Application creation method and apparatus, electronic device, and storage medium

Abstract

The present disclosure relates to an application creation method and device, electronic equipment and storage medium, the method comprising: in response to an attribute setting operation of creating an application interface, a process arrangement interface corresponding to a target application to be created is displayed, the process arrangement interface displays model nodes, dataset nodes and prompt word nodes, and process arrangement relationships between the model nodes, the dataset nodes and the prompt word nodes; in response to setting operations on the model nodes, the dataset nodes and the prompt word nodes respectively, based on a target model corresponding to the model nodes, a target dataset corresponding to the dataset nodes, and a target prompt word corresponding to the prompt word nodes, the target application is created, the target application is used to answer questions input by a user through the target model after learning the target dataset and the target prompt word through the target model.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more particularly to an application creation method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] Currently, in many scenarios, a lot of human resources are needed for system operation and maintenance. For example, after a product is launched, when users encounter problems while using the product, developers or operations and maintenance personnel need to help solve the problems. Subsequently, it may also be necessary to fill in problem summaries, fill in database entries, and other tasks.

[0003] However, relying on manual operation and maintenance is both untimely and prone to errors, resulting in low efficiency in various scenarios. Summary of the Invention

[0004] To solve the above-mentioned technical problems, or at least partially solve them, this disclosure provides an application creation method, apparatus, electronic device, storage medium, and program product.

[0005] A first aspect of this disclosure provides an application creation method, comprising: in response to an attribute setting operation in an application creation interface, displaying a flow orchestration interface corresponding to a target application to be created, the flow orchestration interface displaying a model node, a dataset node, and a prompt word node, and the flow orchestration relationship between the model node, the dataset node, and the prompt word node; in response to setting operations on the model node, the dataset node, and the prompt word node respectively, creating the target application based on a target model corresponding to the model node, a target dataset corresponding to the dataset node, and a target prompt word corresponding to the prompt word node, the target application being used to answer user input questions through the target model after learning the target dataset and the target prompt word through the target model.

[0006] In some embodiments of this disclosure, before displaying the process orchestration interface corresponding to the target application to be created in response to the attribute setting operation of the application creation interface, the method further includes: displaying the application creation interface in response to the triggering operation of the application creation control, the application creation interface being used to set attribute information corresponding to the target application, the attribute information including at least one of the following: application name, application description, and application type.

[0007] In some embodiments of this disclosure, when the first node is selected, the process orchestration interface also displays the setting information of the first node; the method further includes: in response to the selection operation of the second node, switching the second node to the selected state, and updating the setting information of the first node displayed in the process orchestration interface to the setting information of the second node; or, the process orchestration interface also displays the setting information of the dataset node, the setting information of the model node, and the setting information of the prompt word node. When the first node is selected, the setting information of the first node is displayed in the target area. The method further includes: in response to the selection operation of the second node, switching the second node to the selected state, and displaying the setting information of the second node in the target area; wherein the first node and the second node are different nodes among the model node, the dataset node, and the prompt word node.

[0008] In some embodiments of this disclosure, the method further includes: in response to a triggering operation of a model comparison control, displaying a model comparison interface, the model comparison interface including a parameter setting area and a comparison result display area, the parameter setting area displaying a dataset setting option, multiple model setting options, a prompt word input area, and a model comparison submission control; the dataset setting option is used to determine at least one first dataset for model comparison from at least one preset dataset; in response to a selection operation of at least one model setting option among the multiple model setting options, determining at least one first model for model comparison from multiple preset models, the at least one model setting option corresponding one-to-one with the at least one first model; in response to a prompt word input operation in the prompt word input area, displaying a first prompt word for model comparison corresponding to the prompt word input operation; in response to a triggering operation of the model comparison submission control, displaying at least one response area in the comparison result display area, the at least one response area corresponding one-to-one with the at least one first model, each response area displaying the corresponding first model's response to the first prompt word.

[0009] In some embodiments of this disclosure, each response area displays at least one of the following: a best response control, a create application control, and a debug information control; wherein, the best response control displayed in one response area is used to mark that the first model corresponding to the one response area has the best response to the first prompt word; the create application control displayed in one response area is used to create an application based on the first model corresponding to the one response area; and the debug information control displayed in one response area is used to indicate debug information for the first model corresponding to the one response area.

[0010] In some embodiments of this disclosure, the method further includes: in response to a triggering operation of a prompt word comparison control, displaying a prompt word comparison interface, the prompt word comparison interface including a parameter setting area and a comparison result display area, the parameter setting area displaying a dataset setting option, a model setting option, multiple prompt word input areas, and a prompt word comparison submission control; the dataset setting option is used to select at least one second dataset for prompt word comparison from at least one preset dataset; the model setting option is used to select a second model for prompt word comparison from multiple preset models; in response to a prompt word input operation in at least one of the multiple prompt word input areas, displaying at least one second prompt word corresponding to the prompt word input operation for prompt word comparison, the at least one second prompt word corresponding to the at least one prompt word input area; in response to a triggering operation of the prompt word comparison submission control, displaying at least one response area in the comparison result display area, the at least one response area corresponding to the at least one second prompt word, each response area displaying the response of the second model to the corresponding second prompt word.

[0011] In some embodiments of this disclosure, each response area displays at least one of the following: a best response control, a create application control, and a debug information control; wherein, the best response control displayed in one response area is used to mark that the response of the one response area to the corresponding second prompt word based on the second model is the best; the create application control displayed in one response area is used to create an application based on the second prompt word corresponding to the one response area; and the debug information control displayed in one response area is used to indicate debug information for the second prompt word corresponding to the one response area.

[0012] In some embodiments of this disclosure, the positional relationship between the parameter setting area and the comparison result display area is a vertical side-by-side display relationship, and the positional relationship between the at least one response area is a horizontal side-by-side display relationship.

[0013] In some embodiments of this disclosure, the display area required for the content of the response in the at least one response area is larger than the target response area of ​​the response area; the target response area displays a first progress bar that can be adjusted vertically, the first progress bar being used to adjust the response display progress of the target response area; and / or, the comparison result display area also displays a second progress bar that can be adjusted vertically, the second progress bar being used to synchronously adjust the response display progress of the at least one response area.

[0014] A second aspect of this disclosure provides an application creation apparatus, the apparatus comprising: a display module, configured to display a flow arrangement interface corresponding to a target application to be created in response to an attribute setting operation in an application creation interface, the flow arrangement interface displaying model nodes, dataset nodes and prompt word nodes, and the flow arrangement relationship between the model nodes, the dataset nodes and the prompt word nodes;

[0015] A module is created to respond to setting operations on the model node, the dataset node, and the prompt word node, respectively. Based on the target model corresponding to the model node, the target dataset corresponding to the dataset node, and the target prompt word corresponding to the prompt word node, the target application is created. The target application is used to answer user input questions through the target model after learning the target dataset and the target prompt word through the target model.

[0016] In some embodiments of this disclosure, the display module is further configured to display the application creation interface in response to a triggering operation on the application creation control before displaying the process orchestration interface corresponding to the target application to be created in response to the attribute setting operation on the application creation interface. The application creation interface is used to set the attribute information corresponding to the target application. The attribute information includes at least one of the following: application name, application description, and application type.

[0017] In some embodiments of this disclosure, when the first node is selected, the workflow arrangement interface also displays the setting information of the first node; the device further includes: a processing module, configured to, in response to a selection operation on the second node, switch the second node to a selected state and update the setting information of the first node displayed on the workflow arrangement interface to the setting information of the second node; or, the workflow arrangement interface also displays the setting information of the dataset node, the setting information of the model node, and the setting information of the prompt word node, and when the first node is selected, the setting information of the first node is displayed in a target area, the device further includes: a processing module, configured to, in response to a selection operation on the second node, switch the second node to a selected state and display the setting information of the second node in the target area; wherein the first node and the second node are different nodes among the model node, the dataset node, and the prompt word node.

[0018] In some embodiments of this disclosure, the display module is further configured to display a model comparison interface in response to a trigger operation of the model comparison control. The model comparison interface includes a parameter setting area and a comparison result display area. The parameter setting area displays a dataset setting option, multiple model setting options, a prompt word input area, and a model comparison submission control. The dataset setting option is used to determine at least one first dataset for model comparison from at least one preset dataset. In response to the selection operation of at least one model setting option from the multiple model setting options, at least one first model for model comparison is determined from the multiple preset models. The at least one model setting option corresponds one-to-one with the at least one first model. In response to the prompt word input operation in the prompt word input area, the first prompt word corresponding to the prompt word input operation for model comparison is displayed. In response to the trigger operation of the model comparison submission control, at least one response area is displayed in the comparison result display area. The at least one response area corresponds one-to-one with the at least one first model, and each response area displays the corresponding first model's response to the first prompt word.

[0019] In some embodiments of this disclosure, each response area displays at least one of the following: a best response control, a create application control, and a debug information control; wherein, the best response control displayed in one response area is used to mark that the first model corresponding to the one response area has the best response to the first prompt word; the create application control displayed in one response area is used to create an application based on the first model corresponding to the one response area; and the debug information control displayed in one response area is used to indicate debug information for the first model corresponding to the one response area.

[0020] In some embodiments of this disclosure, the display module is further configured to display a prompt word comparison interface in response to a trigger operation of the prompt word comparison control. The prompt word comparison interface includes a parameter setting area and a comparison result display area. The parameter setting area displays dataset setting options, model setting options, multiple prompt word input areas, and a prompt word comparison submission control. The dataset setting options are used to select at least one second dataset from at least one preset dataset for prompt word comparison. The model setting options are used to select a second model from multiple preset models for prompt word comparison. In response to prompt word input operations in at least one of the multiple prompt word input areas, at least one second prompt word corresponding to the prompt word input operation is displayed for prompt word comparison. Each of the at least one second prompt word corresponds one-to-one with the at least one prompt word input area. In response to a trigger operation of the prompt word comparison submission control, at least one response area is displayed in the comparison result display area. Each of the at least one response area corresponds one-to-one with the at least one second prompt word, and each response area displays the response of the second model to the corresponding second prompt word.

[0021] In some embodiments of this disclosure, each response area displays at least one of the following: a best response control, a create application control, and a debug information control; wherein, the best response control displayed in one response area is used to mark that the response of the one response area to the corresponding second prompt word based on the second model is the best; the create application control displayed in one response area is used to create an application based on the second prompt word corresponding to the one response area; and the debug information control displayed in one response area is used to indicate debug information for the second prompt word corresponding to the one response area.

[0022] In some embodiments of this disclosure, the positional relationship between the parameter setting area and the comparison result display area is a vertical side-by-side display relationship, and the positional relationship between the at least one response area is a horizontal side-by-side display relationship.

[0023] In some embodiments of this disclosure, the display area required for the content of the response in the at least one response area is larger than the target response area of ​​the response area; the target response area displays a first progress bar that can be adjusted vertically, the first progress bar being used to adjust the response display progress of the target response area; and / or, the comparison result display area also displays a second progress bar that can be adjusted vertically, the second progress bar being used to synchronously adjust the response display progress of the at least one response area.

[0024] A third aspect of this disclosure provides an electronic device including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the application creation method as described in the first aspect.

[0025] A fourth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the application creation method as described in the first aspect.

[0026] A fifth aspect of this disclosure provides a computer program product, wherein the computer program product includes a computer program that, when the computer program product is run on a processor, causes the processor to execute the computer program to implement the application creation method as described in the first aspect.

[0027] A sixth aspect of this disclosure provides a chip including a processor and a communication interface coupled to the processor, the processor being used to execute program instructions to implement the application creation method as described in the first aspect.

[0028] The technical solution provided in this disclosure has the following advantages compared with the prior art: In response to the attribute setting operation in the application creation interface, a process orchestration interface corresponding to the target application to be created is displayed. This process orchestration interface displays model nodes, dataset nodes, and prompt word nodes, as well as the process orchestration relationship between the model nodes, dataset nodes, and prompt word nodes. In response to the setting operations of the model nodes, dataset nodes, and prompt word nodes respectively, the target application is created based on the target model corresponding to the model node, the target dataset corresponding to the dataset node, and the target prompt word corresponding to the prompt word node. This target application is used to answer user input questions through the target model after learning the target dataset and the target prompt word. This solution provides a method for creating applications, which can be operated and maintained without relying on manual operation and maintenance. It is timely, less prone to errors, and improves the efficiency of operation and maintenance. Attached Figure Description

[0029] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0030] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 A flowchart illustrating an application creation method provided in this embodiment of the disclosure;

[0032] Figure 2 One of the interface diagrams for the application creation method provided in this embodiment of the disclosure;

[0033] Figure 3(a) is a second schematic diagram of the interface of the application creation method provided in the embodiments of this disclosure;

[0034] Figure 3(b) is a third schematic diagram of the interface of the application creation method provided in the embodiments of this disclosure;

[0035] Figure 4(a) is a fourth schematic diagram of the interface of the application creation method provided in the embodiments of this disclosure;

[0036] Figure 4(b) is the fifth schematic diagram of the interface of the application creation method provided in the embodiments of this disclosure;

[0037] Figure 4(c) is a sixth schematic diagram of the interface of the application creation method provided in the embodiments of this disclosure;

[0038] Figure 5 Seventh schematic diagram of the interface for the application creation method provided in this embodiment of the disclosure;

[0039] Figure 6 A structural block diagram of an application creation apparatus provided in an embodiment of this disclosure;

[0040] Figure 7 This is a structural block diagram of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0041] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0042] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0043] The terms "first," "second," etc., used in this disclosure and in the claims are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this disclosure can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0044] The execution subject of the application creation method provided in this disclosure can be an electronic device or a server, or it can be a functional module and / or functional entity in the electronic device or server that can implement the application creation method. The specific implementation subject can be determined according to actual usage requirements, and this disclosure does not limit it.

[0045] The application creation method provided by the present disclosure will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0046] like Figure 1 As shown in the embodiments of this disclosure, an application creation method is provided, which may include the following steps 101 to 102.

[0047] 101. In response to the property setting operation in the application creation interface, display the process orchestration interface corresponding to the target application to be created.

[0048] In this embodiment of the disclosure, the application is an AI application created based on an artificial intelligence (AI) model.

[0049] The workflow orchestration interface displays model nodes, dataset nodes, and prompt word nodes, as well as the workflow orchestration relationships between these nodes.

[0050] The application creation interface is used to set the attribute information of the target application, which includes at least one of the following: application name, application description, and application type.

[0051] The application name can be used to represent the target application. The application name can be a user-defined name based on their own needs, or it can be a default name; there is no restriction here.

[0052] The "Application Introduction" section can be used to introduce the target application's functions, usage scenarios, or other relevant information; there are no restrictions here.

[0053] The application types include text generation or dialogue types, and may also include other types, which are not limited here.

[0054] In some embodiments of this disclosure, the attribute information may further include the privacy type of the target application, wherein the privacy type includes a private type and a public type. The private type is visible only to the user who created the target application, while the public type is visible to any user.

[0055] In some embodiments of this disclosure, the attribute information may also include the identifier of the creator of the target application, and the attribute information may also include other information, which may be determined according to the actual situation and is not limited here.

[0056] Among them, the model node is associated with the model settings of the target application, the dataset node is associated with the dataset settings of the target application, and the prompt word node is associated with the prompt words of the target application. The specific settings can be determined according to the actual situation and are not limited here.

[0057] The process arrangement relationship is used to indicate the process relationship, logical relationship, etc. between the model node, the dataset node and the prompt word node. The specific relationship can be determined according to the actual situation and is not limited here.

[0058] 102. In response to the setting operations of the model node, the dataset node and the prompt word node respectively, create the target application based on the target model corresponding to the model node, the target dataset corresponding to the dataset node and the target prompt word corresponding to the prompt word node.

[0059] Specifically, this target application is used to respond to user-input questions by learning from the target dataset and the target prompt words through the target model.

[0060] The target dataset may include one or more datasets, which can be determined according to the actual situation and are not limited here.

[0061] This solution provides an application creation method that allows for operation and maintenance without relying on manual processes. This approach ensures timely processing, reduces the likelihood of errors, and improves the efficiency of operation and maintenance.

[0062] In this embodiment of the disclosure, a platform for creating applications can be provided, on which the required target applications can be created, and then the created target applications can be run and maintained.

[0063] In some embodiments of this disclosure, the navigation bar of the application creation platform includes, but is not limited to, at least one of the following: "Create Application" tab, "Application Market" tab, "Application Management" tab, "Training Ground" tab, and "Dataset" tab. Specifically, the "Create Application" tab indicates the application creation page; the "Application Market" tab indicates the application market page, which displays created applications; the "Application Management" tab indicates the application management page, which manages user-created applications and / or other user-created applications saved (or favorited); the "Training Ground" tab indicates the training ground page, which displays a model comparison interface and / or a prompt word comparison interface, wherein the model comparison page compares the responses of applications created based on different models to the same prompt word, and the prompt word comparison page compares the responses of applications created based on the same model to different prompt words; and the "Dataset" tab indicates the dataset page, which manages datasets.

[0064] In some embodiments of this disclosure, the application marketplace page may include at least one application identifier, each application identifier indicating a created application. The created application indicated by each application identifier includes applications created and published to the application marketplace page by the user, and / or applications created and published to the application marketplace page by other users. Each application identifier may include attribute information of the corresponding created application; specific attribute information can be found in the above description of attribute information and is not limited here.

[0065] In some embodiments of this disclosure, by opening any application identifier, the application interface of the created application indicated by the application identifier can be displayed, and then by triggering an operation on the application interface of the created application, the created application can be controlled to perform related processing.

[0066] In some embodiments of this disclosure, after displaying the application interface of an already created application indicated by any application identifier, the user can enter the process orchestration interface by triggering the "application adjustment control" on the application interface. Then, by adjusting the settings of at least one of the model node, dataset node, and prompt word node, a new application is generated based on the adjusted model node, dataset node, and prompt word node. In this way, an application that meets the user's needs can be quickly created based on an already created application indicated by any application identifier on the application market page.

[0067] In some embodiments of this disclosure, each application identifier may include a favorites control. By performing a favorites operation on the favorites control in any application identifier, the created application indicated by that application identifier can be added to the favorites interface (which may be an application management page).

[0068] In some embodiments of this disclosure, the application market page may also include a search control, which allows users to search for applications they need from at least one created application indicated by an application identifier by operating the search control.

[0069] In some embodiments of this disclosure, user-created private applications are typically saved to the application management page, while user-created public applications are typically published to the application marketplace page.

[0070] In some embodiments of this disclosure, prior to step 101 described above, the application creation method provided in this disclosure may further include step 103 as described below.

[0071] 103. In response to the triggering operation of the application creation control, display the application creation interface.

[0072] The application creation interface is used to set the attribute information corresponding to the target application. The attribute information includes at least one of the following: application name, application description, and application type.

[0073] In some embodiments of this disclosure, if the navigation bar of the application creation platform includes a "Create Application" tab, the application creation control can be located on the page corresponding to the "Create Application" tab; if the navigation bar of the application creation platform includes an "Application Market" tab, the application creation control can be located on the page corresponding to the "Application Market" tab; if the navigation bar of the application creation platform includes a "Training Ground" tab, the application creation control can be located on the page corresponding to the "Training Ground" tab; the application creation control can also be located on the page corresponding to other tabs, which can be determined according to the actual situation and is not limited here.

[0074] It can be understood that the attribute setting operation in step 101 above is the operation of setting the attribute information of the target application in the application creation interface.

[0075] In this embodiment of the disclosure, the application creation interface is displayed by triggering the application creation control. Then, the attribute information of the target application can be determined by setting the attribute information of the target application in the application creation interface. Based on the attribute information of the target application, the target application can be distinguished from other applications.

[0076] In some embodiments of this disclosure, in addition to displaying model nodes, dataset nodes, and prompt word nodes, as well as the process arrangement relationship, the process arrangement interface can also display the setting information of one or more of the model nodes, dataset nodes, and prompt word nodes. The specific settings can be determined according to the actual situation and are not limited here.

[0077] The settings for the dataset node are used to set the dataset corresponding to the dataset node, the settings for the model node are used to set the model corresponding to the model node, and the settings for the prompt word node are used to set the prompt word corresponding to the prompt word node.

[0078] In some embodiments of this disclosure, when the first node is selected, the process orchestration interface also displays the setting information of the first node; after step 101 above, the application creation method provided in the embodiments of this disclosure may further include the following step 104.

[0079] 104. In response to the selection operation of the second node, switch the second node to the selected state and update the setting information of the first node displayed in the process orchestration interface to the setting information of the second node.

[0080] The first node and the second node are different nodes in the model node, the dataset node, and the prompt word node, respectively.

[0081] It's understandable that the workflow orchestration interface only displays the settings information of the selected node at a time. For example, when the selected node is the first node, the interface displays its settings. When the selected node changes from the first to the second node, the interface updates the displayed settings to reflect the second node's information. In other words, when the selected node becomes the second node, the interface stops displaying the first node's settings and displays the second node's. This way, by only displaying the settings information of the selected node at a time, the user can easily distinguish which node's settings are being displayed, improving the user experience.

[0082] In some embodiments of this disclosure, the process orchestration interface also displays the setting information of the dataset node, the setting information of the model node, and the setting information of the prompt word node. When the first node is selected, the setting information of the first node is displayed in the target area. After step 101 above, the application creation method provided by the embodiments of this disclosure may also include the following step 105.

[0083] 105. In response to the selection operation of the second node, switch the second node to the selected state and display the setting information of the second node in the target area.

[0084] The first node and the second node are different nodes in the model node, the dataset node, and the prompt word node, respectively.

[0085] In some embodiments of this disclosure, the setting information of a selected node can be positioned and displayed in a target area in a preset manner. The preset manner can include bold display, preset color display, highlight display, or box selection display (enclosing the setting information of the selected node within a box), etc., and the specific method can be determined according to the actual situation, and is not limited here.

[0086] In some embodiments of this disclosure, the target area can be the central area in the process orchestration interface used to display the setting information of nodes. In this case, the setting information of the first node is displayed in the target area, specifically, the central area of ​​the setting information of the first node is displayed in the target area; the setting information of the second node is displayed in the target area, specifically, the central area of ​​the setting information of the second node is displayed in the target area.

[0087] In some embodiments of this disclosure, the target area can be the starting position of the setting information of a node in the selected state in the process orchestration interface. In this case, the setting information of the first node is displayed in the target area, specifically, the starting position of the setting information of the first node is displayed in the target area; the setting information of the second node is displayed in the target area, specifically, the starting position of the setting information of the second node is displayed in the target area.

[0088] It's understandable that the workflow orchestration interface can display the settings information for each node, but the settings information for selected nodes is displayed in a specific target area. For example, when the selected node is the first node, its settings information is displayed in the target area of ​​the workflow orchestration interface. When the selected node changes from the first node to the second node, the settings information displayed in the target area of ​​the workflow orchestration interface is updated to reflect the second node's settings. In other words, when the selected node becomes the second node, its settings information is displayed in the target area of ​​the workflow orchestration interface. This allows the workflow orchestration interface to display the settings information for each node, enabling users to view these settings as needed. Furthermore, displaying the settings information for selected nodes in the target area helps users distinguish between the settings of different nodes, improving the user experience.

[0089] In some embodiments of this disclosure, the application creation method provided in this disclosure may further include the following steps 106 to 109.

[0090] 106. In response to the trigger operation of the model comparison control, display the model comparison interface.

[0091] The model comparison interface includes a parameter setting area and a comparison result display area. The parameter setting area displays dataset setting options, multiple model setting options, a prompt input area, and a model comparison submission control. The dataset setting options are used to determine at least one first dataset from at least one preset dataset for model comparison.

[0092] The model comparison interface is used to display the response results for the same prompt words based on the same dataset and different models.

[0093] Among them, at least one preset dataset can be a target dataset or a public dataset, which can be determined according to the actual situation and is not limited here.

[0094] Multiple model setting options are available. For example, three model setting options can be displayed by default. Users can also display more model setting options by adding controls to the options according to their own needs. A horizontal progress bar can also be added to the comparison result display area to display more response areas. The specifics can be determined according to the actual situation and are not limited here.

[0095] In some embodiments of this disclosure, the model comparison interface may also display application type setting options, and may also include other options, which can be determined according to the actual situation and are not limited here.

[0096] In some embodiments of this disclosure, the model comparison submission control can be displayed at any location in the model comparison interface, and there is no limitation here.

[0097] 107. In response to a selection operation of at least one of the plurality of model setting options, determine at least one first model from the plurality of preset models for model comparison.

[0098] Each of the at least one model setting options corresponds one-to-one with the at least one first model.

[0099] It is understandable that a model setting option is used to set a model. Users can select at least one model setting option from multiple model setting options according to their needs, and then set at least one first model through the at least one model setting option for model comparison.

[0100] In this embodiment of the disclosure, one or more models can be selected for model comparison, which makes the operation more flexible and can improve the user experience.

[0101] 108. In response to the input operation of the prompt word in the prompt word input area, display the first prompt word corresponding to the prompt word input operation for model comparison.

[0102] For example, the first prompt could be "You are a designer, please summarize how to use a pop-up component."; the first prompt could also be "You are a code engineer, please describe the process of writing code in English."; the first prompt could also be "How do you write code?"; or other content, which can be determined according to the actual situation, and is not limited here.

[0103] 109. In response to the triggering operation of the model comparison submission control, display at least one response area in the comparison result display area.

[0104] The at least one response area corresponds one-to-one with the at least one first model, and each response area displays the corresponding first model's response to the first prompt word.

[0105] It is understood that in this embodiment of the present disclosure, before the user triggers the model comparison submission control, the comparison result display area displays multiple response areas by default, and these response areas correspond one-to-one with multiple model setting options. After the user triggers the model comparison submission control, the comparison result display area displays at least one response area corresponding to at least one first model. Thus, the number of response areas displayed in the comparison result display area dynamically varies with the number of models selected by the user. On the one hand, it allows for the simultaneous display of response areas corresponding to each model (and consequently, the simultaneous display of responses from each model to the first prompt word). On the other hand, by eliminating invalid response areas (response areas without a corresponding first model), a larger area can be used to display each response area, improving the comparison effect and better displaying the response area corresponding to each model.

[0106] In this embodiment, instead of creating applications based on different models, determining the appropriate model based on the application's responses, and then creating the target application, the method compares the models to determine the accuracy of responses from different models for the same dataset and the same prompt word (first prompt word). The model corresponding to the most accurate response is then selected as the target model, and the target application is created based on this target model. This simplifies the model selection process, improves the efficiency of model selection, and enhances the efficiency of application creation.

[0107] In some embodiments of this disclosure, each response area displays at least one of the following: a best response control, a create application control, and a debug information control; wherein, the best response control displayed in one response area is used to mark that the first model corresponding to the one response area has the best response to the first prompt word; the create application control displayed in one response area is used to create an application based on the first model corresponding to the one response area; and the debug information control displayed in one response area is used to indicate debug information for the first model corresponding to the one response area.

[0108] In this embodiment, each response area displays a best response control. Users can select the best response control from at least one response area that best meets their requirements, based on their actual needs. The best response control is then displayed with a preset marker indicating that the response in the response area corresponding to that best response control is the most suitable. This facilitates users reviewing the model comparison interface to determine which first model's response is best, i.e., which first model performs better for the first prompt word. Furthermore, it allows the backend to statistically analyze which first model performs better for the first prompt word, prioritizing that first model for future prompt words similar to the first prompt word.

[0109] The preset marking format can be displayed with bold text, a preset background color, or a highlighted display, etc., which can be determined according to the actual situation.

[0110] In this embodiment of the disclosure, each response area displays an application creation control. The user can select the application creation control corresponding to the response area that best meets the user's requirements from at least one response area according to the actual situation, thereby creating an application based on the first model corresponding to that response area, which can improve the efficiency of application creation.

[0111] In some embodiments of this disclosure, the above-mentioned process orchestration interface is entered by triggering the creation application control of a response area, and the model corresponding to the model node of the current process orchestration interface is the first model corresponding to the response area, that is, the application to be created by default selects the first model corresponding to the response area.

[0112] In this embodiment of the disclosure, each response area displays a debugging information control. The user can select the debugging information control corresponding to the response area whose response does not yet meet the user's requirements from at least one response area according to the actual situation, and debug the corresponding first model so that the first model's response to the first prompt word can meet the user's requirements after debugging.

[0113] In some embodiments of this disclosure, by triggering the debugging information control of a response area, the relevant debugging interface of the first model corresponding to the response area is displayed, so as to debug the first model based on the relevant debugging interface.

[0114] It should be noted that steps 106 to 109 can be performed before step 101, after step 101 and before step 102, or after step 102. The specific execution time can be determined based on the actual situation, and no restrictions are imposed here.

[0115] In this embodiment of the disclosure, model comparison can quickly determine which model better meets the user's needs for the application to be created, thereby improving model creation efficiency.

[0116] In some embodiments of this disclosure, the model comparison control can be displayed on the training field page; it can also be displayed on the workflow arrangement interface; or it can be displayed on other interfaces. The specific display can be determined according to the actual situation, and no limitation is made here.

[0117] In some embodiments of this disclosure, the application creation method provided in the embodiments of this disclosure may further include the following steps 110 to 112.

[0118] 110. In response to the trigger operation of the prompt word comparison control, display the prompt word comparison interface.

[0119] The prompt word comparison interface includes a parameter setting area and a comparison result display area. The parameter setting area displays dataset setting options, model setting options, multiple prompt word input areas, and prompt word comparison submission controls. The dataset setting options are used to select at least one second dataset from at least one preset dataset for prompt word comparison. The model setting options are used to select a second model from multiple preset models for prompt word comparison.

[0120] The prompt comparison interface is used to display the response results for different prompts based on the same dataset and the same model.

[0121] Among them, at least one preset dataset can be a target dataset or a public dataset, which can be determined according to the actual situation and is not limited here.

[0122] In some embodiments of this disclosure, the prompt word comparison submission control can be displayed at any position in the prompt word comparison interface, and there is no limitation here.

[0123] 111. In response to a prompt word input operation in at least one of the plurality of prompt word input areas, display at least one second prompt word corresponding to the prompt word input operation for prompt word comparison.

[0124] The at least one second prompt word corresponds one-to-one with the at least one prompt word input area.

[0125] It is understood that a prompt input area can be used to input one prompt. Users can select at least one prompt input area from multiple prompt input areas as needed, and then input the corresponding second prompt in each of the at least one prompt input area to obtain at least one second prompt.

[0126] Multiple prompt input areas are available. For example, three prompt input areas can be displayed by default. Users can also display more prompt input areas by adding controls to the prompt input areas according to their own needs. A horizontal progress bar can also be added to the comparison result display area to display more prompt input areas. The specifics can be determined according to the actual situation and are not limited here.

[0127] The description of the second prompt word can be found in the above description of the first prompt word, and will not be repeated here.

[0128] 112. In response to the triggering operation of the comparison submission control for the prompt word, display at least one response area in the comparison result display area.

[0129] In this context, each of the at least one response area corresponds one-to-one with the at least one second prompt word, and each response area displays the response of the second model to the corresponding second prompt word.

[0130] It is understood that in this embodiment of the present disclosure, before the user triggers the prompt word comparison submission control, the comparison result display area displays multiple response areas by default, with each response area corresponding one-to-one with a prompt word input area. After the user triggers the prompt word comparison submission control, the comparison result display area displays at least one response area corresponding to at least one second prompt word. Thus, the number of response areas displayed in the comparison result display area dynamically varies with the number of prompt word input areas, allowing for the simultaneous display of response areas corresponding to each second prompt word (and consequently, the simultaneous display of the second model's responses to each second prompt word). Furthermore, by eliminating invalid response areas (response areas without corresponding second prompt words), a larger area can be used to display each response area, improving the comparison effect and better displaying the response area corresponding to each model.

[0131] In this embodiment of the disclosure, before creating an application, the type of prompt word can be quickly determined by comparison, which can make the created application perform better. By selecting this type of prompt word to create the application, the efficiency of prompt word selection can be improved, and the efficiency of application creation can be improved.

[0132] In some embodiments of this disclosure, each response area displays at least one of the following: a best response control, a create application control, and a debug information control; wherein, the best response control displayed in one response area is used to mark that the response of the one response area to the corresponding second prompt word based on the second model is the best; the create application control displayed in one response area is used to create an application based on the second prompt word corresponding to the one response area; and the debug information control displayed in one response area is used to indicate debug information for the second prompt word corresponding to the one response area.

[0133] In this embodiment, each response area displays a best response control. Users can select the best response control from at least one response area that best meets their requirements, based on their actual needs. The best response control is then displayed with a preset marker indicating that the response in the response area corresponding to that best response control is the most suitable. This facilitates the user's ability to determine which second prompt word's response is best when reviewing the prompt comparison interface again, i.e., which second prompt word the second model performs better for. Furthermore, it allows the backend to statistically analyze which second prompt word the second model performs best for, prioritizing the recommendation of second prompt words for future use.

[0134] The preset marking format can be displayed with bold text, a preset background color, or a highlighted display, etc., which can be determined according to the actual situation.

[0135] In this embodiment of the disclosure, each response area displays an application creation control. The user can select the application creation control corresponding to the response area that best meets the user's requirements from at least one response area according to the actual situation, thereby creating an application based on the second prompt word corresponding to that response area, which can improve the efficiency of application creation.

[0136] In some embodiments of this disclosure, the above-mentioned process orchestration interface is entered by triggering the creation application control of a response area, and the prompt word node of the current process orchestration interface corresponds to the second prompt word corresponding to the response area, that is, by default, the application to be created selects the second prompt word corresponding to the response area.

[0137] In this embodiment of the disclosure, each response area displays a debugging information control. The user can select the debugging information control corresponding to the response area that does not yet meet the user's requirements from at least one response area according to the actual situation, and debug the corresponding second prompt word so that the second model's response to the debugged second prompt word can meet the user's requirements.

[0138] In some embodiments of this disclosure, by triggering a debugging information control of a response area, a related debugging interface for the second prompt word corresponding to that response area is displayed, so as to debug the second prompt word based on the related debugging interface.

[0139] In some embodiments of this application, both the debugging interface for the first model and the debugging interface for the second prompt word are divided into five modules: original question, question rewriting, knowledge retrieval, prompt word generation, and model output. The specific content of these five modules is automatically generated by the system to display relevant debugging information to the user. Knowledge retrieval retrieves the corresponding response based on the currently selected model and prompt word, compares this response with other preset responses, and determines a similarity value. The higher the similarity value, the better the matching degree of the knowledge. The knowledge retrieval module typically displays the question and answer, as well as the similarity value. The knowledge retrieval module also includes an "expand control" and a "manage control." The "expand control" is used to view detailed information about the knowledge retrieval module; the "manage control" is used to manage model nodes and / or dataset nodes. Knowledge retrieval is closely related to the model and dataset. If there are problems with the information displayed in the knowledge retrieval module of the debugging interface, the "manage control" can be triggered to analyze whether the problem lies with the model itself or the dataset. If the problem lies with the model itself, then manage the model; if the problem lies with the dataset, then manage the dataset.

[0140] It should be noted that steps 110 to 112 can be performed before step 101, after step 101 and before step 102, or after step 102. The specific execution time can be determined based on the actual situation, and no restrictions are imposed here.

[0141] In this embodiment of the disclosure, by comparing prompt words, it is possible to quickly determine which prompt word is more in line with the user's needs for the application to be created, thereby improving the efficiency of model creation.

[0142] In some embodiments of this disclosure, the prompt word comparison control can be displayed on the training field page; it can also be displayed on the process arrangement interface; or it can be displayed on other interfaces. The specific display can be determined according to the actual situation, and no limitation is made here.

[0143] In some embodiments of this disclosure, the positional relationship between the parameter setting area and the comparison result display area is a vertical side-by-side display relationship, and the positional relationship between the at least one response area is a horizontal side-by-side display relationship.

[0144] It is understandable that, for the model comparison interface, the parameter setting area and the comparison result display area are displayed side-by-side vertically, while the at least one response area is displayed side-by-side horizontally. This effectively distinguishes the parameter setting area and the comparison result display area within the model comparison interface, and facilitates horizontal comparison of responses corresponding to different first models. It also allows users to easily compare and view the model comparison results, determine the response that meets their needs, and ultimately identify the first model that best suits their requirements.

[0145] It is understandable that, for the prompt comparison interface, the parameter setting area and the comparison result display area are displayed side-by-side vertically, while the at least one response area is displayed side-by-side horizontally. This effectively distinguishes the parameter setting area and the comparison result display area within the prompt comparison interface, and facilitates horizontal comparison of responses corresponding to different second prompts. It also allows users to easily compare and view the prompt comparison results, determine the response that meets their needs, and ultimately identify the second prompt that satisfies their requirements.

[0146] In some embodiments of this disclosure, the display area required for the content of the response in the at least one response area is larger than the target response area of ​​the response area; the target response area displays a first progress bar that can be adjusted vertically, and the first progress bar is used to adjust the response display progress of the target response area.

[0147] It is understandable that the target response area cannot display the full content of the corresponding response at the same time, but only a part of the corresponding response. In this case, a first progress bar is set in the target response area (the first progress bar can only adjust the response display progress of the target response area), so that the user can view the full content of the corresponding response by adjusting the first progress bar.

[0148] In some embodiments of this disclosure, when the response area can display all the content of the corresponding response at the same time, the vertical adjustment progress bar may not be displayed.

[0149] In some embodiments of this disclosure, the display area required for the content of the response in the at least one response area is larger than the target response area of ​​the response area; the comparison result display area also displays a vertically adjustable second progress bar, which is used to synchronously adjust the response display progress of the at least one response area.

[0150] It is understandable that the target response area cannot display the full content of the corresponding response at the same time, but can only display a portion of the corresponding response. In this case, a second progress bar is set in the comparison result display area (the second progress bar is used to synchronously adjust the response display progress of the at least one response area), so that users can view the full content of the corresponding response by adjusting the second progress bar.

[0151] In some embodiments of this disclosure, the first progress bar and the second progress bar described above can be displayed simultaneously. That is, the user can choose to adjust the response display progress of the target response area through the first progress bar, or can choose to adjust the response display progress of the at least one response area synchronously through the second progress bar.

[0152] For example, such as Figure 2 The diagram illustrates an optional application creation platform, where the navigation bar includes "Create Application" tab, "Application Marketplace" tab, "Training Ground" tab, and "Dataset" tab. Currently, the "Create Application" tab is selected. The application creation page displays a workflow orchestration interface, which shows dataset nodes, model nodes, and prompt word nodes. Since the model node is currently selected, the workflow orchestration interface also displays its settings information.

[0153] For example, following the above Figure 2 As shown in Figure 3(a), this is a schematic diagram of an optional application market page. The application market page includes a "search control" and two interfaces: one is the interface corresponding to "all tags" and the other is the interface corresponding to "my favorite tags". Each interface includes at least one application identifier. The interface corresponding to "all tags" is currently displayed. The mark "31" indicates an application identifier. Each application identifier includes the application's attribute information and a "favorites control".

[0154] For example, following Figure 3(a) above, as shown in Figure 3(b), to display the application interface corresponding to application 1 by triggering an operation on the application identifier corresponding to application 1 on the application market page, the application interface includes an "application adjustment control". By triggering the "application adjustment control", the following can be displayed: Figure 2 The flowchart interface shown.

[0155] For example, following the above Figure 2As shown in Figure 4(a), this is a schematic diagram of an optional model comparison interface. The "Training Ground" tab of the application creation platform is selected. On the Training Ground page, mark "41" refers to the model comparison control, and mark "42" refers to the prompt word comparison control. Currently, the model comparison control is selected, and the model comparison interface is displayed on the Training Ground page. The model comparison interface includes the parameter setting area (marked "43") and the comparison result display area (marked "44"). The parameter setting area includes one dataset setting option, three model setting options, one prompt word input area, and a model comparison submission control; the comparison result display area includes three response areas.

[0156] For example, following Figure 4(a), when the dataset setting option is set to dataset 1, two model setting options are selected from the three model setting options and set to model 1 and model 2 respectively. Prompt word 1 is entered in the prompt word input area. After clicking the model comparison submission control, the model comparison interface shown in Figure 4(b) is displayed. The comparison result display area includes two response areas. The two response areas respectively display the response of the first model to the first prompt word. Specifically, response 1 and response 2 are displayed respectively. The corresponding "best response control", "debugging information control" and "create application control" are displayed in these two response areas respectively.

[0157] For example, following Figure 4(a), Figure 4(c) shows a schematic diagram of an optional prompt word comparison interface. The prompt word comparison control is currently selected, and the prompt word comparison interface is displayed on the training page. Mark "45" indicates the parameter setting area, and mark "46" indicates the comparison result display area. The parameter setting area includes a dataset setting option, a model setting option, three prompt word input areas, and a prompt word comparison submission control. The comparison result display area includes three response areas.

[0158] For example, such as Figure 5 As shown, in response to the triggering operation of the "Debug Information Control" in Figure 4(b), the debug information interface is displayed. The debug information interface includes five modules: original problem, problem rewriting, knowledge retrieval, prompt word generation, and model output. Among them, the knowledge retrieval module also displays "expand control" and "go to manage control".

[0159] Figure 6 This is a structural block diagram of an application creation apparatus shown in an embodiment of the present disclosure, such as... Figure 6As shown, it includes: a display module 601, used to display the process orchestration interface corresponding to the target application to be created in response to the attribute setting operation in the application creation interface. The process orchestration interface displays model nodes, dataset nodes, and prompt word nodes, as well as the process orchestration relationship between the model node, the dataset node, and the prompt word node; and a creation module 602, used to create the target application based on the target model corresponding to the model node, the target dataset corresponding to the dataset node, and the target prompt word corresponding to the prompt word node in response to the setting operations of the model node, the dataset node, and the prompt word node respectively. The target application is used to answer the user's input questions through the target model after learning the target dataset and the target prompt word through the target model.

[0160] In some embodiments of this disclosure, the display module 601 is further configured to display the application creation interface in response to a triggering operation of the application creation control before displaying the process orchestration interface corresponding to the target application to be created in response to the attribute setting operation of the application creation interface. The application creation interface is used to set the attribute information corresponding to the target application. The attribute information includes at least one of the following: application name, application description, and application type.

[0161] In some embodiments of this disclosure, when the first node is selected, the workflow arrangement interface also displays the setting information of the first node; the device further includes: a processing module, configured to, in response to a selection operation on the second node, switch the second node to a selected state and update the setting information of the first node displayed on the workflow arrangement interface to the setting information of the second node; or, the workflow arrangement interface also displays the setting information of the dataset node, the setting information of the model node, and the setting information of the prompt word node, and when the first node is selected, the setting information of the first node is displayed in a target area, the device further includes: a processing module, configured to, in response to a selection operation on the second node, switch the second node to a selected state and display the setting information of the second node in the target area; wherein the first node and the second node are different nodes among the model node, the dataset node, and the prompt word node.

[0162] In some embodiments of this disclosure, the display module 601 is further configured to display a model comparison interface in response to a trigger operation of the model comparison control. The model comparison interface includes a parameter setting area and a comparison result display area. The parameter setting area displays a dataset setting option, multiple model setting options, a prompt word input area, and a model comparison submission control. The dataset setting option is used to determine at least one first dataset for model comparison from at least one preset dataset. In response to the selection operation of at least one model setting option from the multiple model setting options, at least one first model for model comparison is determined from the multiple preset models. The at least one model setting option corresponds one-to-one with the at least one first model. In response to the prompt word input operation of the prompt word input area, the first prompt word corresponding to the prompt word input operation for model comparison is displayed. In response to the trigger operation of the model comparison submission control, at least one response area is displayed in the comparison result display area. The at least one response area corresponds one-to-one with the at least one first model, and each response area displays the response of the corresponding first model to the first prompt word.

[0163] In some embodiments of this disclosure, each response area displays at least one of the following: a best response control, a create application control, and a debug information control; wherein, the best response control displayed in one response area is used to mark that the first model corresponding to the one response area has the best response to the first prompt word; the create application control displayed in one response area is used to create an application based on the first model corresponding to the one response area; and the debug information control displayed in one response area is used to indicate debug information for the first model corresponding to the one response area.

[0164] In some embodiments of this disclosure, the display module 601 is further configured to display a prompt word comparison interface in response to a trigger operation of the prompt word comparison control. The prompt word comparison interface includes a parameter setting area and a comparison result display area. The parameter setting area displays a dataset setting option, a model setting option, multiple prompt word input areas, and a prompt word comparison submission control. The dataset setting option is used to select at least one second dataset for prompt word comparison from at least one preset dataset. The model setting option is used to select a second model for prompt word comparison from multiple preset models. In response to a prompt word input operation in at least one of the multiple prompt word input areas, at least one second prompt word corresponding to the prompt word input operation is displayed for prompt word comparison. The at least one second prompt word corresponds one-to-one with the at least one prompt word input area. In response to a trigger operation of the prompt word comparison submission control, at least one response area is displayed in the comparison result display area. The at least one response area corresponds one-to-one with the at least one second prompt word, and each response area displays the response of the second model to the corresponding second prompt word.

[0165] In some embodiments of this disclosure, each response area displays at least one of the following: a best response control, a create application control, and a debug information control; wherein, the best response control displayed in one response area is used to mark that the response of the one response area to the corresponding second prompt word based on the second model is the best; the create application control displayed in one response area is used to create an application based on the second prompt word corresponding to the one response area; and the debug information control displayed in one response area is used to indicate debug information for the second prompt word corresponding to the one response area.

[0166] In some embodiments of this disclosure, the positional relationship between the parameter setting area and the comparison result display area is a vertical side-by-side display relationship, and the positional relationship between the at least one response area is a horizontal side-by-side display relationship.

[0167] In some embodiments of this disclosure, the display area required for the content of the response in the at least one response area is larger than the target response area of ​​the response area; the target response area displays a first progress bar that can be adjusted vertically, the first progress bar being used to adjust the response display progress of the target response area; and / or, the comparison result display area also displays a second progress bar that can be adjusted vertically, the second progress bar being used to synchronously adjust the response display progress of the at least one response area.

[0168] In this embodiment, each module can implement the application creation method provided in the above method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0169] Figure 7This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. It is used to illustrate the electronic device that implements any application creation method in the embodiments of the present disclosure and should not be construed as a specific limitation on the embodiments of the present disclosure.

[0170] like Figure 7 As shown, the electronic device 700 may include a processor (e.g., a central processing unit, a graphics processor, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device 700. The processor 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0171] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic device 700 to communicate wirelessly or wiredly with other devices to exchange data. Although an electronic device 700 with various devices is shown, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0172] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 709, or installed from storage device 708, or installed from ROM 702. When the computer program is executed by processor 701, it can perform the functions defined in any application creation method provided in embodiments of this disclosure.

[0173] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0174] In some implementations, the client and server can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0175] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0176] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: in response to an attribute setting operation in an application creation interface, display a flow orchestration interface corresponding to the target application to be created, the flow orchestration interface displaying model nodes, dataset nodes, and prompt word nodes, as well as the flow orchestration relationship between the model nodes, dataset nodes, and prompt word nodes; and in response to setting operations on the model nodes, dataset nodes, and prompt word nodes respectively, create the target application based on the target model corresponding to the model node, the target dataset corresponding to the dataset node, and the target prompt word corresponding to the prompt word node, the target application being used to answer user input questions through the target model after learning the target dataset and the target prompt word through the target model.

[0177] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on a computer, partially on a computer, as a standalone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0178] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0179] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0180] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0181] In the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of computer-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0182] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0183] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0184] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. An application creation method, characterized in that, The method includes: In response to the attribute setting operation in the application creation interface, the process orchestration interface corresponding to the target application to be created is displayed. The process orchestration interface displays model nodes, dataset nodes and prompt word nodes, as well as the process orchestration relationship between the model nodes, the dataset nodes and the prompt word nodes. In response to the setting operations on the model node, the dataset node, and the prompt word node respectively, the target application is created based on the target model corresponding to the model node, the target dataset corresponding to the dataset node, and the target prompt word corresponding to the prompt word node. The target application is used to answer the user's input question through the target model after learning the target dataset and the target prompt word through the target model. In response to a trigger operation on the model comparison control, a model comparison interface is displayed. The model comparison interface includes a parameter setting area and a comparison result display area. The parameter setting area displays dataset setting options, multiple model setting options, a prompt input area, and a model comparison submission control. The dataset setting options are used to determine at least one first dataset for model comparison from at least one preset dataset. In response to the selection operation of at least one of the plurality of model setting options, at least one first model for model comparison is determined from a plurality of preset models, wherein the at least one model setting option corresponds one-to-one with the at least one first model. In response to a prompt word input operation in the prompt word input area, the first prompt word corresponding to the prompt word input operation for model comparison is displayed; In response to the triggering operation of the model comparison submission control, at least one response area is displayed in the comparison result display area. The at least one response area corresponds one-to-one with the at least one first model, and each response area displays the corresponding first model's response to the first prompt word.

2. The method according to claim 1, characterized in that, Before displaying the workflow orchestration interface corresponding to the target application to be created in response to the property setting operation in the application creation interface, the method further includes: In response to a trigger operation on the application creation control, the application creation interface is displayed. The application creation interface is used to set the attribute information corresponding to the target application. The attribute information includes at least one of the following: application name, application description, and application type.

3. The method according to claim 1, characterized in that, When the first node is selected, the process orchestration interface also displays the settings information of the first node; the method further includes: In response to the selection operation of the second node, the second node is switched to the selected state, and the setting information of the first node displayed in the process orchestration interface is updated to the setting information of the second node; or, The workflow orchestration interface also displays settings for dataset nodes, model nodes, and prompt word nodes. When the first node is selected, its settings are displayed in the target area. The method further includes: In response to the selection operation of the second node, the second node is switched to the selected state, and the setting information of the second node is displayed in the target area; The first node and the second node are different nodes among the model node, the dataset node and the prompt word node, respectively.

4. The method according to claim 1, characterized in that, Each response area displays at least one of the following: Best response control, application creation control, and debug information control; The best response control displayed in one response area is used to mark the first model corresponding to the one response area as having the best response to the first prompt word; The application creation control displayed in a response area is used to create an application based on the first model corresponding to the response area; The debug information control displayed in a response area is used to indicate debug information for the first model corresponding to the response area.

5. The method according to claim 1, characterized in that, The method further includes: In response to a trigger operation on the prompt word comparison control, a prompt word comparison interface is displayed. The prompt word comparison interface includes a parameter setting area and a comparison result display area. The parameter setting area displays dataset setting options, model setting options, multiple prompt word input areas, and a prompt word comparison submission control. The dataset setting options are used to select at least one second dataset from at least one preset dataset for prompt word comparison. The model setting options are used to select a second model from multiple preset models for prompt word comparison. In response to a prompt word input operation in at least one of the plurality of prompt word input areas, at least one second prompt word corresponding to the prompt word input operation for prompt word comparison is displayed, wherein the at least one second prompt word corresponds one-to-one with the at least one prompt word input area; In response to the triggering operation of the prompt word comparison submission control, at least one response area is displayed in the comparison result display area. The at least one response area corresponds one-to-one with the at least one second prompt word, and each response area displays the response of the second model to the corresponding second prompt word.

6. The method according to claim 5, characterized in that, Each response area displays at least one of the following: Best response control, application creation control, and debug information control; The best response control displayed in one response area is used to mark the best response in that response area based on the second model for the corresponding second prompt word. The application creation control displayed in a response area is used to create an application based on the second prompt word corresponding to the response area; The debug information control displayed in a response area is used to indicate debug information for the second prompt word corresponding to the response area.

7. The method according to any one of claims 1 to 6, characterized in that, The parameter setting area and the comparison result display area are arranged side-by-side vertically, and the at least one response area is arranged side-by-side horizontally.

8. The method according to claim 7, characterized in that, The display area required for the content to be responded in at least one response area is larger than the target response area of ​​the response area; The target response area displays a vertically adjustable first progress bar, which is used to adjust the response display progress of the target response area. And / or, The comparison result display area also displays a second progress bar that can be adjusted vertically. The second progress bar is used to synchronously adjust the response display progress of the at least one response area.

9. An application creation apparatus, characterized in that, include: The display module is used to respond to the attribute setting operation in the application creation interface and display the process orchestration interface corresponding to the target application to be created. The process orchestration interface displays model nodes, dataset nodes and prompt word nodes, as well as the process orchestration relationship between the model nodes, dataset nodes and prompt word nodes. A creation module is used to respond to setting operations on the model node, the dataset node, and the prompt word node respectively, and to create the target application based on the target model corresponding to the model node, the target dataset corresponding to the dataset node, and the target prompt word corresponding to the prompt word node. The target application is used to answer user input questions through the target model after learning the target dataset and the target prompt word through the target model. The display module is used to respond to the trigger operation of the model comparison control and display the model comparison interface. The model comparison interface includes a parameter setting area and a comparison result display area. The parameter setting area displays dataset setting options, multiple model setting options, prompt input area and model comparison submission control. The dataset setting option is used to determine at least one first dataset from at least one preset dataset for model comparison; In response to the selection operation of at least one of the plurality of model setting options, at least one first model for model comparison is determined from a plurality of preset models, wherein the at least one model setting option corresponds one-to-one with the at least one first model; in response to the prompt word input operation in the prompt word input area, the first prompt word for model comparison corresponding to the prompt word input operation is displayed; In response to the triggering operation of the model comparison submission control, at least one response area is displayed in the comparison result display area. The at least one response area corresponds one-to-one with the at least one first model, and each response area displays the corresponding first model's response to the first prompt word.

10. An electronic device, characterized in that, include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to execute the application creation method according to any one of claims 1 to 8 when the computer program is invoked.

11. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the application creation method according to any one of claims 1 to 8.

Images