a triggering operation on the workflow start control, displaying a permission configuration page, wherein the permission configuration page is provided with a permission start control;

[0049] In response to the triggering operation of the permission opening control, the permission to obtain target data is opened for the workflow processing application, and the process jumps to the target application corresponding to the first work stage in the workflow. The target data is used to generate the guidance information.

[0050] Furthermore, the first processing module is specifically configured to:

[0051] In response to a triggering operation on the workflow start control, displaying a permission guidance page, wherein the permission guidance page displays prompt information and is provided with a jump control, wherein the prompt information is used to indicate an operation to be performed when the permission to obtain the target data is enabled for the workflow processing application in the permission configuration page;

[0052] In response to a triggering operation on the jump control, the permission configuration page is displayed.

[0053] Furthermore, the workflow start control is set on the workflow start page of the workflow processing application. The workflow processing device further includes an application download module, which is specifically used to:

[0054] When all the target applications have been downloaded, a downloaded mark is displayed on the workflow start page, where the downloaded mark is used to indicate that all the target applications have been downloaded;

[0055] When there is at least one undownloaded application, a download control is displayed on the workflow start page, and in response to a triggering operation on the download control, the undownloaded application is downloaded, where the undownloaded application is the undownloaded target application.

[0056] On the other hand, an embodiment of the present disclosure further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned workflow processing method when executing the computer program.

[0057] On the other hand, an embodiment of the present disclosure further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is executed by a processor to implement the above-mentioned workflow processing method.

[0058] In another aspect, embodiments of the present disclosure further provide a computer program product, comprising a computer program stored in a computer-readable storage medium. A processor of an electronic device reads the computer program from the computer-readable storage medium and executes the computer program, causing the electronic device to implement the workflow processing method described above.

[0059] The disclosed embodiments include at least the following beneficial effects: by responding to the operation of starting a workflow, jumping to the target application corresponding to the first work stage in the workflow, automatically jumping to the first target application when processing the first work stage, and then displaying guidance information in the target application currently jumped, indicating the target operation to be performed by the target application currently jumped when processing the corresponding work stage through the guidance information. Since the target operations in the target application have all been executed, it means that the processing of the corresponding work stage is completed. Therefore, whenever it is detected that the target operations in the target application currently jumped have all been executed, jumping to the target application corresponding to the next work stage, displaying guidance information again in the target application currently jumped and executing the corresponding target operation, processing the new work stage through the next target application until the workflow is ended, automatically jumping to the corresponding target application when processing the new work stage, without manual operation, which can simplify operation, and quickly displaying guidance information in the corresponding target application during the processing of each work stage, which can realize quick viewing of guidance information without switching target applications during the processing of the workflow, which can simplify operation and thus improve the processing efficiency of the workflow.

[0060] Other features and advantages of the present disclosure will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practicing the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings are used to provide a further understanding of the technical solution of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the technical solution of the present disclosure and do not constitute a limitation to the technical solution of the present disclosure.

[0062] Figure 1 A schematic diagram of an optional implementation environment provided for an embodiment of the present disclosure;

[0063] Figure 2 An optional flowchart of the workflow processing method provided in the embodiment of the present disclosure;

[0064] Figure 3 An optional page diagram of the processing flow of the first input task node and the text generation task node provided in the embodiment of the present disclosure;

[0065] Figure 4 An optional page diagram of the processing flow of the copy text task node provided in the embodiment of the present disclosure;

[0066] Figure 5 An optional page diagram of a partial processing flow of a second input task node provided by an embodiment of the present disclosure;

[0067] Figure 6 An optional page diagram of a partial processing flow of the second input task node and the image generation task node provided in an embodiment of the present disclosure;

[0068] Figure 7 An optional page diagram of a partial processing flow of a second input task node and a picture generation task node, and a processing flow of a save picture task node provided in an embodiment of the present disclosure;

[0069] Figure 8 An optional page diagram of a partial processing flow of the third input task node provided in an embodiment of the present disclosure;

[0070] Figure 9 An optional page diagram of a partial processing flow of the third input task node and a partial processing flow of the video generation task node provided in an embodiment of the present disclosure;

[0071] Figure 10 An optional page diagram of a partial processing flow of a video generation task node and a partial processing flow of a cover setting task node provided in an embodiment of the present disclosure;

[0072] Figure 11 An optional page diagram of a partial processing flow of a cover setting task node provided in an embodiment of the present disclosure;

[0073] Figure 12 An optional page diagram of a partial processing flow of a cover setting task node and a partial processing flow of a video export task node provided in an embodiment of the present disclosure;

[0074] Figure 13 An optional page diagram of a partial processing flow of a video export task node provided in an embodiment of the present disclosure;

[0075] Figure 14 A schematic diagram of an optional page in the process of starting a workflow in a workflow processing application provided by an embodiment of the present disclosure;

[0076] Figure 15 A schematic diagram of an optional page in the permission opening process provided in an embodiment of the present disclosure;

[0077] Figure 16 A schematic diagram of an optional architecture of the workflow processing method provided in the embodiment of the present disclosure;

[0078] Figure 17 An optional structural diagram of a workflow processing device provided in an embodiment of the present disclosure;

[0079] Figure 18 A partial structural block diagram of a terminal provided in an embodiment of the present disclosure;

[0080] Figure 19 A partial structural block diagram of the server provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0081] In order to make the purpose, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present disclosure and are not intended to limit the present disclosure.

[0082] It should be noted that in various specific embodiments of the present disclosure, when it comes to the need to perform relevant processing based on data related to the characteristics of the target object, such as the target object attribute information or attribute information set, the permission or consent of the target object will be obtained first, and the collection, use and processing of these data will comply with relevant laws, regulations and standards. Among them, the target object can be a user. In addition, when the embodiment of the present disclosure needs to obtain the attribute information of the target object, the separate permission or separate consent of the target object will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the separate permission or separate consent of the target object, the necessary target object-related data for the normal operation of the embodiment of the present disclosure will be obtained.

[0083] In the embodiments of the present disclosure, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0084] At present, some complex tasks are often implemented in the form of workflows, which require the collaborative completion of multiple target applications. Traditional guidance information is usually published in the guidance application in the form of pictures, texts, or videos. Users need to spend time to understand the overall process of the guidance information first, and the memory retention rate of the operation steps is low. Accordingly, during the processing of the workflow, users need to switch to the corresponding target application according to the guidance information, and frequently return to the guidance application to view the guidance information, which makes the operation cumbersome and reduces the processing efficiency of the workflow.

[0085] Based on this, the embodiments of the present disclosure provide a workflow processing method, apparatus, electronic device, and storage medium, which can simplify operations and thus improve workflow processing efficiency.

[0086] Reference Figure 1 , Figure 1 This is a schematic diagram of an optional implementation environment provided for an embodiment of the present disclosure, wherein the implementation environment includes a terminal 101 and a server 102, wherein the terminal 101 and the server 102 are connected via a communication network.

[0087] Exemplarily, the terminal 101 can jump to the target application corresponding to the first work stage in the workflow in response to the operation of starting the workflow, and each work stage of the workflow is processed by the corresponding target application respectively; display guidance information in the target application currently jumped, and the guidance information is used to indicate the target operation to be performed by the target application currently jumped when processing the corresponding work stage; whenever it is detected that the target operation in the target application currently jumped has been executed, jump to the target application corresponding to the next work stage, display the guidance information again in the target application currently jumped and execute the corresponding target operation until the workflow is ended; wherein, during the processing of each target application, the terminal 101 can send a data processing request to the server 102, so that the server 102 determines the data processing result based on the data processing request, and then the server 102 sends the data processing result to the terminal.

[0088] Terminal 101 jumps to the target application corresponding to the first work stage in the workflow in response to the operation of starting the workflow, so as to automatically jump to the first target application when processing the first work stage, and then displays guidance information in the target application currently jumped to, and indicates the target operation to be performed by the target application currently jumped to when processing the corresponding work stage through the guidance information. Since the target operations in the target application have been completed, it means that the corresponding work stage processing is completed. Therefore, whenever it is detected that the target operations in the target application currently jumped to are completed, it jumps to the target application corresponding to the next work stage, and displays guidance information again in the target application currently jumped to and executes the corresponding target operation. The new work stage is processed through the next target application until the workflow is ended, so as to automatically jump to the corresponding target application when processing the new work stage, without manual operation, which can simplify operation, and in the processing process of each work stage, the guidance information can be quickly displayed in the corresponding target application, so that during the processing of the workflow, the guidance information can be quickly viewed without switching the target application, which can simplify operation and thus improve the processing efficiency of the workflow.

[0089] Server 102 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Furthermore, server 102 can be a node server in a blockchain network.

[0090] The terminal 101 may be a mobile phone, a computer, an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, etc., but is not limited thereto. The terminal 101 and the server 102 may be connected directly or indirectly via wired or wireless communication, which is not limited in the present embodiment.

[0091] Reference Figure 2 , Figure 2 An optional flow chart of a workflow processing method provided in an embodiment of the present disclosure is provided. The workflow processing method can be executed by a server, or by a terminal, or by a server in cooperation with a terminal. The workflow processing method includes but is not limited to the following steps 201 to 203.

[0092] Step 201: In response to the operation of starting a workflow, jump to the target application corresponding to the first work stage in the workflow.

[0093] Among them, the workflow is an abstract and general description of the business rules between the workflow and its various operation steps. The workflow can include multiple ordered work stages. Each work stage of the workflow is processed by the corresponding target application, and the corresponding work tasks can be completed by the corresponding target application in each work stage. For example, in a video creation scenario, the workflow of video creation may include an ordered text generation work stage, an image generation work stage, and a video generation work stage. The target application may include an ordered text generation application, an image generation application, and a video generation application. The text generation work stage is processed by the text generation application, and the text generation task is completed by the text generation application. The image generation work stage is processed by the image generation application, and the image generation task is completed by the image generation application. The video generation work stage is processed by the video generation application, and the video generation task is completed by the video generation application. In addition, other types of workflows can also be started. In other types of workflows, other types of target applications can be used. The embodiments of the present disclosure are not limited here.

[0094] It should be noted that the operation of starting a workflow can be in various forms. For example, the operation of starting a workflow can include clicking a start control of the workflow or entering a start instruction of the workflow. In addition, the operation of starting a workflow can be a single operation or a series of operations, which is not limited in the embodiments of the present disclosure.

[0095] It can be understood that by starting a workflow, it is first necessary to process the first work stage in the workflow, so jump to the target application corresponding to the first work stage, and start processing the first work stage of the workflow through the first target application, so as to automatically jump to the first target application when processing the first work stage.

[0096] Step 202: Displaying guidance information in the current target application.

[0097] Among them, the guidance information is used to indicate the target operation to be performed by the target application of the current jump when processing the corresponding work stage. The form of the guidance information can be diverse. For example, the form of the guidance information can include text, image, video or audio, etc. Therefore, in addition to displaying guidance information in the form of text or image, the target application can also display preview content of guidance information in the form of video or audio, etc., and can also play guidance information in the form of video or audio, etc.; the target operation refers to the operation that needs to be performed in the corresponding target application when processing the work stage. The target operation can be a single operation or a series of operations. The type of target operation can include click operation, move operation or input operation, etc. In addition, the target operation of each work stage is set based on the corresponding target application, and the operations that different target applications need to perform when realizing their functions are usually different. Therefore, when the target applications corresponding to any two work stages are different, the target operations of these two work stages are usually different.

[0098] It can be understood that the guidance information can be a system-level message of the terminal, and the display process does not depend on the target application. The guidance information can also be application-level information displayed in the target application. The guidance information is displayed in the currently jumped target application, so that the guidance information can be presented simultaneously during the display of the currently jumped target application. The guidance information indicates the target operation to be performed by the currently jumped target application when processing the corresponding work stage. During the processing of the first work stage, the guidance information can be quickly viewed without switching the target application, which can simplify the operation.

[0099] Step 203: Whenever it is detected that the target operations in the currently jumped target application have been completed, jump to the target application corresponding to the next work stage, display the guidance information again in the currently jumped target application and execute the corresponding target operations until the workflow is completed.

[0100] Among them, it is detected that all target operations in the target application of the current jump have been executed, which means that the work stage corresponding to the target application of the current jump has been processed, and the next work stage in the workflow needs to be started, so it is necessary to jump to the target application corresponding to the next work stage.

[0101] It should be noted that when jumping to the target application corresponding to the next work stage, the guidance information needs to be displayed again in the target application currently jumped to, so that during the processing of the new work stage, the guidance information can be quickly viewed without switching the target application. Under the guidance of the guidance information, the corresponding target operation can be executed in the target application corresponding to the next work stage, which can simplify the operation. Executing the corresponding target operation means executing the target operation in the corresponding work stage through the target application currently jumped to.

[0102] Based on this, by responding to the operation of starting the workflow, jumping to the target application corresponding to the first work stage in the workflow, it is realized that the process automatically jumps to the first target application when processing the first work stage, and then the guidance information is displayed in the target application currently jumped. The guidance information indicates the target operation to be performed by the target application currently jumped when processing the corresponding work stage. Since the target operations in the target application have been completed, it means that the corresponding work stage processing is completed. Therefore, whenever it is detected that the target operations in the target application currently jumped have been completed, it jumps to the target application corresponding to the next work stage, and the guidance information is displayed again in the target application currently jumped and the corresponding target operation is executed. The new work stage is processed through the next target application until the workflow is ended, and it is realized that the process automatically jumps to the corresponding target application when processing the new work stage. No manual operation is required, which can simplify the operation. Moreover, the guidance information can be quickly displayed in the corresponding target application during the processing of each work stage, so that the guidance information can be quickly viewed during the processing of the workflow without switching the target application. This can simplify the operation and thus improve the processing efficiency of the workflow.

[0103] In one possible implementation, the working stage includes multiple task nodes in order, and guidance information is displayed in the target application of the current jump. Specifically, a floating window can be displayed in the target application of the current jump, and the guidance information corresponding to the first task node is displayed in the floating window; whenever it is detected that the target operation corresponding to the current task node is completed, the guidance information in the floating window is updated to the guidance information corresponding to the next task node.

[0104] Among them, the task node is the basic unit of the working stage, and each task node is used to indicate the specific working steps in the working stage. The ordered multiple task nodes define the overall execution logic of the working stage; for example, the text generation working stage may include a first input task node, a text generation task node, and a copy text task node, etc. The guidance information corresponding to the first input task node is used to indicate the input of the first prompt text, the guidance information corresponding to the text generation task node is used to indicate waiting for text generation, and the guidance information corresponding to the copy text task node is used to indicate the copy text generation result.

[0105] It should be noted that the floating window is displayed on top of the target application, that is, the display priority of the floating window is higher than the display priority of the target application. If the floating window is not completely transparent, the floating window located above can block the target application located below. The floating window supports movement or resizing. The floating window can be moved or scaled to avoid blocking the key areas of the target application, ensuring that the normal use of the target application is not affected. In addition, the floating window can be a system-level floating window independent of the target application, supporting cross-application display. The floating window can also be an interface component within the target application, displayed only within the application. The embodiments of this disclosure do not limit the specific form of the floating window.

[0106] Specifically, the types of target operations corresponding to the task node can be diverse. For example, the types of target operations can include active operations such as click operations, move operations, or input operations. The types of target operations can also include passive operations such as conditional waiting operations and event-driven operations. The target operation corresponding to the task node can be a single operation or a series of operations, which depends on the actual design of the task node. The embodiments of the present disclosure are not limited here.

[0107] It is worth noting that whenever it is detected that the target operation corresponding to the current task node is completed, the guidance information in the floating window is updated to the guidance information corresponding to the next task node. Specifically, whenever it is detected that the target operation corresponding to the current task node is completed, it is determined whether the current task node is the last task node of the current working stage;

[0108] If the current task node is not the last task node of the current working stage, the guidance information in the floating window is updated to the guidance information corresponding to the next task node; if the current task node is the last task node of the current working stage, it is determined whether the current working stage is the last working stage;

[0109] If the current working stage is not the last working stage, it is equivalent to detecting that the target operation corresponding to the last task node of the current working stage has been executed. It can be considered that the target operations in the target application of the current jump have been executed. At this time, jump to the target application corresponding to the next working stage, display the guidance information again in the target application of the current jump and execute the corresponding target operation; if the current working stage is the last working stage, it means that the target operation corresponding to the last task node of the last working stage has been detected and executed. At this time, the workflow ends.

[0110] It can be understood that after the workflow is started to jump to the target application corresponding to the first work stage in the workflow, a floating window is displayed in the target application currently jumped, so that the floating window can be presented simultaneously during the display of the target application currently jumped, and the guidance information corresponding to the first task node in the current work stage is displayed in the floating window, so that the currently displayed guidance information can accurately indicate the target operation to be performed when processing the current task node, without having to search for the target operation corresponding to the current task node from the full amount of guidance information, which can further simplify the operation, thereby further improving the processing efficiency of the workflow. Whenever it is detected that the target operation corresponding to the current task node has been executed, it means that the current task node has been processed and the next task node needs to be processed. At this time, the guidance information in the floating window is updated to the guidance information corresponding to the next task node, so that the guidance information is automatically updated when processing the new task node, without manual operation, which can further simplify the operation, thereby further improving the processing efficiency of the workflow, and can also ensure that the guidance information displayed in the floating window provides accurate guidance during the processing of each task node.

[0111] In addition, when jumping to the next target application subsequently, the floating window is displayed again in the current jump target application, so that the corresponding guidance information is displayed through the floating window in each work stage, thereby further improving the processing efficiency of the workflow.

[0112] It should be noted that there are many ways to determine whether the target operation corresponding to the current task node has been completed. For example, it can be implemented by page interaction event detection or data response event detection. Specifically, the event stream of the target application is detected. When a page interaction event or data response event is detected in the event stream that indicates that the target operation corresponding to the current task node has been completed, it is determined that the target operation corresponding to the current task node has been completed. Other methods can also be used, and the other methods are described in detail below.

[0113] In one possible implementation, whenever it is detected that the target operation corresponding to the current task node has been completed, the guidance information in the floating window is updated to the guidance information corresponding to the next task node. Specifically, the application page of the target application currently jumped to is detected to obtain a detection result; whenever the detection result indicates that the target page element is displayed in the application page, it is determined that the target operation corresponding to the current task node has been completed, and the guidance information in the floating window is updated to the guidance information corresponding to the next task node.

[0114] Among them, the application page is the human-computer interaction page of the target application. The application page supports users to view information and perform interactive operations, etc. The page elements refer to the basic components in the application page used to realize interaction and display. The types of page elements can be diverse. For example, page elements can include display elements, interactive elements or container elements, etc. Display elements can include text, pictures or icons, etc. Interactive elements can include controls such as text input boxes, buttons or check boxes, and container elements can include tables, panels or tabs, etc. Page elements can also include other types of elements, which are not limited in the embodiments of the present disclosure.

[0115] Among them, the target page element is the page element corresponding to the current task node. Specifically, the target page element is a page element that is not displayed before the target operation corresponding to the current task node is completed, and is displayed when the target operation corresponding to the current task node is completed. It ensures that the target page element displayed in the application page can be used as a basis for judging whether the target operation corresponding to the current task node is completed. That is, when the detection result indicates that the target page element is displayed in the application page, it means that it is detected that the target operation corresponding to the current task node is completed, and when the detection result indicates that the target page element is not displayed in the application page, it means that it is detected that the target operation corresponding to the current task node is not completed. Under normal circumstances, the target page element will only be displayed in the specified area of ​​the application page. Therefore, it is only necessary to perform page element detection on the specified area of ​​the application page to determine whether the target page element is displayed in the specified area. There is no need to perform page element detection on the entire application page, which can improve efficiency.

[0116] For example, assuming that the current task node is a text generation task node in the text generation working phase, and the target operation is to display the generation result copy control after waiting for the text to be generated, the target page element corresponding to the text generation task node can be a generation result copy control for copying the text generation result. Before the target operation corresponding to the text generation task node is executed, the application page does not display the generation result copy control. At this time, by performing page element detection on the application page of the target application currently jumped, a detection result is obtained indicating that the generation result copy control is not displayed in the application page; and when the target operation corresponding to the text generation task node is executed, the application page displays the generation result copy control. At this time, by performing page element detection on the application page of the target application currently jumped, a detection result is obtained indicating that the generation result copy control is displayed in the application page; therefore, by performing page element detection on the application page of the target application currently jumped, a detection result indicating whether the generation result copy control is displayed in the application page is obtained. Whenever the detection result indicates that the generation result copy control is displayed in the application page, it is determined that the target operation corresponding to the text generation task node is executed.

[0117] It can be understood that page element detection is performed on the application page of the target application currently jumped to obtain a detection result, so that the detection result can indicate whether the target page element is displayed in the application page. Whenever the detection result indicates that the target page element is displayed in the application page, the guidance information in the floating window is updated to the guidance information corresponding to the next task node. By performing page element detection on the application page, and then displaying the target page element in the application page as the basis for judging whether the target operation corresponding to the current task node has been executed, the completion status of the current task node can be accurately determined, and the completion status of the task node can be automatically detected. As well as the guidance information can be automatically updated when processing a new task node, real-time feedback can be given to the user through the automatically updated guidance information, effectively avoiding user operation errors and ensuring that each task node is completed in order, thereby improving the success rate of workflow execution. Moreover, this process does not require manual operation, which can further simplify the operation and further improve the processing efficiency of the workflow.

[0118] In addition, when processing a new task node subsequently, the application page of the target application currently jumped to is again detected for page elements to obtain the detection results, and whenever the detection results indicate that the target page elements are displayed in the application page, the guidance information in the floating window is updated to the guidance information corresponding to the next task node, so that page element detection is required when processing each task node to accurately determine the completion status of the current task node.

[0119] Specifically, page element detection is used to identify each page element in the page. Page element detection can be implemented in a variety of ways. For example, page element detection can also be implemented by page change event detection. Specifically, the event stream of the target application is detected. When a page change event is detected in the event stream that indicates that the target page element is displayed in the application page, it is determined that the target operation corresponding to the current task node has been executed.

[0120] For another example, page element detection can also be implemented using image understanding technology. The first implementation method of image understanding technology is: page element detection can be implemented using target detection. By performing target detection on the application page, the bounding box and corresponding category of each page element in the application page are determined. Assuming that the target page element is a generated result copy control, if the target detection result of the application page includes a bounding box with the category of "copy control", it can be determined that the target page element is displayed in the application page. In addition, page element detection can also be implemented through optical character recognition (OCR). ion, OCR) extracts the text content within the bounding box in the target detection result. When the category of the bounding box matches the target page element and the extracted text content is consistent with the text content of the target page element, it is determined that the target page element is displayed in the application page, which can improve the accuracy and reliability of page element detection; the second implementation method of image understanding technology: page element detection can be implemented by semantic segmentation. By performing semantic segmentation on the application page, the element area where each page element in the application page is located and the corresponding category are determined. If the semantic segmentation result of the application page includes an element area with the category of "copy control", it can be determined that the target page element is displayed in the application page based on this. In addition, page element detection can also extract the text content in the element area in the semantic segmentation result through optical character recognition. When the category of the element area matches the target page element and the extracted text content is consistent with the text content of the target page element, it is determined that the target page element is displayed in the application page, which can improve the accuracy and reliability of page element detection.

[0121] It should be noted that page element detection can be configured to be performed periodically at preset time intervals, so that the detection results can promptly reflect the changes in page elements in the application page, and realize that when the target operation corresponding to the current task node is completed, the target page displayed in the application page can be detected in a timely manner.

[0122] In one possible implementation, page element detection is performed on the application page of the target application currently jumped to obtain a detection result. Specifically, page element detection can be performed on the application page of the target application currently jumped to obtain the current element identifier of the current page element, which is the page element currently displayed in the application page; the preset element identifier of the target page element is obtained, and the current element identifier is matched with the preset element identifier for consistency to obtain a detection result.

[0123] Among them, the element identifier refers to the structured information used to identify the page element; the current element identifier refers to the structured information of the current page element. The current element identifier is obtained by page element detection. For example, the page change event record has the element identifier of the page element currently displayed on the target page. The element identifier of the currently displayed page element can be used as the current element identifier. The current element identifier may include information such as the category, location or description of the current page element. The current element identifier is used to identify that the page elements currently displayed in the application page include the current page element. For example, assuming that the current page element is a generation result copy control, the current element identifier of the generation result copy control can be "copy control". The current element identifier is used to identify that the page elements currently displayed in the application page include the generation result copy control.

[0124] Among them, the preset element identifier refers to the structured information of the target page element. The preset element identifier can be obtained by manual annotation or automatic generation. The preset element identifier can include information such as the category, location or description of the target page element. The preset element identifier is used to determine whether the application page includes the specified target page element. The preset element identifier is used to identify that the page elements currently expected to be displayed in the application page include the target page element. For example, assuming that the target page element is a generation result copy control, the preset element identifier of the generation result copy control can be "copy control". The preset element identifier is used to identify that the page element currently expected to be displayed in the application page is a generation result copy control.

[0125] It can be understood that by performing page element detection on the application page of the target application currently jumped to, the current element identifier of each current page element in the application page can be obtained, and then the preset element identifier of the target page element is obtained, and the current element identifier and the preset element identifier are matched for consistency to obtain a detection result. The detection result can indicate whether the current element identifier is consistent with the preset element identifier, so that the detection result can accurately indicate whether the target page element is displayed in the application page. This is because when the current element identifier is consistent with the preset element identifier, it means that the page elements actually displayed in the application page include the target page elements, and when the current element identifier is inconsistent with the preset element identifier, it means that the page elements actually displayed in the application page do not include the target page elements. Then, the target page element is displayed in the application page as a basis for judging whether the target operation corresponding to the current task node has been executed. The completion status of the current task node can be accurately determined, and the completion status of the task node can be automatically detected. This process does not require manual operation, can further simplify the operation, and thus further improve the processing efficiency of the workflow.

[0126] In one possible implementation, a current element identifier is matched with a preset element identifier for consistency to obtain a detection result, specifically, the current element identifier is matched with the preset element identifier for consistency to obtain a first matching result; the current operation instruction information of the current operation is obtained, and the current operation is an operation triggered before the current target page element is generated and after the previous target page element is generated; the preset operation instruction information of the target operation is obtained, and the current operation instruction information is matched with the preset operation instruction information for consistency to obtain a second matching result; a logical judgment is performed based on the first matching result and the second matching result to obtain a detection result.

[0127] Among them, the operation instruction information is structured information of the operation. The operation instruction information may include the type of operation. The type of operation may be diverse. For example, the type of operation may include active operations such as click operations, move operations or input operations. The type of operation may also include passive operations such as conditional waiting operations and event-driven operations. When the operation type is a click operation, the operation instruction information may also include the click position; when the operation type is a move operation, the operation instruction information may also include the coordinates before and after the change; when the operation type is an input operation, the operation instruction information may also include the input content; when the operation type is a conditional waiting operation, the operation instruction information may also include the waiting conditions and the operations triggered when the conditions are met, etc.

[0128] Among them, the current operation instruction information and the preset operation instruction information both belong to operation instruction information. The current operation instruction information is the operation instruction information of the current operation actually triggered. Since the page interaction event will be recorded after the interactive operation is triggered on the application page, the current operation instruction information can be extracted from the page interaction event of the current operation. The preset operation instruction information is the operation instruction information of the target operation expected to be triggered.

[0129] It should be noted that the second matching result can accurately indicate whether the target operation is correctly triggered. This is because when the second matching result indicates that the current operation instruction information is consistent with the preset operation instruction information, it means that the target operation is correctly triggered, and when the second matching result indicates that the current operation instruction information is inconsistent with the preset operation instruction information, it means that the target operation is not correctly triggered. In addition to displaying the target page element in the application page when the target operation is completed, there may also be other operations that display the target page element in the application page when they are completed. The premise for the target operation to be completed is that the target operation is correctly triggered. In order to avoid misjudgment, it is necessary to use the correct triggering of the target operation as an auxiliary basis for the completion of the target operation corresponding to the current task node.

[0130] It can be understood that by performing consistency matching on the current element identifier and the preset element identifier, a first matching result is obtained. The first matching result can indicate whether the current element identifier is consistent with the preset element identifier, so that the first matching result can accurately indicate whether the target page element is displayed in the application page. By obtaining the current operation instruction information of the current operation and the preset operation instruction information of the target operation corresponding to the current task node, the current operation instruction information is matched with the preset operation instruction information to obtain a second matching result. The second matching result can indicate whether the current operation instruction information is consistent with the preset operation instruction information, so that the second matching result can accurately indicate whether the target operation is correctly triggered. Then, a logical judgment is performed based on the first matching result and the second matching result to obtain a detection result. The detection result can further indicate whether the target operation is correctly triggered on the basis of indicating whether the target page element is displayed in the application page. Whenever the detection result indicates that the target page element is displayed in the application page and the target operation is correctly triggered, it is determined that the target operation corresponding to the current task node has been completed. This can further improve the accuracy of the judgment of the completion status of the task node and realize automatic detection of the completion status of the task node. This process does not require manual operation, can further simplify the operation, and thus further improve the processing efficiency of the workflow.

[0131] Therefore, whenever the detection result indicates that the target page element is displayed in the application page, it is determined that the target operation corresponding to the current task node has been executed. Specifically, whenever the detection result indicates that the target page element is displayed in the application page and the target operation is triggered, it is determined that the target operation corresponding to the current task node has been executed.

[0132] Specifically, a logical judgment is performed based on the first matching result and the second matching result to obtain a detection result. Specifically, when the first matching result indicates that the target page element is displayed in the application page, and the second matching result indicates that the target operation is correctly triggered, the detection result is an execution completion result; when the first matching result indicates that the target page element is not displayed in the application page, or the second matching result indicates that the target operation is not correctly triggered, the detection result is an incomplete execution result; on this basis, when the detection result is an execution completion result, it is determined that the target operation corresponding to the current task node is executed, and when the detection result is an incomplete execution result, it is determined that the target operation corresponding to the current task node is not executed.

[0133] In one possible implementation, if the target application currently jumped to is a text generation application, the target operations corresponding to the multiple task nodes include a first input operation, a text generation operation, and a generation result copy operation in sequence, and the target page elements include a first prompt text, a generation result copy control, or a copy success prompt. Whenever the detection result indicates that the target page element is displayed in the application page, it is determined that the target operation corresponding to the current task node has been executed, and the guidance information in the floating window is updated to the guidance information corresponding to the next task node. Specifically, when the detection result indicates that the first prompt text is displayed in the application page, it is determined that the first input operation is executed, and the guidance information in the floating window is updated to the guidance information corresponding to the text generation operation; when the detection result indicates that the generation result copy control is displayed in the application page, it is determined that the text generation operation is executed, and the guidance information in the floating window is updated to the guidance information corresponding to the generation result copy operation.

[0134] Then, whenever it is detected that the target operations in the target application of the current jump have been completed, jump to the target application corresponding to the next work stage, display the guidance information again in the target application of the current jump and execute the corresponding target operation until the workflow is completed. Specifically, when the detection result indicates that a copy success prompt is displayed on the application page, it is determined that the target operations in the text generation application have been completed, jump to the target application corresponding to the next work stage, display the guidance information again in the target application of the current jump and execute the corresponding target operation until the workflow is completed.

[0135] Among them, the text generation application is an application for generating text. The text generation application can rely on a large language model to generate text. Specifically, the text generation application can generate text through an image generation model deployed on a text generation server. The text generation application can process multiple task nodes, namely the first input task node, the text generation task node, and the copy text task node.

[0136] Specifically, when the target application currently jumped to is a text generation application, the first task node may be a first input task node. When the processing of the first input task node begins, the guidance information corresponding to the first task node is displayed in a floating window. The detection result of the page element detection can be used to determine whether the first input operation corresponding to the first task node has been completed. For example, the first prompt text may be a target page element. When the detection result indicates that the first prompt text is displayed in the application page, it is determined that the first input operation has been completed.

[0137] Then, the text generation task node is processed, and the guidance information in the floating window is updated to the guidance information corresponding to the text generation operation. Then, the detection result of the page element detection can be used to determine whether the text generation operation corresponding to the second task node has been completed. For example, the generation result copy control can be a target page element. When the detection result indicates that the generation result copy control is displayed in the application page, it is determined that the text generation operation has been completed.

[0138] Then, start processing the copy text task node, update the guidance information in the floating window to the guidance information corresponding to the generation result copy operation, and then use the detection result of the page element detection to determine whether the generation result copy operation corresponding to the third task node has been completed. For example, the copy success prompt can be the target page element. When the detection result indicates that the copy success prompt is displayed in the application page, it is determined that the generation result copy operation has been completed. Since the copy text task node is the last task node processed by the text generation application, the generation result copy operation has been completed, which is equivalent to all the target operations in the text generation application being completed. At this time, jump to the target application corresponding to the next work stage, display the guidance information again in the currently jumped target application and execute the corresponding target operation until the workflow ends.

[0139] It can be understood that the text generation application processes each task node in turn to generate a text generation result for the first prompt text, so that the text generation result can meet the requirements of the workflow. Moreover, during the processing of the text generation application, the completion status of the target operation corresponding to each task node is automatically detected, and the guidance information is automatically updated. This process does not require manual operation, which can further simplify the operation and thus further improve the processing efficiency of the workflow.

[0140] The following describes in detail the first input task node of the text generation application.

[0141] Among them, the target operation corresponding to the first input task node is the first input operation, the first input operation can be used to display the first prompt text, and the guidance information corresponding to the first input operation can be used to indicate the input of the first prompt text. For example, the application page of the text generation application is provided with a first message area for displaying historical content. Since the first prompt text is displayed in the first message area, it represents the successful display of the first prompt text, so the target page element corresponding to the first input task node can be the first prompt text displayed in the first message area. Since the first prompt text needs to wait for text generation after successful display, the target page element corresponding to the first input task node can also be the first waiting icon displayed in the first message area to indicate waiting for text generation. The target page element corresponding to the first input task node can also be other elements, which is not limited in the embodiments of the present disclosure.

[0142] It is worth noting that the first prompt text can be obtained by manual input, pulling from a prompt text template, or modifying the prompt text template. The first prompt text is a prompt text associated with the workflow. The first prompt text contains the intention of text generation. The first prompt text is used to guide the text generation application to generate a specific type of text content. For example, in a video creation scenario, for the workflow of video creation, the first prompt text can be a prompt text used to prompt the generation of a video script.

[0143] It should be noted that, when processing the first input task node, the guidance information corresponding to the first input operation is displayed in the floating window, and the guidance information corresponding to the first input operation needs to be set according to the actual design of the first input operation; the form of the first input operation can be diverse, for example, the first input operation can be to input a specified number of words of text in the first text input box, and when the text in the text input box reaches the specified number of words, the text in the text input box is automatically submitted as the first prompt text to display the first prompt text; for another example, the first input operation can include inputting text in the first text input box, and clicking the first submit control corresponding to the first text input box, so that the text in the text input box can be submitted as the first prompt text to display the first prompt text; for another example, jumping to the text generation When the application is created, the prompt text template is automatically copied. The first input operation can be clicking the first paste control for pasting the prompt text template. After clicking the first paste control, the prompt text template is automatically submitted as the first prompt text to display the first prompt text. For example, the first input operation can include clicking the first paste control for pasting the prompt text template, pasting the prompt text template into the first text input box, and clicking the first submit control corresponding to the first text input box to submit the text in the text input box as the first prompt text to display the first prompt text. In addition, before submitting the text in the text input box, the text in the first text input box can also be edited. The first input operation depends on the actual design of the text generation application, and the embodiments of the present disclosure are not limited here.

[0144] The following is a detailed description of the text generation task node of the text generation application.

[0145] Among them, the target operation corresponding to the text generation task node is the text generation operation. The text generation operation can be used to display the generation result copy control after waiting for the text to be generated. The guidance information corresponding to the text generation operation can be used to indicate waiting for text generation. For example, when the generation result copy control is displayed in the first message area, it means that the text generation result is successfully generated, so the target page element corresponding to the text generation task node can be the generation result copy control.

[0146] It should be noted that when processing a text generation task node, the guidance information in the floating window is updated to the guidance information corresponding to the text generation operation. The guidance information corresponding to the text generation operation needs to be set according to the actual design of the text generation operation; the form of the text generation operation can be diverse. For example, the text generation operation can automatically trigger the display of the generation result copy control after waiting for the text to be generated; for another example, the text generation operation can wait for the text to be generated, and after the text generation result is generated, the display of the generation result copy control is triggered by selecting the text generation result; the text generation operation depends specifically on the actual design of the text generation application, and the embodiments of the present disclosure are not limited here.

[0147] The following is a detailed description of the copy text task node of the text generation application.

[0148] Among them, the target operation corresponding to the copy text task node is the generation result copy operation. The generation result copy operation can be used to copy the text generation result. The guidance information corresponding to the generation result copy operation can be used to indicate the copy text generation result. For example, when the application page of the text generation application displays a copy success prompt, it means that the text generation result is successfully copied, so the target page element corresponding to the copy text task node can be a copy success prompt.

[0149] It should be noted that when processing the copy text task node, the guidance information in the floating window is updated to the guidance information corresponding to the generation result copy operation. The guidance information corresponding to the generation result copy operation needs to be set according to the actual design of the generation result copy operation; the form of the generation result copy control can be diverse, for example, the generation result copy control can be an operability control such as a button control or a drag and drop control, so the form of the generation result copy operation can be diverse, for example, the generation result copy operation can include clicking the generation result copy control or dragging and dropping the generation result copy control, etc. The generation result copy operation can also be a series of operations, depending on the actual design of the text generation application, and the embodiments of the present disclosure are not limited here.

[0150] For example, refer to Figure 3 , Figure 3 An optional page diagram of the processing flow of the first input task node and the text generation task node provided in an embodiment of the present disclosure.

[0151] Among them, when jumping to the text generation application, the prompt text template is automatically copied, and the processing of the first input task node begins. The application page displayed by the text generation application can be a text generation page 301. The text generation page 301 is provided with a first message area 304, a first text input box 305 and a first submission control 306. A floating window 302 is displayed in the text generation page 301, and the floating window 302 displays the first text generation guidance information 303 corresponding to the first input operation. Assuming that the first input operation is to paste the prompt text template, modify the text and submit the text, the first text generation guidance information 303 can be "Current progress: Use the text generation application to generate a video script; please paste the template, modify the content and submit it";

[0152] Then, when processing the first input task node, by clicking the first text input box 305, an input keyboard 307 can be displayed, and a first paste control 307 is displayed above the input keyboard 307. In addition, the first text input box 305 can be long-pressed to display the first paste control 308.

[0153] Then, when processing the first input task node, by clicking the first paste control 308, the prompt text template can be pasted into the first text input box 305, and the text in the first text input box 305 can be edited. By clicking the first submit control 306, the text in the first text input box 305 can be submitted as the first prompt text 309, so that the first prompt text 309 can be displayed in the first message area 304, indicating that the first prompt text 309 is successfully displayed;

[0154] Then, when processing the first input task node, the first prompt text 309 can be the target page element. When the detection result indicates that the first prompt text 309 is displayed in the first message area 304, it is determined that the first input operation is completed, and the text generation task node is processed. The first text generation guide information 303 in the floating window 302 is updated to the second text generation guide information 310 corresponding to the text generation operation. Assuming that the text generation operation is used to automatically trigger the display of the generation result copy control 311 after waiting for the text to be generated, then the second text generation guide information 310 can be "Current progress: Use the text generation application to generate a video script; the video script is being generated, please wait patiently."

[0155] Then, when processing the text generation task node, wait for a while, and automatically trigger the display of the generation result copy control 311 after generating the text generation result 312. The generation result copy control 311 can be a target page element. When the detection result indicates that the generation result copy control 311 is displayed in the first message area 304, it is determined that the text generation operation is completed and the processing of the copy text task node begins.

[0156] Then, refer to Figure 4 , Figure 4 An optional page diagram of the processing flow of the copy text task node provided in an embodiment of the present disclosure.

[0157] Among them, when starting to process the copy text task node, the second text generation guide information 310 in the floating window 302 is updated to the first image generation guide information 401 corresponding to the generation result copy operation, and the generation result copy operation is used to copy the text generation result 312. At this time, the first image generation guide information 401 can be "Current progress: Use the text generation application to generate a video script; please copy the generation result."

[0158] Then, when processing the copy text task node, by clicking the generation result copy control 311, the text generation result 312 can be copied, and a copy success prompt 402 is displayed in the text generation page 301, indicating that the text generation result 312 is successfully copied. The copy success prompt 402 can be a target page element. When the detection result indicates that the copy success prompt 402 is displayed in the text generation page 301, it is determined that the generation result copy operation is completed, that is, it is determined that all target operations in the text generation application are completed, and it is necessary to jump to the target application corresponding to the next working stage. For example, the target application corresponding to the next working stage can be a picture generation application. In the process of the text generation application jumping to the picture generation application, the information displayed in the floating window 302 is updated, so that the first jump information 403 is displayed in the floating window 302. The first jump information 403 is used to prompt that it is jumping to the target application corresponding to the next working stage. The first jump information 403 can be "Current progress: Use the text generation application to generate a video script; copying is successful, and the picture generation application is opening for you..."

[0159] In one possible implementation, if the target application corresponding to the next work stage is an image generation application, the target operations corresponding to the multiple task nodes include, in sequence, a second input operation, an image generation operation, and a generation result saving operation, and the target page elements include a second prompt text generated by the text generation application, a generation result saving control, or a save success prompt. When the detection result indicates that a copy success prompt is displayed on the application page, it is determined that all target operations in the text generation application have been completed, and the process jumps to the target application corresponding to the next work stage. The guidance information is displayed again in the currently jumped target application and the corresponding target operation is executed until the workflow is terminated. Specifically, when the detection result indicates that a copy success prompt is displayed on the application page, it is determined that all target operations in the text generation application have been completed, and the process jumps to the image generation application.

[0160] Then, when the detection result indicates that the second prompt text is displayed in the application page, it is determined that the second input operation has been completed, and the guidance information in the floating window is updated to the guidance information corresponding to the image generation operation; when the detection result indicates that the generation result save control is displayed in the application page, it is determined that the image generation operation has been completed, and the guidance information in the floating window is updated to the guidance information corresponding to the generation result save operation; when the detection result indicates that a save success prompt is displayed in the application page, it is determined that all target operations in the image generation application have been completed, jump to the target application corresponding to the next work stage, display the guidance information again in the currently jumped target application and execute the corresponding target operation until the workflow is completed.

[0161] Among them, the image generation application is an application used to generate images. The image generation application can rely on the image generation model to generate images. Specifically, the image generation application can generate images through the image generation model deployed on the image generation server. The image generation application can process multiple task nodes, which are the second input task node, the image generation task node, and the image saving task node.

[0162] Specifically, if the target application corresponding to the next work stage is an image generation application, the first task node may be a second input task node. When the second input task node begins to be processed, the guidance information corresponding to the first task node is displayed in a floating window. The detection result of the page element detection can be used to determine whether the second input operation corresponding to the first task node has been completed. For example, the second prompt text may be a target page element. When the detection result indicates that the second prompt text is displayed in the application page, it is determined that the second input operation has been completed.

[0163] Then, the image generation task node is processed, and the guidance information in the floating window is updated to the guidance information corresponding to the image generation operation. Then, the detection result of the page element detection can be used to determine whether the image generation operation corresponding to the second task node has been completed. For example, the generation result saving control can be a target page element. When the detection result indicates that the generation result saving control is displayed in the application page, it is determined that the image generation operation has been completed.

[0164] Then, start processing the save image task node, update the guidance information in the floating window to the guidance information corresponding to the generation result save operation, and then use the detection result of the page element detection to determine whether the generation result save operation corresponding to the third task node has been executed. For example, the save success prompt can be the target page element. When the detection result indicates that the save success prompt is displayed in the application page, it is determined that the generation result save operation has been completed. Since the save image task node is the last task node processed by the image generation application, the generation result save operation has been completed, which is equivalent to all the target operations in the image generation application being executed. At this time, jump to the target application corresponding to the next work stage, display the guidance information again in the currently jumped target application and execute the corresponding target operation until the workflow ends.

[0165] It can be understood that, by processing each task node in sequence through the image generation application, an image generation result is generated for the second prompt text generated by the text generation application when the image generation application processes the text generation application, so that the image generation result can meet the requirements of the workflow, and can effectively link the text generation application and the image generation application. Moreover, during the processing of the image generation application, the completion status of the target operation corresponding to each task node is automatically detected, and the guidance information is automatically updated. This process does not require manual operation, can further simplify the operation, and thus further improve the processing efficiency of the workflow.

[0166] The second input task node of the image generation application is described in detail below.

[0167] Among them, the target operation corresponding to the second input task node is the second input operation, the second input operation can be used to input the second prompt text, and the guidance information corresponding to the second input operation can be used to indicate the input of the second prompt text. For example, the application page of the image generation application is provided with a second message area for displaying historical content. Since the second prompt text is displayed in the second message area, it means that the second prompt text is successfully displayed, so the target page element corresponding to the second input task node can be the second prompt text displayed in the second message area.

[0168] It is worth noting that the second prompt text can be a text generation result generated by a text generation application. The second prompt text contains the intention of image generation. The second prompt text is used to guide the image generation application to generate a specific type of image. For example, in a video creation scenario, for the workflow of video creation, the second prompt text can be a prompt text for prompting the generation of a video cover.

[0169] It should be noted that when processing the second input task node, the guidance information corresponding to the second input operation is displayed in the floating window, and the guidance information corresponding to the second input operation needs to be set according to the actual design of the first input operation; the form of the second input operation can be diverse. For example, the text generation result is copied before jumping to the image generation application. The second input operation can be clicking the second paste control for pasting the prompt text generation result. After clicking the second paste control, the text generation result is automatically submitted as the second prompt text to display the second prompt text; for example, the second input operation can include clicking the second paste control for pasting the text generation result, pasting the text generation result into the second text input box, and clicking the second submit control corresponding to the second text input box to submit the text in the text input box as the second prompt text to display the second prompt text. In addition, before submitting the text in the text input box, the text in the second text input box can also be edited; the second input operation depends on the actual design of the image generation application, and the embodiments of the present disclosure are not limited here.

[0170] The following is a detailed description of the image generation task node of the image generation application.

[0171] Among them, the target operation corresponding to the image generation task node is the image generation operation. The image generation operation can be used to display the generation result save control after waiting for the image to be generated. The guidance information corresponding to the image generation operation is used to indicate waiting for the image to be generated. When the generation result save control is displayed on the application page of the image generation application, it means that the image generation result is successfully generated. Therefore, the target page element corresponding to the image generation task node can be the generation result save control.

[0172] It should be noted that when processing an image generation task node, the guidance information in the floating window is updated to the guidance information corresponding to the image generation operation. The guidance information corresponding to the image generation operation needs to be set according to the actual design of the image generation operation. The image generation operation can take various forms. For example, the image generation operation can automatically trigger the display of the generation result save control after waiting for the image to be generated. For example, the image generation operation can wait for the image to be generated, generate the image generation result, and then trigger the display of the generation result save control by selecting the image generation result. The specific image generation operation depends on the actual design of the image generation application and is not limited in the present embodiment.

[0173] The following is a detailed description of the save image task node of the image generation application.

[0174] Among them, the target operation corresponding to the save image task node is the generation result save operation. The generation result save operation can be used to save the image generation result. The guidance information corresponding to the generation result save operation is used to indicate the saving of the image generation result. For example, when the application page of the image generation application displays a copy success prompt, it means that the image generation result is successfully saved, so the target page element corresponding to the save image task node can be a copy success prompt.

[0175] For example, refer to Figure 5 , Figure 5 An optional page diagram of a partial processing flow of the second input task node provided in an embodiment of the present disclosure.

[0176] Among them, when jumping to the image generation application, the text generated by the copied text generation application is used as the video script, and the second input task node is processed. The application page displayed when the image generation application is opened can be the first home page 501, and the floating window 302 is displayed in the first home page 501. The first home page 501 can be provided with a first page jump control for jumping pages. The first page jump control can be a creation button 502. The second input operation can include a series of operations. When the first home page 501 is displayed, the second input operation can include clicking the creation button 502. At this time, the information displayed in the floating window 302 is updated so that the first image generation guide information 503 corresponding to the second input operation displayed in the floating window 302 can be "Current progress: Use the image generation application to generate a video cover; click the "Create" button".

[0177] Then, when processing the second input task node, by clicking the creation button 502, the picture generation page 504 can be displayed, and the first picture generation guide information 503 in the floating window 302 is updated to the second picture generation guide information 505 corresponding to the picture generation operation. The picture generation page 504 belongs to the application page of the picture generation application. The picture generation page 504 is provided with a second message area 506 and a second text input box 507. The second text input box 507 is used to enter text. When the picture generation page 504 is displayed, the second input operation can also include clicking the second text input box 507, and pasting the copied video script in the second text input box 507. At this time, the second picture generation guide information 505 can be "Current progress: Use the picture generation application to generate video cover; click the input box to paste the script."

[0178] Then, refer to Figure 6 , Figure 6 An optional page diagram of a partial processing flow of the second input task node and the image generation task node provided in an embodiment of the present disclosure.

[0179] Among them, when processing the image generation task node, by clicking the second text input box 507, the second text input box 507 can be expanded and the input keyboard 307 can be displayed, and the text generation result 312 generated by the text generation application can be pasted into the expanded second text input box 507. The text in the expanded second text input box 507 can be edited, and the second image generation guide information 505 in the floating window 302 is updated to the third image generation guide information 601 corresponding to the image generation operation. A second submission control is set in the expanded second text input box 507, and the second submission control can be a generate button 602. When the second text input box 507 is expanded, the second input operation can also include clicking the generate button 602. At this time, the third image generation guide information 601 can be "Current progress: Use the image generation application to generate a video cover; click the "Generate" button".

[0180] Then, when processing the image generation task node, by clicking the generate button 602, the text in the second text input box 507 can be submitted as the second prompt text 603, so that the second prompt text 603 can be displayed in the second message area 506, indicating that the second prompt text 603 is successfully displayed. The second prompt text 603 can be a target page element. When the detection result indicates that the second prompt text 603 is displayed in the second message area 506, it is determined that the second input operation is completed, and the image generation task node is processed. The third image generation guide information 601 in the floating window 302 is updated to the fourth image generation guide information 604 corresponding to the image generation operation. The image generation operation can include automatically triggering the display of the image generation result 605 after waiting for the image to be generated. Then, the fourth image generation guide information 604 can be "Current progress: Use the image generation application to generate a video cover; click to view the image".

[0181] Then, refer to Figure 7 , Figure 7 An optional page diagram of a partial processing flow of a second input task node and a picture generation task node, as well as a processing flow of a save picture task node provided in an embodiment of the present disclosure.

[0182] Among them, when processing the image generation task node, by clicking the image generation result 605, the image saving page 701 can be displayed. The image saving page 701 belongs to the application page of the image generation application. The image saving page 701 displays a generation result saving control 702. The generation result saving control 702 can be a target page element. When the detection result indicates that the generation result saving control 702 is displayed in the image saving page 701, it is determined that the image generation operation is completed and the processing of the image saving task node begins.

[0183] Then, when processing the save picture task node, the fourth picture generation guide information 604 in the floating window 302 is updated to the fifth picture generation guide information 703 corresponding to the generation result save operation. The generation result save operation is used to save the picture generation result 605. At this time, the fifth picture generation guide information 703 can be "Current progress: Use the picture generation application to generate a video cover; click the Save button".

[0184] Then, when processing the image generation task node, by clicking the generation result save control 702, the image generation result 605 can be saved, and a save success prompt 704 is displayed in the image save page 701, indicating that the image generation result 605 is successfully saved. The save success prompt 704 can be a target page element. When the detection result indicates that the save success prompt 704 is displayed in the image save page 701, it is determined that the generation result save operation is completed, that is, it is determined that all target operations in the image generation application are completed, and it is necessary to jump to the target application corresponding to the next working stage. For example, the target application corresponding to the next working stage can be a video generation application. In the process of jumping from the image generation application to the video generation application, the information displayed in the floating window 302 is updated, so that the second jump information 705 is displayed in the floating window 302. The second jump information 705 is used to prompt that it is jumping to the target application corresponding to the next working stage. The second jump information 705 can be "Current progress: Use the image generation application to generate a video cover; the picture is saved successfully, and the video generation application is opening for you..."

[0185] In one possible implementation, if the target application corresponding to the next work stage is a video generation application, the target operations corresponding to the multiple task nodes include, in sequence, a third input operation, a video generation operation, a cover setting operation, and a video export operation, and the target page elements include a third prompt text, a cover setting control, a cover image generated by the image generation application, or an export success prompt. When the detection result indicates that a save success prompt is displayed on the application page, it is determined that all target operations in the image generation application have been completed, and the process jumps to the target application corresponding to the next work stage. The guidance information is displayed again in the currently jumped target application and the corresponding target operation is executed until the workflow is terminated. Specifically, when the detection result indicates that a save success prompt is displayed on the application page, it is determined that all target operations in the image generation application have been completed, and the process jumps to the video generation application.

[0186] Then, when the detection result indicates that the third prompt text is displayed in the application page, it is determined that the third input operation is completed, and the guidance information in the floating window is updated to the guidance information corresponding to the video generation operation; when the detection result indicates that the cover setting control is displayed in the application page, it is determined that the video generation operation is completed, and the guidance information in the floating window is updated to the guidance information corresponding to the cover setting operation; when the detection result indicates that a cover image is inserted in the application page, it is determined that the cover setting operation corresponding to the currently displayed guidance information is completed, and the guidance information in the floating window is updated to the guidance information corresponding to the video export operation; when the detection result indicates that an export success prompt is displayed in the application page, it is determined that all target operations in the video generation application are completed, and the workflow ends.

[0187] Among them, the video generation application is an application for generating videos. The video generation application can rely on the video generation model to generate videos. Specifically, the video generation application can generate videos through the image generation model deployed on the video generation server. Multiple task nodes can be processed by the video generation application, namely the third input task node, the video generation task node, the cover setting task node and the video export task node.

[0188] Specifically, if the target application corresponding to the next work stage is a video generation application, the first task node may be the third input task node. When the third input task node begins to be processed, the guidance information corresponding to the first task node is displayed in a floating window. The detection result of the page element detection can be used to determine whether the third input operation corresponding to the first task node has been completed. For example, the third prompt text may be the target page element. When the detection result indicates that the third prompt text is displayed in the application page, it is determined that the third input operation has been completed.

[0189] Then, the video generation task node is processed, and the guidance information in the floating window is updated to the guidance information corresponding to the video generation operation. Then, the detection result of the page element detection can be used to determine whether the video generation operation corresponding to the second task node has been completed. For example, the cover setting control can be the target page element. When the detection result indicates that the cover setting control is displayed in the application page, it is determined that the video generation operation has been completed.

[0190] Then, the cover setting task node is processed, and the guidance information in the floating window is updated to the guidance information corresponding to the cover setting operation. Then, the detection result of the page element detection can be used to determine whether the cover setting operation corresponding to the third task node has been completed. For example, the cover image can be the target page element. When the detection result indicates that the cover image is inserted into the application page, it is determined that the cover setting operation has been completed.

[0191] Then, start processing the video export task node, update the guidance information in the floating window to the guidance information corresponding to the video export operation, and then use the detection result of the page element detection to determine whether the video export operation corresponding to the fourth task node has been completed. For example, the export success prompt can be a target page element. When the detection result indicates that the export success prompt is displayed in the application page, it is determined that the video export operation is completed. Since the video export task node is the last task node processed by the video generation application, the video export operation is completed, which is equivalent to determining that all target operations in the video generation application have been completed, and the video generation application is the last application among multiple target applications, so it can be determined that all target operations in the video generation application have been completed, and then the workflow ends;

[0192] It can be understood that by processing each task node in sequence through the video generation application, a video generation result for the third prompt text is generated, so that the video generation result can meet the requirements of the workflow, and the cover image generated by the picture generation application is used for cover setting, which effectively improves the quality of the video, and can effectively link the picture generation application and the video generation application. Moreover, in the processing process of the video generation application, the completion status of the target operation corresponding to each task node is automatically detected, and the guidance information is automatically updated. This process does not require manual operation, which can further simplify the operation, thereby further improving the processing efficiency of the workflow.

[0193] The third input task node of the video generation application is described in detail below.

[0194] Among them, the target operation corresponding to the third input task node is the third input operation, the third input operation can be used to input the third prompt text, the guidance information corresponding to the third input operation can be used to indicate the input of the third prompt text, and the application page of the video generation application is provided with a third text input box. Since the submitted third prompt text can be displayed in the third text input box, it means that the third prompt text is successfully displayed, so the target page element corresponding to the third input task node can be the submitted third prompt text displayed in the third text input box.

[0195] It is worth noting that the third prompt text can be a text generation result generated by a text generation application. The third prompt text contains the intention of video generation. The third prompt text is used to guide the video generation application to generate a specific type of video. For example, in a video creation scenario, for the workflow of video creation, the third prompt text can be a prompt text for prompting video generation.

[0196] It should be noted that when processing the third input task node, the guidance information corresponding to the third input operation is displayed in the floating window. The guidance information corresponding to the third input operation needs to be set according to the actual design of the third input operation; the form of the third input operation can be diverse. For example, before jumping to the video generation application, the text generation result is copied and the video generation result is saved. The third input operation can be clicking the third paste control for pasting the prompt text generation result. After clicking the third paste control, the text generation result is automatically submitted as the third prompt text to display the third prompt text; for example, the third input operation can include clicking the third paste control for pasting the text generation result, pasting the text generation result into the third text input box, and clicking the third submit control corresponding to the third text input box, so that the text in the text input box can be submitted as the third prompt text to display the third prompt text. In addition, before submitting the text in the text input box, the text in the third text input box can also be edited; the third input operation depends on the actual design of the image generation application, and the embodiments of the present disclosure are not limited here.

[0197] The following is a detailed description of the video generation task node of the video generation application.

[0198] Among them, the target operation corresponding to the video generation task node is the video generation operation. The video generation operation can be used to display the cover setting control after waiting for the video to be generated. The guidance information corresponding to the video generation operation can be used to indicate waiting for the video to be generated. When the cover setting control is displayed on the application page of the video generation application, it means that the video generation result is successfully generated, so the target page element corresponding to the video generation task node can be the cover setting control.

[0199] It should be noted that when processing the video generation task node, the guidance information in the floating window is updated to the guidance information corresponding to the video generation operation. The guidance information corresponding to the video generation operation needs to be set according to the actual design of the video generation operation; the form of the video generation operation can be diverse. For example, the video generation operation can automatically trigger the display of the cover setting control after waiting for the video to be generated. For example, the video generation operation can wait for the video to be generated, and after the video generation result is generated, the display of the cover setting control is triggered by selecting the video generation result; the specific video generation operation depends on the actual design of the video generation application, and the embodiments of the present disclosure are not limited here.

[0200] The following is a detailed description of the cover setting task node of the video generation application.

[0201] Among them, the target operation corresponding to the cover setting task node is the cover setting operation. The cover setting operation can be used to set the video cover. The guidance information corresponding to the cover setting operation can be used to instruct the setting of the video cover. The application page of the video generation application can include a video preview page for previewing the video generation results. When the cover image is displayed on the video preview page of the video generation application, it is equivalent to inserting the cover image into the application page, indicating that the video cover is successfully set. Therefore, the target page element corresponding to the video export task node is the cover image.

[0202] It should be noted that when processing the cover setting task node, the guidance information in the floating window is updated to the guidance information corresponding to the cover setting operation. The guidance information corresponding to the cover setting operation needs to be set according to the actual design of the cover setting operation; the cover setting operation can be in various forms, for example, clicking the cover setting control or dragging and dropping the cover setting control, etc. In addition, the cover setting operation can be a single operation or a series of operations, depending on the actual design of the video generation application, and the embodiments of the present disclosure are not limited here.

[0203] The following is a detailed description of the video export task node of the video generation application.

[0204] Among them, the target operation corresponding to the video export task node is the video export operation. The video export operation can be used to export the video generation result. The guidance information corresponding to the video export operation can be used to indicate the export of the video generation result. When the application page of the video generation application displays the export success prompt, it means that the video generation result is successfully exported. Therefore, the target page element corresponding to the video export task node is the export success prompt.

[0205] It should be noted that when processing the video export task node, the guidance information in the floating window is updated to the guidance information corresponding to the video export operation. The guidance information corresponding to the video export operation needs to be set according to the actual design of the video export operation; the form of the video export operation can be diverse. For example, the application page of the video generation application is provided with an export control. The video export operation can be a trigger operation for the export control, and can also be implemented in other ways, depending on the actual design of the video generation application. The embodiments of the present disclosure are not limited here.

[0206] For example, refer to Figure 8 , Figure 8 An optional page diagram of a partial processing flow of the third input task node provided in an embodiment of the present disclosure.

[0207] Among them, when jumping to the video generation application, the third input task node is started to be processed. The application page displayed when the video generation application is opened can be the second home page 801. The floating window 302 is displayed in the second home page 801. The second home page 801 can be provided with a second page jump control for jumping pages. The second page jump control can be a picture and text into film control 802. The third input operation can include a series of operations. When the second home page 801 is displayed, the third input operation can include clicking the picture and text into film control 802. At this time, the information displayed in the floating window 302 is updated so that the first video generation guide information 803 corresponding to the third input operation displayed in the floating window 302 can be "Current progress: Use the video generation application to generate a complete video; click "Picture and text into film"".

[0208] Then, when processing the third input task node, by clicking the text-image control 802, the text determination page 804 can be displayed, and the first video generation guide information 803 in the floating window 302 is updated to the second video generation guide information 805 corresponding to the third input operation. The text determination page 804 belongs to the application page of the video generation application. The text determination page 804 is provided with an input text control 806. At this time, the second video generation guide information 805 can be "Current progress: Use the video generation application to generate a complete video; click "Enter text"".

[0209] Then, refer to Figure 9 , Figure 9 An optional page diagram of a partial processing flow of the third input task node and a partial processing flow of the video generation task node provided in an embodiment of the present disclosure.

[0210] Among them, when processing the third input task node, by clicking the input copy control 806, the text input page 901 can be displayed, and the second video generation guide information 805 in the floating window 302 is updated to the third video generation guide information 902 corresponding to the third input operation. The text input page 901 belongs to the application page of the video generation application. The text input page 901 is provided with a third text input box 903 and a third submission control. The third text input box 903 is used to input text. The text generation result 312 generated by the text generation application is pasted into the third text input box 903. The text in the expanded third text input box 903 can be edited. The third submission control can be an apply button 904. By clicking the third text input box 903, the input keyboard 307 can be displayed. When the text input page 901 is displayed, the third input operation can also include pasting the copied video script, editing the video script and clicking the apply button 904. At this time, the third video generation guide information 902 can be "Current progress: Use the video generation application to generate a complete video; paste and edit the script, and click "Apply" after completion."

[0211] Then, by clicking the Apply button 904, the text in the third text input box 903 can be submitted as the third prompt text, so that the third prompt text in the third text input box 903 is in a submitted state, that is, an uneditable state. The submitted third prompt text can be a target page element. When the detection result indicates that the submitted third prompt text is displayed in the third text input box 903, it is determined that the third input operation is completed, and the video generation task node is processed. The third video generation guide information 902 in the floating window 302 is updated to the fourth video generation guide information 907 corresponding to the video generation operation. After clicking the Apply button 904, a generation method setting page 905 for setting the video generation method is displayed. The generation method setting page 905 can be provided with a smart matching material determination control 906. The video generation operation can include setting the video generation method. Then, the fourth video generation guide information 907 can be "Current progress: Use the video generation application to generate a complete video; click "Smart matching material"".

[0212] Then, refer to Figure 10 , Figure 10 An optional page diagram of a partial processing flow of a video generation task node and a partial processing flow of a cover setting task node provided in an embodiment of the present disclosure.

[0213] Among them, when processing the video generation task node, by clicking the smart matching material determination control 906, the video waiting page 1001 can be displayed, and the fourth video generation guide information 907 in the floating window 302 is updated to the fifth video generation guide information 1002 corresponding to the video generation operation. The video waiting page 1001 can be provided with a first waiting prompt 1003 for indicating waiting for video generation, and a cancel control 1004 for canceling video generation. The video generation operation can include waiting for video generation, and the fifth video generation guide information 1002 can be "Current progress: Use the video generation application to generate a complete video; wait for video generation".

[0214] Then, when processing the video generation task node, after waiting for the video to be generated, the video setting page 1005 can be displayed. The generated video generation result can be displayed in the video setting page 1005. The video setting page 1005 is provided with a cover setting control 1006 and a video export control 1007. The cover setting control 1006 can be a target page element. When the detection result indicates that the cover setting control 1006 is displayed in the video setting page 1005, it is determined that the video generation operation is completed and the cover setting task node is processed.

[0215] Then, when processing the cover setting task node, the fifth video generation guide information 1002 in the floating window 302 is updated to the sixth video generation guide information 1008 corresponding to the cover setting operation. The cover setting operation may include clicking the cover setting control 1006. At this time, the sixth video generation guide information 1008 can be "Current progress: Use the video generation application to generate a complete video; click "Set cover"."

[0216] Then, refer to Figure 11 , Figure 11 An optional page diagram of a partial processing flow of a cover setting task node provided in an embodiment of the present disclosure.

[0217] Among them, when processing the cover setting task node, by clicking the cover setting control 1006, the picture selection page 1101 can be displayed, and the sixth video generation guide information 1008 in the floating window 302 is updated to the seventh video generation guide information 1102 corresponding to the video generation operation. The picture selection page 1101 can display the picture generation result 605 saved in the picture generation application. The cover setting operation can also include selecting the picture generation result 605 saved by the picture generation application. At this time, the seventh video generation guide information 1102 can be "Current progress: Use the video generation application to generate a complete video; select the cover picture saved by the picture generation application."

[0218] Then, when processing the cover setting task node, by selecting the picture generation result 605 as the cover picture on the picture selection page 1101, the picture editing page 1103 can be displayed, and the seventh video generation guide information 1102 in the floating window 302 is updated to the eighth video generation guide information 1104 corresponding to the video generation operation. The picture editing page 1103 can display the selected cover picture, the draggable video selection display area 1105 and the clickable cover confirmation button 1106. The cover setting operation can also include dragging the video selection display area 1105 and clicking the cover confirmation button 1106. At this time, the eighth video generation guide information 1104 can be "Current progress: Use the video generation application to generate a complete video; drag the video selection display area 1105 and confirm".

[0219] Then, refer to Figure 12 , Figure 12 An optional page diagram of a partial processing flow of a cover setting task node and a partial processing flow of a video export task node provided in an embodiment of the present disclosure.

[0220] Among them, when processing the cover setting task node, by clicking the cover confirmation button 1106 in the picture editing page 1103, the cover confirmation page 1201 can be displayed, and the eighth video generation guide information 1104 in the floating window 302 is updated to the ninth video generation guide information 1202 corresponding to the video generation operation. The cover confirmation page 1201 is provided with a cover save button 1203, and the cover setting operation can also include clicking the cover save button 1203. At this time, the ninth video generation guide information 1202 can be "Current progress: Use the video generation application to generate a complete video; click "Save"".

[0221] Then, when processing the cover setting task node, by clicking the cover save button 1203 in the cover determination page 1201, the video setting page 1005 can be displayed again. At this time, the video setting page 1005 can display the inserted cover image, and the inserted cover image can be a target page element. When the detection result indicates that the inserted cover image is displayed in the video setting page 1005, it is determined that the cover setting operation is completed and the video export task node is processed.

[0222] Then, when processing the video export task node, the ninth video generation guide information 1202 in the floating window 302 is updated to the tenth video generation guide information 1204 corresponding to the video export operation. The video export operation is used to export the video generation results. At this time, the tenth video generation guide information 1204 can be "Current progress: Use the video generation application to generate a complete video; click "Export"."

[0223] Then, refer to Figure 13 , Figure 13 An optional page diagram of a partial processing flow of a video export task node provided in an embodiment of the present disclosure.

[0224] Among them, when processing the video export task node, by clicking the video export control 1007, the export waiting page 1301 can be displayed, and the tenth video generation guide information 1204 in the floating window 302 is updated to the eleventh video generation guide information 1302 corresponding to the video generation operation. The export waiting page 1301 can be provided with a second waiting prompt 1303 for indicating waiting for video export. The video export operation may include waiting for video export. The eleventh video generation guide information 1302 can be "Current progress: Use the video generation application to generate a complete video; wait for video export".

[0225] Then, when processing the video export task node, after waiting for the video to be exported, the video sharing page 1304 can be displayed, and the export success prompt 1305 is displayed in the video sharing page 1304, indicating that the video generation result has been successfully exported. The eleventh video generation guide information 1302 in the floating window 302 is updated to the twelfth video generation guide information 1306 corresponding to the video generation operation. The export success prompt 1305 can be a target page element. When the detection result indicates that the export success prompt 1305 is displayed in the video sharing page 1304, it is determined that the video export operation has been completed, that is, it is determined that all target operations in the video generation application have been completed. Since the video generation application is the last target application, the workflow is ended, and the twelfth video generation guide information 1306 can be "Current progress: Use the video generation application to generate a complete video; creation is completed."

[0226] In one possible implementation, when the detection result indicates that the first prompt text is displayed in the application page, before determining that the first input operation is completed, the workflow processing method also includes: in response to a triggering operation on the prompt text input box in the text generation application, displaying an input keyboard, and displaying a preset prompt text template on the input keyboard; in response to the triggering operation on the prompt text template, inserting the prompt text template as the first prompt text in the prompt text input box.

[0227] Among them, the application page of the text generation application can display the text input box in a variety of ways. For example, when jumping to the text generation application, the text input box is directly displayed in the application page of the text generation application. For example, when jumping to the text generation application, it is also necessary to click the start dialogue control in the text generation application to display the text input box in the application page of the text generation application. The specific method depends on the actual design of the text generation application, and the embodiments of the present disclosure are not limited here.

[0228] It should be noted that the triggering operation for the prompt text input box can be in various forms, for example, clicking the prompt text input box in the text generation application, or automatically triggering the text input box after waiting for a specified time in the text generation application. The specific operation depends on the actual design of the text generation application, and the embodiments of the present disclosure are not limited here.

[0229] Among them, the prompt text template is a reusable and structurally complete prompt text, which is used to guide the text generation application to generate a specific type of text content. After inserting the prompt text template in the prompt text input box, the prompt text template in the prompt text input box can also be edited, and the edited prompt text template can be used as the first prompt text; in addition, the prompt text template can be pre-stored in the first material library associated with the input keyboard, so that the preset area of ​​the input keyboard can display the prompt text template pre-stored in the first material library. The prompt text template can also be pre-stored in the second material library associated with the text generation application. When jumping to the text generation application, the prompt text template pre-stored in the second material library is automatically copied, so that the preset area of ​​the input keyboard can display the pre-copied prompt text template.

[0230] It should be noted that the triggering operation of the prompt text template can be in various forms, for example, clicking on the prompt text template or dragging and dropping the prompt text template, etc. In addition, the triggering operation of the prompt text template can be a single operation or a series of operations, depending on the actual design of the text generation application, and the embodiments of the present disclosure are not limited here.

[0231] It can be understood that by displaying an input keyboard in response to a triggering operation on a prompt text input box in a text generation application, the input keyboard can be displayed in the target application and is a virtual keyboard. A preset prompt text template is displayed on the input keyboard, and then in response to a triggering operation on the prompt text template, the prompt text template is inserted into the prompt text input box as the first prompt text, which can effectively save the time spent on inputting the first prompt text, further simplify the operation, and thus further improve the processing efficiency of the workflow.

[0232] In one possible implementation, in response to the operation of starting a workflow, the process jumps to the target application corresponding to the first work stage in the workflow, which can specifically be a running workflow processing application, which is provided with a workflow start control; in response to the triggering operation of the workflow start control, the permission configuration page is displayed, which is provided with a permission opening control; in response to the triggering operation of the permission opening control, the permission to obtain target data is opened for the workflow processing application, and the process jumps to the target application corresponding to the first work stage in the workflow, and the target data is used to generate guidance information.

[0233] The workflow processing application is an application program used to start a workflow. The workflow processing application can also be used to create, adjust, and terminate workflows. The workflow processing application can be provided with a workflow startup page, and the workflow startup control can be provided on the workflow startup page or on other pages of the workflow processing application. The embodiments of the present disclosure are not limited thereto.

[0234] It should be noted that the form of the workflow start control can be diverse. For example, the workflow start control can be an operational control such as a button control or a drag-and-drop control. Therefore, the form of the triggering operation of the workflow start control can be diverse. For example, the triggering operation of the workflow start control can include clicking the workflow start control or dragging and dropping the workflow start control, etc. In addition, the triggering operation of the workflow start control can be a single operation or a series of operations, which depends on the actual design of the workflow start control and is not limited in the embodiments of the present disclosure.

[0235] Among them, the permission configuration page can be a human-computer interaction page for the terminal running the workflow processing application. The permission configuration page supports users to view information and perform interactive operations, etc. The permission activation control can be set in a specific location on the permission configuration page. The permission configuration page can also be provided with a prompt for prompting to activate the permission to obtain the target data.

[0236] It should be noted that the form of the permission-enabling control can be diverse. For example, the permission-enabling control can be an operational control such as a button control or a drag-and-drop control. Therefore, the form of the triggering operation of the permission-enabling control can be diverse. For example, the triggering operation of the permission-enabling control can include clicking the permission-enabling control or dragging and dropping the permission-enabling control, etc. In addition, the triggering operation of the permission-enabling control can be a single operation or a series of operations, which depends on the actual design of the permission-enabling control and is not limited in the embodiments of the present disclosure.

[0237] Among them, target data refers to data used to determine whether the target operation corresponding to the task node has been completed. For example, the target data can be the current element identifier or the current operation instruction information. Assuming that the target operation corresponding to the task node is determined to be completed by other means, the target data can also be other data, which is not limited in the embodiment of the present disclosure. Since target data refers to data used to determine whether the target operation corresponding to the task node has been completed, guidance information can be generated based on the target data so that the guidance information can indicate the target operation to be performed to ensure the reliability of the guidance information. For example, in a text generation task node, when the detection result indicates that a generation result copy control is displayed in the application page, it is determined that the text generation operation is completed and the copy text task node is processed. According to the current element identifier corresponding to the generation result copy control, guidance information for prompting the generation result copy control to be triggered can be generated.

[0238] It is worth noting that the workflow processing application can obtain target data only during the processing of the workflow. The target data obtained by the workflow processing application can only be the current element identifier or the current operation instruction information. The target data does not include sensitive data. At the same time, the target data can be desensitized to further ensure that the target data does not include sensitive information. In addition, the workflow processing application and the target application can be installed in the same terminal, so that the workflow processing application obtains the target data from within the terminal, which can avoid the leakage of the target data. Specifically, the permission configuration page can be the permission configuration page of the terminal's accessibility service. After the permission is enabled, the workflow processing application can obtain the event stream of the target application through the accessibility service, and then extract the target data through the event stream.

[0239] It can be understood that by running the workflow processing application, and then responding to the trigger operation of the workflow start control, a permission configuration page with a permission opening control is displayed, and then responding to the trigger operation of the permission opening control, the permission to obtain target data is opened for the workflow processing application. When the workflow processing application opens the permission to obtain target data, it jumps to the target application corresponding to the first work stage in the workflow to start processing the workflow, so that the workflow processing application can determine whether the target operation corresponding to the task node has been executed through the target data during the processing of the workflow, ensuring that the workflow can be completed in an orderly manner. During the permission configuration process, the workflow start control of the workflow processing application can be triggered to quickly open the permission configuration page. There is no need to find the way to open the permission configuration page by yourself. By triggering the permission opening control, the permission to obtain target data is opened for the workflow processing application, and it can jump to the target application corresponding to the first work stage in the workflow, which can simplify the operation and further improve the processing efficiency of the workflow.

[0240] It is worth noting that in response to the triggering operation of the workflow start control, the permission configuration page is displayed. Specifically, in response to the triggering operation of the workflow start control, the permission status of the workflow processing application is determined; when the permission status indicates that the workflow processing application has not enabled the permission to obtain the target data, the permission configuration page is displayed; when the permission status indicates that the workflow processing application has enabled the permission to obtain the target data, the process jumps to the target application corresponding to the first work stage in the workflow. Based on this, when the workflow start control is triggered, if the workflow processing application has already enabled the permission to obtain the target data in advance, the process jumps directly to the target application corresponding to the first work stage in the workflow without having to enable the permission again through the permission configuration page. This can simplify the operation and further improve the processing efficiency of the workflow.

[0241] It should be noted that, in addition to being configured to directly display the permission configuration page when triggered, the workflow startup control can also be configured not to directly display the permission configuration page when triggered. This method is described in detail below.

[0242] In one possible implementation, in response to a triggering operation on a workflow start control, a permission configuration page is displayed. Specifically, in response to a triggering operation on a workflow start control, a permission guide page is displayed, the permission guide page displays prompt information and is provided with a jump control, the prompt information is used to indicate the operation to be performed when the permission to obtain target data is enabled for the workflow processing application in the permission configuration page; in response to a triggering operation on the jump control, the permission configuration page is displayed.

[0243] Among them, the permission guidance page can be a human-computer interaction page for a workflow processing application. The permission guidance page supports users to view information and perform interactive operations, etc. Prompt information and jump controls can be set in specific locations on the permission configuration page.

[0244] It should be noted that the form of the jump control can be diverse. For example, the jump control can be an operational control such as a button control or a drag-and-drop control. Therefore, the form of the triggering operation of the jump control can be diverse. For example, the triggering operation of the jump control can include clicking the jump control or dragging and dropping the jump control, etc. In addition, the triggering operation of the jump control can be a single operation or a series of operations, which depends on the actual design of the permission-enabling control. The embodiments of the present disclosure are not limited here.

[0245] It can be understood that by responding to the triggering operation of the workflow start control, a permission guidance page with prompt information and a jump control is displayed, and the prompt information prompts the operation to be performed when the permission to obtain target data is enabled for the workflow processing application in the permission configuration page. Then, in response to the triggering operation of the jump control, the permission configuration page is displayed, and the permission to obtain target data is enabled for the workflow processing application in the permission configuration page. There is no need to find the way to open the permission configuration page by yourself, which can simplify the operation and further improve the processing efficiency of the workflow.

[0246] In one possible implementation, a workflow startup control is set on a workflow startup page of a workflow processing application. In response to a triggering operation on the workflow startup control, before displaying a permission configuration page, the workflow processing method further includes: when all target applications have been downloaded, displaying a downloaded mark on the workflow startup page, and the downloaded mark is used to indicate that all target applications have been downloaded; when there is at least one application that has not been downloaded, displaying a download control on the workflow startup page, and in response to a triggering operation on the download control, downloading the undownloaded application, and the undownloaded application is a target application that has not been downloaded.

[0247] Among them, the target application has been downloaded means that the target application has been installed and can be run on the terminal. Therefore, all target applications have been downloaded means that all target applications used in the processing workflow have been installed and can be run. For example, assuming that three target applications are required to process the workflow, then when these three target applications are installed and can be run, it means that all target applications have been downloaded.

[0248] Among them, the downloaded identifier is used to indicate that all target applications used to process the workflow are in a ready state. The form of the downloaded identifier can be diverse. For example, the form of the downloaded identifier can include an icon, a control or text, etc., which is not limited in this embodiment of the present disclosure.

[0249] It should be noted that the download control can be in various forms. For example, the download control can be an operational control such as a button control or a drag-and-drop control. Therefore, the triggering operation of the download control can be in various forms. For example, the triggering operation of the download control can include clicking the download control or dragging and dropping the download control, etc. In addition, the triggering operation of the download control can be a single operation or a series of operations, which depends on the actual design of the download control. The embodiments of the present disclosure are not limited here.

[0250] It can be understood that when all target applications have been downloaded, it means that all target applications used to process the workflow are in a ready state, ensuring that each target application can be jumped to run. At this time, a downloaded mark is displayed on the workflow startup page, prompting that there is no need to download the target application. When there is at least one undownloaded application, that is, there is an undownloaded target application, it means that at least one target application used to process the workflow is not in a ready state. By displaying a download control on the workflow startup page and then downloading the undownloaded application in response to the triggering operation of the download control, it can be ensured that all target applications used to process the workflow are in a ready state. By triggering the download control to quickly download the undownloaded application, the operation can be simplified, thereby further improving the processing efficiency of the workflow.

[0251] For example, refer to Figure 14 , Figure 14 This is a schematic diagram of an optional page in the process of starting a workflow in a workflow processing application provided in an embodiment of the present disclosure.

[0252] Among them, a workflow processing application is run, and the application page of the workflow processing application can be a workflow start page 1401. A workflow start control 1402 for starting the workflow with one click is set on the workflow start page 1401. When all target applications have been downloaded, the workflow start page 1401 displays a downloaded mark 1403. When the permission has been enabled, the workflow start page 1401 displays an enabled mark 1404.

[0253] Then, when the permission is not enabled, by clicking the workflow start control 1402, the permission guide page 1405 can be displayed. The permission guide page is provided with prompt information 1406 and a jump control 1407. The prompt information 1406 is used to display the permission configuration process, and the jump control 1407 can be provided with the text "Go to enable".

[0254] Then, refer to Figure 15 , Figure 15 A schematic diagram of an optional page in the permission opening process provided in an embodiment of the present disclosure.

[0255] Among them, by clicking the jump control 1407, the permission configuration page 1501 can be displayed. The permission configuration page 1501 is provided with a permission opening control 1502 and an opening confirmation control 1503. By clicking the permission opening control 1502 and then clicking the opening confirmation control 1503, the permission to obtain target data is opened for the workflow processing application.

[0256] The complete process of the workflow processing method is described in detail below.

[0257] Reference Figure 16 , Figure 16 A schematic diagram of an optional architecture of the workflow processing method provided in the embodiment of the present disclosure.

[0258] First, when all target applications have been downloaded, a downloaded indicator is displayed on the workflow startup page, and the downloaded indicator is used to indicate that all target applications have been downloaded; when there is at least one application that has not been downloaded, a download control is displayed on the workflow startup page, and in response to the triggering operation of the download control, the undownloaded application is downloaded, and the undownloaded application is the target application that has not been downloaded.

[0259] Then, the user can run a workflow processing application on the terminal, and the workflow processing application is provided with a workflow start control; in response to the triggering operation of the workflow start control, a permission guidance page is displayed, and the permission guidance page displays prompt information and is provided with a jump control, and the prompt information is used to indicate the operation to be performed when the permission to obtain target data is enabled for the workflow processing application in the permission configuration page; in response to the triggering operation of the jump control, a permission configuration page is displayed, and the permission configuration page is provided with a permission enable control; in response to the user's triggering operation of the permission enable control, the permission to obtain target data is enabled for the workflow processing application, and the process jumps to the target application corresponding to the first work stage in the workflow, and the target data is used to generate guidance information, which is equivalent to enabling the permission of the accessibility service 1602. The target data may include the current element identifier or the current operation instruction information. The target data can be obtained by extracting the page change event or page interaction event provided by the accessibility service 1602 through the event handler of the workflow processing application. For example, the page state change 1601 extracted from the page change event can determine the current element identifier, and the interactive operation extracted from the page interaction event can determine the current operation instruction information.

[0260] Then, a floating window is displayed in the target application of the current jump, and the guidance information corresponding to the first task node is displayed in the floating window, which is equivalent to obtaining the current task node from multiple task nodes in the task list 1603. The task list 1603 is used to record each task node of the workflow; the application page of the target application of the current jump is detected to obtain the current element identifier of the current page element. The current page element is the page element currently displayed in the application page; the preset element identifier of the target page element is obtained, and the current element identifier is matched with the preset element identifier for consistency to obtain the detection result.

[0261] Then, whenever the detection result indicates that the target page element is displayed in the application page, it is determined that the target operation corresponding to the current task node has been executed, and the guidance information in the floating window is updated to the guidance information corresponding to the next task node, which is equivalent to judging whether the task is completed. After determining that the task is completed, the guidance information needs to be updated, and the user is prompted with the updated guidance information through the floating window. After the task is completed, other operations to be performed can be performed, and then the next task node is started. The next task node is determined through the task list 1603, and the completed task node is deleted from the task list 1603. The target page element is the page element corresponding to the current task node, and the guidance information is used to indicate the target operation to be performed when the target application of the current jump is processing the corresponding work stage.

[0262] Then, whenever it is detected that the target operations in the current target application have been completed, jump to the target application corresponding to the next work stage, display the guidance information again in the current target application and execute the corresponding target operations until the task list 1603 is empty and the workflow ends.

[0263] Based on this, by responding to the operation of starting the workflow, jumping to the target application corresponding to the first work stage in the workflow, it is realized that the process automatically jumps to the first target application when processing the first work stage, and then the guidance information is displayed in the target application currently jumped. The guidance information indicates the target operation to be performed by the target application currently jumped when processing the corresponding work stage. Since the target operations in the target application have been completed, it means that the corresponding work stage processing is completed. Therefore, whenever it is detected that the target operations in the target application currently jumped have been completed, it jumps to the target application corresponding to the next work stage, and the guidance information is displayed again in the target application currently jumped and the corresponding target operation is executed. The new work stage is processed through the next target application until the workflow is ended, and it is realized that the process automatically jumps to the corresponding target application when processing the new work stage. No manual operation is required, which can simplify the operation. Moreover, the guidance information can be quickly displayed in the corresponding target application during the processing of each work stage, so that the guidance information can be quickly viewed during the processing of the workflow without switching the target application. This can simplify the operation and thus improve the processing efficiency of the workflow.

[0264] It is worth noting that the workflow processing method can be applied to a variety of scenarios. For example, in a video creation scenario, whenever the detection result indicates that the target page element is displayed in the application page, it is determined that the target operation corresponding to the current task node is completed, and the guidance information in the floating window is updated to the guidance information corresponding to the next task node, including: when the detection result indicates that the first prompt text is displayed in the application page, it is determined that the first input operation is completed, and the guidance information in the floating window is updated to the guidance information corresponding to the text generation operation; when the detection result indicates that the generation result copy control is displayed in the application page, it is determined that the text generation operation is completed, and the guidance information in the floating window is updated to the guidance information corresponding to the generation result copy operation;

[0265] Then, whenever it is detected that the target operations in the currently jumped target application have been completed, jump to the target application corresponding to the next work stage, display the guidance information again in the currently jumped target application and perform the corresponding target operations until the workflow is completed, including: when the detection result indicates that a copy success prompt is displayed on the application page, determine that the target operations in the text generation application have been completed, and jump to the image generation application;

[0266] Then, when the detection result indicates that the second prompt text is displayed in the application page, it is determined that the second input operation is completed, and the guidance information in the floating window is updated to the guidance information corresponding to the image generation operation; when the detection result indicates that the generation result save control is displayed in the application page, it is determined that the image generation operation is completed, and the guidance information in the floating window is updated to the guidance information corresponding to the generation result save operation; when the detection result indicates that a save success prompt is displayed in the application page, it is determined that all target operations in the image generation application are completed, and jump to the video generation application;

[0267] Then, when the detection result indicates that the third prompt text is displayed in the application page, it is determined that the third input operation has been completed, and the guide information in the floating window is updated to the guide information corresponding to the video generation operation; when the detection result indicates that the cover setting control is displayed in the application page, it is determined that the video generation operation has been completed, and the guide information in the floating window is updated to the guide information corresponding to the cover setting operation; when the detection result indicates that a cover image is inserted in the application page, it is determined that the cover setting operation corresponding to the currently displayed guide information has been completed, and the guide information in the floating window is updated to the guide information corresponding to the video export operation; when the detection result indicates that the export success prompt is displayed in the application page, it is determined that all target operations in the video generation application have been completed, and the workflow ends. Based on this, during the processing of the video creation workflow, it is possible to quickly view the guide information without switching the target application, which can simplify the operation and thus improve the processing efficiency of the video creation workflow.

[0268] It will be appreciated that, although the various steps in the above-mentioned various flow charts are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless clearly stated in the present embodiment, the execution of these steps does not have strict order restrictions, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the above-mentioned flow charts can include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps.

[0269] Reference Figure 17 , Figure 17 This is an optional structural diagram of a workflow processing device provided in an embodiment of the present disclosure. The workflow processing device 1700 includes:

[0270] The first processing module 1701 is configured to jump to the target application corresponding to the first work stage in the workflow in response to the operation of starting the workflow, and each work stage of the workflow is processed by the corresponding target application;

[0271] The second processing module 1702 is used to display guidance information in the target application currently jumped to, where the guidance information is used to indicate the target operation to be performed by the target application currently jumped to when processing the corresponding working phase;

[0272] The third processing module 1703 is used to jump to the target application corresponding to the next work stage whenever it is detected that the target operation in the current jump target application has been completed, display the guidance information again in the current jump target application and execute the corresponding target operation until the workflow is completed.

[0273] Furthermore, the working phase includes a plurality of task nodes in order, and the second processing module 1702 is specifically used to:

[0274] Display a floating window in the target application currently being redirected, and display the guidance information corresponding to the first task node in the floating window;

[0275] Whenever it is detected that the target operation corresponding to the current task node is completed, the guidance information in the floating window is updated to the guidance information corresponding to the next task node.

[0276] Furthermore, the second processing module 1702 is specifically configured to:

[0277] Perform page element detection on the application page of the target application currently being redirected to obtain the detection result;

[0278] Whenever the detection result indicates that the target page element is displayed in the application page, it is determined that the target operation corresponding to the current task node has been executed, and the guidance information in the floating window is updated to the guidance information corresponding to the next task node, and the target page element is the page element corresponding to the current task node.

[0279] Furthermore, the second processing module 1702 is specifically configured to:

[0280] Performing page element detection on the application page of the target application currently being redirected to obtain a current element identifier of the current page element, where the current page element is the page element currently displayed on the application page;

[0281] Obtain the preset element identifier of the target page element, perform consistency matching on the current element identifier and the preset element identifier, and obtain a detection result.

[0282] Furthermore, the second processing module 1702 is specifically configured to:

[0283] Perform consistency matching on the current element identifier and the preset element identifier to obtain a first matching result;

[0284] Get the current operation instruction information of the current operation. The current operation is the operation triggered before the current target page element is generated and after the previous target page element is generated;

[0285] Obtaining preset operation instruction information of the target operation, performing consistency matching between the current operation instruction information and the preset operation instruction information, and obtaining a second matching result;

[0286] A logical judgment is performed based on the first matching result and the second matching result to obtain a detection result.

[0287] Furthermore, if the target application currently jumped to is a text generation application, the target operations corresponding to the multiple task nodes include, in sequence, a first input operation, a text generation operation, and a generation result copy operation, and the target page elements include a first prompt text, a generation result copy control, or a copy success prompt, the second processing module 1702 is specifically used to:

[0288] When the detection result indicates that the first prompt text is displayed in the application page, determining that the first input operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the text generation operation;

[0289] When the detection result indicates that a generation result copy control is displayed on the application page, it is determined that the text generation operation is completed, and the guidance information in the floating window is updated to the guidance information corresponding to the generation result copy operation;

[0290] Furthermore, the third processing module 1703 is specifically configured to:

[0291] When the detection result indicates that a successful copy prompt is displayed on the application page, it is determined that all target operations in the text generation application have been executed, and the process jumps to the target application corresponding to the next work stage. The guidance information is displayed again in the currently jumped target application and the corresponding target operation is executed until the workflow is completed.

[0292] Furthermore, if the target application corresponding to the next work phase is an image generation application, the target operations corresponding to the multiple task nodes include, in sequence, a second input operation, an image generation operation, and a generation result saving operation, and the target page elements include a second prompt text generated by the text generation application, a generation result saving control, or a save success prompt, the third processing module 1703 is specifically configured to:

[0293] When the detection result indicates that a copy success prompt is displayed on the application page, it is determined that all target operations in the text generation application have been completed, and the process jumps to the image generation application;

[0294] When the detection result indicates that the second prompt text is displayed on the application page, determining that the second input operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the image generation operation;

[0295] When the detection result indicates that a generation result save control is displayed on the application page, it is determined that the image generation operation is completed, and the guidance information in the floating window is updated to the guidance information corresponding to the generation result save operation;

[0296] When the detection result indicates that a successful save prompt is displayed on the application page, it is determined that all target operations in the image generation application have been completed, and the process jumps to the target application corresponding to the next work stage. The guidance information is displayed again in the currently jumped target application and the corresponding target operation is executed until the workflow is completed.

[0297] Furthermore, if the target application corresponding to the next work phase is a video generation application, the target operations corresponding to the multiple task nodes include, in sequence, a third input operation, a video generation operation, a cover setting operation, and a video export operation, and the target page elements include a third prompt text, a cover setting control, a cover image generated by the image generation application, or an export success prompt. The third processing module 1703 is specifically configured to:

[0298] When the detection result indicates that a successful save prompt is displayed on the application page, it is determined that all target operations in the image generation application have been completed, and the process jumps to the video generation application;

[0299] When the detection result indicates that the third prompt text is displayed on the application page, determining that the third input operation is completed, and updating the guidance information in the floating window to guidance information corresponding to the video generation operation;

[0300] When the detection result indicates that the cover setting control is displayed in the application page, it is determined that the video generation operation is completed, and the guidance information in the floating window is updated to the guidance information corresponding to the cover setting operation;

[0301] When the detection result indicates that a cover image has been inserted into the application page, determining that the cover setting operation corresponding to the currently displayed guidance information has been completed, and updating the guidance information in the floating window to guidance information corresponding to the video export operation;

[0302] When the detection result indicates that an export success prompt is displayed on the application page, it is determined that all target operations in the video generation application have been completed, and the workflow ends.

[0303] Furthermore, the workflow processing device further includes a text insertion module (not shown in the figure), which is specifically used to:

[0304] In response to a triggering operation on a prompt text input box in a text generation application, an input keyboard is displayed, and a preset prompt text template is displayed on the input keyboard;

[0305] In response to a triggering operation on the prompt text template, the prompt text template is inserted into the prompt text input box as the first prompt text.

[0306] Furthermore, the first processing module 1701 is specifically configured to:

[0307] Running a workflow processing application, wherein the workflow processing application is provided with a workflow start control;

[0308] In response to a triggering operation on a workflow start control, a permission configuration page is displayed, wherein the permission configuration page is provided with a permission start control;

[0309] In response to the triggering operation of the permission opening control, the permission to obtain target data is opened for the workflow processing application, and the process jumps to the target application corresponding to the first work stage in the workflow. The target data is used to generate guidance information.

[0310] Furthermore, the first processing module 1701 is specifically configured to:

[0311] In response to a triggering operation on a workflow start control, a permission guidance page is displayed, wherein the permission guidance page displays prompt information and is provided with a jump control, wherein the prompt information is used to indicate an operation to be performed when the permission to obtain target data is enabled for the workflow processing application in the permission configuration page;

[0312] In response to the triggering operation on the jump control, the permission configuration page is displayed.

[0313] Furthermore, the workflow start control is set on the workflow start page of the workflow processing application. The workflow processing device further includes an application download module (not shown in the figure), which is specifically used to:

[0314] When all target applications have been downloaded, a downloaded indicator is displayed on the workflow start page. The downloaded indicator is used to indicate that all target applications have been downloaded.

[0315] When there is at least one undownloaded application, a download control is displayed on the workflow start page. In response to a triggering operation on the download control, the undownloaded application is downloaded, and the undownloaded application is a target application that has not been downloaded.

[0316] The above-mentioned workflow processing device 1700 and the workflow processing method are based on the same inventive concept. By responding to the operation of starting the workflow, jumping to the target application corresponding to the first work stage in the workflow, it is realized that the process automatically jumps to the first target application when processing the first work stage, and then displays guidance information in the target application currently jumped to. The guidance information indicates the target operation to be performed by the target application currently jumped to when processing the corresponding work stage. Since the target operations in the target application have been completed, it means that the processing of the corresponding work stage is completed. Therefore, whenever it is detected that the target operations in the target application currently jumped to have been completed, it jumps to the target application corresponding to the next work stage, and displays guidance information again in the target application currently jumped to and executes the corresponding target operation. The new work stage is processed by the next target application until the workflow is terminated, and the process automatically jumps to the corresponding target application when processing the new work stage. No manual operation is required, which can simplify the operation. Moreover, the guidance information can be quickly displayed in the corresponding target application during the processing of each work stage, so that the guidance information can be quickly viewed without switching the target application during the processing of the workflow. This can simplify the operation and thus improve the processing efficiency of the workflow.

[0317] The electronic device for executing the above-mentioned workflow processing method provided by the embodiment of the present disclosure may be a terminal. Figure 18 , Figure 18 This is a partial structural block diagram of a terminal provided in an embodiment of the present disclosure. The terminal includes: a camera assembly 1810, a first memory 1820, an input unit 1830, a display unit 1840, a sensor 1850, an audio circuit 1860, a wireless fidelity (WiFi) module 1870, a first processor 1880, and a first power supply 1890. Those skilled in the art will understand that Figure 18 The terminal structure shown in the figure does not constitute a limitation to the terminal, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0318] The camera assembly 1810 can be used to capture images or videos. Optionally, the camera assembly 1810 includes a front camera and a rear camera. Typically, the front camera is set on the front panel of the terminal, and the rear camera is set on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions.

[0319] The first memory 1820 may be used to store software programs and modules. The first processor 1880 executes the software programs and modules stored in the first memory 1820 to execute various functional applications and data processing of the terminal.

[0320] The input unit 1830 may be configured to receive input digital or character information and generate key signal input related to terminal settings and function control. Specifically, the input unit 1830 may include a touch panel 1831 and other input devices 1832 .

[0321] The display unit 1840 may be configured to display input information or provided information and various menus of the terminal. The display unit 1840 may include a display panel 1841 .

[0322] The audio circuit 1860 , the speaker 1861 , and the microphone 1862 may provide an audio interface.

[0323] The first power source 1890 may be alternating current, direct current, a disposable battery, or a rechargeable battery.

[0324] The number of sensors 1850 can be one or more, and the one or more sensors 1850 include but are not limited to: acceleration sensors, gyroscope sensors, pressure sensors, optical sensors, etc. Among them:

[0325] The accelerometer can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the terminal. For example, the accelerometer can be used to detect the components of gravity acceleration on the three coordinate axes. The first processor 1880 can control the display unit 1840 to display the user interface in a horizontal or vertical view based on the gravity acceleration signal collected by the accelerometer. The accelerometer can also be used to collect game or user motion data.

[0326] The gyroscope sensor can detect the terminal's orientation and rotation angle. It can also work with the accelerometer to capture the user's 3D movements on the terminal. Based on the data collected by the gyroscope sensor, the first processor 1880 can implement the following functions: motion sensing (such as changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0327] The pressure sensor can be set on the side frame of the terminal and / or the lower layer of the display unit 1840. When the pressure sensor is set on the side frame of the terminal, it can detect the user's grip signal of the terminal, and the first processor 1880 performs left and right hand recognition or shortcut operations based on the grip signal collected by the pressure sensor. When the pressure sensor is set on the lower layer of the display unit 1840, the first processor 1880 controls the operability controls on the UI interface based on the user's pressure operation on the display unit 1840. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0328] The optical sensor is used to collect ambient light intensity. In one embodiment, the first processor 1880 can control the display brightness of the display unit 1840 based on the ambient light intensity collected by the optical sensor. Specifically, when the ambient light intensity is high, the display brightness of the display unit 1840 is increased; when the ambient light intensity is low, the display brightness of the display unit 1840 is decreased. In another embodiment, the first processor 1880 can also dynamically adjust the shooting parameters of the camera assembly 1810 based on the ambient light intensity collected by the optical sensor.

[0329] In this embodiment, the first processor 1880 included in the terminal can execute the workflow processing method of the previous embodiment.

[0330] The electronic device for executing the above-mentioned workflow processing method provided by the embodiment of the present disclosure may also be a server. Figure 19 , Figure 19 This is a partial structural block diagram of a server provided in an embodiment of the present disclosure. The server may have relatively large differences due to different configurations or performances, and may include one or more second processors 1910 and a second memory 1930, and one or more storage media 1940 (for example, one or more mass storage devices) storing application programs 1943 or data 1942. Among them, the second memory 1930 and the storage medium 1940 can be short-term storage or persistent storage. The program stored in the storage medium 1940 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Furthermore, the second processor 1910 can be configured to communicate with the storage medium 1940 to execute a series of instruction operations in the storage medium 1940 on the server.

[0331] The server may also include one or more second power supplies 1920, one or more wired or wireless network interfaces 1950, one or more input and output interfaces 1960, and / or one or more operating systems 1941, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0332] The second processor 1910 in the server may be configured to execute the workflow processing method.

[0333] The embodiments of the present disclosure further provide a computer-readable storage medium, which is used to store a computer program. The computer program is used to execute the workflow processing methods of the aforementioned embodiments.

[0334] The present disclosure also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. A processor of an electronic device reads the computer program from the computer-readable storage medium and executes the computer program, causing the electronic device to implement the workflow processing method.

[0335] The terms "first," "second," "third," "fourth," and the like (if any) in the specification of the present disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate to describe embodiments of the present disclosure, e.g., capable of being implemented in orders other than those illustrated or described herein. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions, e.g., a process, method, system, product, or apparatus comprising a series of steps or elements is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0336] It should be understood that in the present disclosure, "at least one (item)" refers to one or more, and "plurality" refers to two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0337] It should be understood that in the description of the embodiments of the present disclosure, the meaning of multiple (or multiple items) is more than two, greater than, less than, exceed, etc. are understood to exclude the number itself, and above, below, within, etc. are understood to include the number itself.

[0338] In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0339] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0340] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0341] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the various embodiments of the present disclosure. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

[0342] It should also be understood that the various implementations provided in the embodiments of the present disclosure can be combined arbitrarily to achieve different technical effects.

[0343] The above is a specific description of the preferred implementation of the present disclosure, but the present disclosure is not limited to the above implementation. Technical personnel familiar with the art can also make various equivalent modifications or substitutions under the shared conditions that do not violate the spirit of the present disclosure. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present disclosure.

Claims

1. A workflow processing method, characterized in that: include: In response to the operation of starting a workflow, jumping to the target application corresponding to the first work stage in the workflow, each work stage of the workflow is processed by the corresponding target application respectively; Displaying guidance information in the target application currently jumped to, wherein the guidance information is used to indicate a target operation to be performed by the target application currently jumped to when processing the corresponding working phase; Whenever it is detected that the target operation in the target application currently jumped to has been completed, jump to the target application corresponding to the next work stage, display the guidance information again in the target application currently jumped to and execute the corresponding target operation until the workflow is completed.

2. The workflow processing method according to claim 1, characterized in that: The working phase includes a plurality of task nodes in order, and the displaying of the guidance information in the target application currently jumped to includes: Displaying a floating window in the target application currently jumped to, and displaying guidance information corresponding to the first task node in the floating window; Whenever it is detected that the target operation corresponding to the current task node is completed, the guidance information in the floating window is updated to the guidance information corresponding to the next task node.

3. The workflow processing method according to claim 2, wherein: Whenever it is detected that the target operation corresponding to the current task node is completed, updating the guidance information in the floating window to the guidance information corresponding to the next task node includes: Performing page element detection on the target application page currently redirected to obtain a detection result; Whenever the detection result indicates that the target page element is displayed in the application page, it is determined that the target operation corresponding to the current task node has been executed, and the guidance information in the floating window is updated to the guidance information corresponding to the next task node, and the target page element is the page element corresponding to the current task node.

4. The workflow processing method according to claim 3, characterized in that: The performing page element detection on the application page of the target application currently jumped to obtain the detection result includes: Performing page element detection on the application page of the target application currently jumped to obtain a current element identifier of the current page element, where the current page element is a page element currently displayed on the application page; The preset element identifier of the target page element is obtained, and the current element identifier is matched with the preset element identifier to obtain a detection result.

5. The workflow processing method according to claim 4, characterized in that: The performing consistency matching between the current element identifier and the preset element identifier to obtain a detection result includes: Performing consistency matching on the current element identifier and the preset element identifier to obtain a first matching result; Obtaining current operation instruction information of a current operation, where the current operation is an operation triggered before generating the current target page element and after generating the previous target page element; Obtaining preset operation instruction information of the target operation, performing consistency matching between the current operation instruction information and the preset operation instruction information to obtain a second matching result; A logical judgment is performed based on the first matching result and the second matching result to obtain a detection result.

6. The workflow processing method according to claim 3, characterized in that: If the target application currently being redirected is a text generation application, the target operations corresponding to the plurality of task nodes sequentially include a first input operation, a text generation operation, and a generation result copy operation, and the target page element includes a first prompt text, a generation result copy control, or a copy success prompt, and whenever the detection result indicates that a target page element is displayed on the application page, determining that the target operation corresponding to the current task node has been completed, and updating the guidance information in the floating window to the guidance information corresponding to the next task node, include: When the detection result indicates that the first prompt text is displayed on the application page, determining that the first input operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the text generation operation; When the detection result indicates that the generation result copy control is displayed in the application page, determining that the text generation operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the generation result copy operation; Whenever it is detected that the target operation in the target application currently jumped to is completed, jumping to the target application corresponding to the next work stage, displaying the guidance information again in the target application currently jumped to and executing the corresponding target operation until the workflow is terminated, including: When the detection result indicates that the copy success prompt is displayed in the application page, it is determined that the target operations in the text generation application have been completed, and the process jumps to the target application corresponding to the next work stage. The guidance information is displayed again in the target application currently jumped to and the corresponding target operation is executed until the workflow is completed.

7. The workflow processing method according to claim 6, characterized in that: If the target application corresponding to the next work stage is an image generation application, the target operations corresponding to the multiple task nodes sequentially include a second input operation, an image generation operation, and a generation result saving operation, and the target page elements include a second prompt text generated by the text generation application, a generation result saving control, or a save success prompt. When the detection result indicates that the copy success prompt is displayed on the application page, it is determined that all the target operations in the text generation application have been completed, and the process jumps to the target application corresponding to the next work stage. The process again displays the guidance information in the currently jumped target application and executes the corresponding target operation until the workflow ends, including: When the detection result indicates that the copy success prompt is displayed on the application page, determining that the target operations in the text generation application are all completed, and jumping to the image generation application; When the detection result indicates that the second prompt text is displayed on the application page, determining that the second input operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the image generation operation; When the detection result indicates that the generation result saving control is displayed on the application page, determining that the image generation operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the generation result saving operation; When the detection result indicates that the save success prompt is displayed in the application page, it is determined that the target operations in the image generation application have been completed, and the process jumps to the target application corresponding to the next work stage. The guidance information is displayed again in the target application currently jumped to and the corresponding target operation is executed until the workflow is completed.

8. The workflow processing method according to claim 7, characterized in that: If the target application corresponding to the next work stage is a video generation application, the target operations corresponding to the multiple task nodes include, in sequence, a third input operation, a video generation operation, a cover setting operation, and a video export operation, and the target page elements include the third prompt text, a cover setting control, a cover image generated by the image generation application, or an export success prompt, when the detection result indicates that the save success prompt is displayed on the application page, determining that all the target operations in the image generation application have been completed, jumping to the target application corresponding to the next work stage, displaying the guidance information again in the currently jumped target application and executing the corresponding target operation, until the workflow is terminated, including: When the detection result indicates that the save success prompt is displayed on the application page, determining that the target operations in the image generation application are all executed, and jumping to the video generation application; When the detection result indicates that the third prompt text is displayed on the application page, determining that the third input operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the video generation operation; When the detection result indicates that the cover setting control is displayed in the application page, determining that the video generation operation is completed, and updating the guidance information in the floating window to the guidance information corresponding to the cover setting operation; When the detection result indicates that the cover image is inserted into the application page, determining that the cover setting operation corresponding to the currently displayed guide information is completed, and updating the guide information in the floating window to the guide information corresponding to the video export operation; When the detection result indicates that the export success prompt is displayed in the application page, it is determined that all the target operations in the video generation application have been completed, and the workflow is ended.

9. The workflow processing method according to claim 6, characterized in that: When the detection result indicates that the first prompt text is displayed on the application page, before determining that the first input operation is completed, the workflow processing method further includes: In response to a triggering operation on a prompt text input box in the text generation application, displaying an input keyboard, and displaying a preset prompt text template on the input keyboard; In response to a triggering operation on the prompt text template, the prompt text template is inserted into the prompt text input box as the first prompt text.

10. The workflow processing method according to claim 1, wherein: In response to the operation of starting the workflow, jumping to the target application corresponding to the first work stage in the workflow includes: Running a workflow processing application, wherein the workflow processing application is provided with a workflow start control; In response to a triggering operation on the workflow start control, displaying a permission configuration page, wherein the permission configuration page is provided with a permission start control; In response to the triggering operation of the permission opening control, the permission to obtain target data is opened for the workflow processing application, and the process jumps to the target application corresponding to the first work stage in the workflow. The target data is used to generate the guidance information.

11. The workflow processing method according to claim 10, characterized in that: The step of displaying a permission configuration page in response to a triggering operation on the workflow start control includes: In response to a triggering operation on the workflow start control, displaying a permission guidance page, wherein the permission guidance page displays prompt information and is provided with a jump control, wherein the prompt information is used to indicate an operation to be performed when the permission to obtain the target data is enabled for the workflow processing application in the permission configuration page; In response to a triggering operation on the jump control, the permission configuration page is displayed.

12. The workflow processing method according to claim 10, characterized in that: The workflow start control is set on the workflow start page of the workflow processing application. Before displaying the permission configuration page in response to the triggering operation of the workflow start control, the workflow processing method further includes: When all the target applications have been downloaded, a downloaded mark is displayed on the workflow start page, where the downloaded mark is used to indicate that all the target applications have been downloaded; When there is at least one undownloaded application, a download control is displayed on the workflow start page, and in response to a triggering operation on the download control, the undownloaded application is downloaded, where the undownloaded application is the undownloaded target application.

13. A workflow processing device, characterized in that: include: A first processing module is configured to jump to a target application corresponding to a first work stage in the workflow in response to an operation of starting the workflow, wherein each work stage of the workflow is processed by the corresponding target application; a second processing module, configured to display guidance information in the target application currently redirected, wherein the guidance information is used to indicate a target operation to be performed by the target application currently redirected when processing the corresponding working phase; The third processing module is used to jump to the target application corresponding to the next work stage whenever it is detected that the target operation in the target application currently jumped to has been executed, and to display the guidance information again in the target application currently jumped to and execute the corresponding target operation until the workflow is completed.

14. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the workflow processing method according to any one of claims 1 to 12 is implemented.

15. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the workflow processing method according to any one of claims 1 to 12 is implemented.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the workflow processing method according to any one of claims 1 to 12 is implemented.