Application configuration method, application running method, application creation method, and device and medium

Abstract

Provided in the present disclosure is an application configuration method. The method is applied to an application platform as a service (aPaaS) platform. The method comprises: presenting a configuration page of a first application, wherein the first application is an application in an aPaaS platform; in the configuration page of the first application, receiving an association operation for a second application, wherein the second application is an application in a language model application development platform, and the language model application development platform provides a natural language processing capability; and on the basis of the association operation, establishing an association relationship between the first application and the second application, wherein the association relationship is used by the first application to call the second application. In the application configuration method, the natural language processing capability of the second application can be introduced into the first application without the need to re-establish the first application, such that the usage efficiency of using the first application by a user can be improved.

Description

Application configuration methods, application execution methods, application creation methods, devices and media

[0001] This application claims priority to Chinese Patent Application No. 202411045548.8, filed on July 31, 2024, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0002] This disclosure relates to an application configuration method, an application running method, an application creation method, an electronic device, and a computer-readable storage medium. Background Technology

[0003] Application Platform as a Service (aPaaS) is a cloud computing service model. APaaS platforms are also known as low-code development platforms (LCDP). By providing a graphical interface, they enable developers to quickly develop, deploy, and run applications with minimal or no coding.

[0004] With the continuous development of computer technology, especially machine learning technology, language model application development platforms have emerged. Typically, these platforms are based on various language models, allowing developers to create applications with artificial intelligence (AI) capabilities, such as natural language processing.

[0005] However, how to enable applications that have been developed, deployed, and run through the aPaaS platform to also have AI capabilities has become an urgent problem for the industry. Summary of the Invention

[0006] This disclosure provides an application configuration method. This method enables applications developed on an aPaaS platform to possess AI capabilities, improving application efficiency. This disclosure also provides an application running method, an application creation method, an electronic device, a computer-readable storage medium, and a computer program product.

[0007] Firstly, this disclosure provides an application configuration method applied to an application platform as a service (aPaaS) platform, the application configuration method comprising:

[0008] The configuration page for the first application is displayed; the first application is an application in the aPaaS platform.

[0009] In the configuration page of the first application, the associated operation for the second application is received; wherein, the second application is an application in the language model application development platform, which provides natural language processing capabilities;

[0010] Based on the association operation, an association relationship is established between the first application and the second application. This association relationship is used by the first application to call the second application.

[0011] Secondly, this disclosure provides an application running method applied to a first application, which is an application in an Application Platform as a Service (aPaaS) platform. The application running method includes:

[0012] In the application page of the first application, a request message representing natural language content is received;

[0013] The second application is invoked to perform natural language processing on the request information to determine the response information to the request information; wherein, the second application is an application in the language model application development platform, the language model application development platform provides natural language processing capabilities, and the second application is associated with the first application;

[0014] The application page of the first application displays the response information to the request.

[0015] Thirdly, this disclosure provides an application creation method applied to a language model application development platform that provides natural language processing capabilities. The application creation method includes:

[0016] Receive a creation operation for a second application; wherein the second application is used to establish an association with the first application, and the first application is an application in the Application Platform as a Service (aPaaS) platform;

[0017] Presenting a configuration page for the second application; wherein the configuration page is used to configure at least one information processing type of the second application and the data range corresponding to the at least one information processing type;

[0018] Receive configuration operations triggered on the configuration page, and create a second application based on the configuration operations.

[0019] Fourthly, this disclosure provides an application execution method for a second application, which is an application within a language model application development platform that provides natural language processing capabilities. The application execution method includes:

[0020] Receive a request message representing natural language content sent by a first application; wherein the first application is an application in the application platform as a service (aPaaS) platform, and the first application is associated with the second application;

[0021] The language model is used to perform natural language processing on the request information to generate intermediate processing results and / or response information to the request information;

[0022] Send the intermediate processing results and / or response information to the request information to the first application.

[0023] Fifthly, this disclosure provides an electronic device including a processor and a memory. The processor and the memory communicate with each other. The processor executes instructions stored in the memory to cause the electronic device to perform an application configuration method as described in the first aspect, an application execution method as described in the second aspect, an application creation method as described in the third aspect, or an application execution method as described in the fourth aspect.

[0024] In a sixth aspect, this disclosure provides a computer-readable storage medium storing instructions that instruct an electronic device to perform an application configuration method as described in the first aspect, or an application operation method as described in the second aspect, or an application creation method as described in the third aspect, or an application operation method as described in the fourth aspect.

[0025] In a seventh aspect, this disclosure provides a computer program product containing instructions that, when run on an electronic device, causes the electronic device to perform an application configuration method as described in the first aspect, or an application running method as described in the second aspect, or an application creation method as described in the third aspect, or an application running method as described in the fourth aspect.

[0026] Based on the implementation methods provided in the above aspects, this disclosure can be further combined to provide more implementation methods. Attached Figure Description

[0027] To more clearly illustrate the technical methods of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below.

[0028] Figure 1 is a flowchart illustrating an application configuration method provided in an embodiment of this disclosure;

[0029] Figure 2 is a flowchart illustrating an application running method provided in an embodiment of this disclosure;

[0030] Figures 3A to 3C are schematic diagrams of a process for determining response information according to an embodiment of this disclosure;

[0031] Figure 4 is a flowchart illustrating an application creation method provided in an embodiment of this disclosure;

[0032] Figure 5 is a flowchart illustrating another application operation method provided in an embodiment of this disclosure;

[0033] Figures 6A to 6D are schematic diagrams of a page provided in an embodiment of this disclosure;

[0034] Figure 7 is a schematic diagram of the structure of an application configuration system provided in an embodiment of this disclosure;

[0035] Figure 8 is a schematic diagram of the structure of an application running system provided in an embodiment of this disclosure;

[0036] Figure 9 is a schematic diagram of the structure of an application creation system provided in an embodiment of this disclosure;

[0037] Figure 10 is a schematic diagram of another application running system provided in an embodiment of this disclosure;

[0038] Figure 11 is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0039] The terms "first" and "second" used in the embodiments of this disclosure are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0040] First, some technical terms involved in the embodiments of this disclosure will be introduced.

[0041] Application Platform as a Service (aPaaS) platforms, also known as low-code development platforms (LCDPs), are a cloud computing service model that provides developers with a development environment that includes various automation functions and integrated services. Developers can quickly and efficiently build, deploy, and manage applications by writing little or no code through graphical drag-and-drop and parameterized configuration.

[0042] Specifically, an aPaaS platform typically includes a form engine, a process engine, and a business intelligence (BI) engine. The form engine is used to build and manage forms, the process engine manages the flow rules of forms, and the BI engine generates visual results.

[0043] A language model application development platform can be understood as an application development platform based on various language models. For example, a language model application development platform can be an aPaaS platform based on various language models. Developers can develop applications with artificial intelligence (AI) capabilities, such as natural language processing capabilities, within the language model application development platform by adding data sources and designing workflows.

[0044] With the continuous development of machine learning technology, more and more developers want their applications to have AI capabilities. In related technologies, for applications already developed, deployed, and running through an aPaaS platform, developers can modify the application's business processes. For example, they can add a step to call an external language model. In this way, the application can call the external language model during execution to perform preset tasks, such as text translation, copywriting polishing, and data entry checks, thus enabling the application to have AI capabilities.

[0045] However, the above methods require developers to modify the business processes of applications developed based on the aPaaS platform, which is costly. Furthermore, since aPaaS platforms typically do not provide language models, developers need to write their own code related to calling external language models, which is quite difficult.

[0046] In view of this, the present disclosure provides an application configuration method. This method is applied to an Application Platform as a Service (aPaaS) platform. First, a configuration page for a first application is presented. This first application is an application within the aPaaS platform. Then, on the configuration page of the first application, an association operation for a second application is received. The second application is an application within a language model application development platform, which provides natural language processing capabilities. Based on the association operation, an association relationship is established between the first application and the second application. This association relationship is used by the first application to call the second application.

[0047] In this method, for the first application in the aPaaS platform that does not have AI capabilities, the association between the second application in the language model application development platform and the first application is established. Without rebuilding the first application, the natural language processing capabilities of the second application are introduced into the first application, thereby improving the efficiency of users using the first application.

[0048] To facilitate understanding of the technical solutions provided in the embodiments of this disclosure, the following description will be provided in conjunction with the accompanying drawings.

[0049] Referring to Figure 1, which shows a flowchart of an application configuration method provided in this embodiment of the present disclosure, this method can be applied to an aPaaS platform, and specifically includes:

[0050] S101: Presents the configuration page for the first application.

[0051] In this embodiment of the disclosure, the first application can be an application within the aPaaS platform. That is, the first application can be understood as an application built using the functions and integration services provided by the aPaaS platform. For example, the first application can be a business-related application such as a customer relationship management (CRM) application, a human capital management (HCM) application, or an enterprise resource planning (ERP) application.

[0052] Specifically, under normal circumstances, aPaaS platforms do not provide AI (such as natural language processing) capabilities. Therefore, the first application created on an aPaaS platform can be understood as an application without AI capabilities, and cannot perform natural language processing functions such as human-computer dialogue and intelligent analysis.

[0053] The configuration page for the first application can be understood as a page provided by the aPaaS platform for configuring the relevant functions of the first application. Typically, the configuration page for the first application can be a visual page, where users (such as the developers of the first application) can perform various application configuration-related operations such as data model management, form design, workflow design, permission management, connector management, component addition, and application deployment.

[0054] S102: In the configuration page of the first application, receive the associated operation for the second application.

[0055] In this embodiment of the disclosure, the second application can be an application within a language model application development platform. That is, the second application can be understood as an application built using a language model application development platform.

[0056] Specifically, the language model application development platform provides natural language processing capabilities. For example, it can provide components or functions related to natural language processing. Users (e.g., developers of a second application) can utilize the natural language processing capabilities provided by the platform to enable their applications to perform natural language processing during the application creation process.

[0057] In some possible implementations, a language model application development platform can invoke at least one language model. This language model can be a model with natural language processing capabilities, capable of handling natural language tasks, such as a deep learning model trained on text data. Thus, applications created through the language model application development platform can invoke at least one language model during runtime to perform natural language processing.

[0058] This disclosure does not limit the deployment method of the aPaaS platform and the language model application development platform. In some possible implementations, both the aPaaS platform and the language model application development platform can be deployed within an office automation (OA) system. An OA system, also known as a business system, business platform, or office system, can be understood as an office management system integrating multiple functional modules. For example, an OA system may provide video conferencing, instant messaging, document processing, and scheduling modules. In other words, the aPaaS platform and the language model application development platform can serve as functional modules of the OA system, providing application development capabilities to OA system users (e.g., enterprises). OA system users can quickly develop applications based on their actual business needs through either the aPaaS platform or the language model application development platform.

[0059] In other possible implementations, the aPaaS platform and the language model application development platform can both be independent software systems, and they can communicate with each other. For example, the aPaaS platform and the language model application development platform can be independent applications (APPs).

[0060] The association operation for the second application can be understood as an operation used to establish the association relationship between the first application and the second application. In other words, the aPaaS platform provides the function of associating a first application that does not have natural language processing capabilities with a second application that does have natural language processing capabilities, so as to introduce the natural language processing capabilities of the second application into the first application.

[0061] In practice, the configuration page of the first application can receive association operations, as well as receive selection operations for the second application from multiple applications in the language model application development platform, thus receiving association operations for the second application.

[0062] Understandably, a language model application development platform can include multiple applications with natural language processing capabilities that can be associated with the first application. During the configuration process of the first application, the user (e.g., the developer of the first application) can first trigger the association operation, and then select the specific application from the multiple applications in the language model application development platform to establish the association.

[0063] In some embodiments, the aPaaS platform provides a component for establishing a relationship between applications in the aPaaS platform and applications in the language model application development platform. In this case, the addition of the first component can be received on the configuration page of the first application. The first component can be used to establish a relationship between the first application and applications in the language model application development platform.

[0064] In other words, users (such as the developers of the first application) can trigger associated operations by adding a first component to the first application. For example, users can drag and drop the first component into the first application from its configuration page to quickly and conveniently trigger associated operations.

[0065] S103: Based on the association operation, establish the association relationship between the first application and the second application.

[0066] In this embodiment of the disclosure, the association between the first application and the second application can be used by the first application to call the second application. In other words, when there is an association between the first application and the second application, the first application can call the relevant functions of the second application, for example, the first application can call the natural language processing capabilities of the second application.

[0067] After establishing the association between the first application and the second application, the first application and the second application can have at least partially shared data models.

[0068] For example, a data model can be used to describe the data structure and relationships of applications in an aPaaS platform or a language model application development platform. Data models can include relational data models, hierarchical data models, object-oriented data models, document data models, etc.

[0069] Both aPaaS platforms and language model application development platforms offer form designers. Users can design forms using these designers based on their business needs. A form can be considered a data object, and each data object can further include at least one data field. Data models can be used in conjunction with form designers; the data objects and data fields defined in the form can be mapped to and stored in the data model.

[0070] During the operation of applications on an aPaaS platform or language model application development platform, business data can be collected by executing application business processes. For example, when the application on the aPaaS platform or language model application development platform is a CRM application, the business data can be data related to customer information. As another example, when the application on the aPaaS platform or language model application development platform is an HCM application, the business data can be data related to employee information. Yet another example is when the application on the aPaaS platform or language model application development platform is used to manage the operational failures of a system, the business data can be data related to system failure information.

[0071] The data model can be used to store business data recorded in applications within an aPaaS platform or a language model application development platform. For a first application and a second application with a relationship, the data model can be shared between them, enabling data sharing.

[0072] Thus, for the first application in an aPaaS platform that does not have AI capabilities, without modifying the original process of the first application or recreating the first application in the language model application development platform, the first application can use the AI ​​capabilities of the second application by associating the first application with the second application, thereby realizing the AI-ization of the first application.

[0073] In this method, for the first application in the aPaaS platform that does not have AI capabilities, the association between the second application in the language model application development platform and the first application is established. Without rebuilding the first application, the natural language processing capabilities of the second application are introduced into the first application, thereby improving the efficiency of users using the first application.

[0074] The configuration process of the first application in the aPaaS platform has been described above. The running process of the first application will be described below.

[0075] Referring to Figure 2, a flowchart illustrating an application running method provided in this embodiment of the present disclosure is shown. This method can be applied to a first application, which is an application in an aPaaS platform. The method specifically includes:

[0076] S201: In the application page of the first application, receive request information representing natural language content.

[0077] In this context, the application page of the first application can be understood as the page displayed to the user during the operation of the first application. Request information typically refers to information entered by the user to express a specific instruction.

[0078] In this embodiment of the disclosure, users are supported in inputting request information representing natural language content on the application page of a first application. The user can be a user of the first application (e.g., an administrator of the first application), and the request information can represent natural language content. In other words, while using the first application, the user can input request information by entering natural language on the application page.

[0079] The request information can indicate the type of information processing and the specific scope of data processing. Specifically, the request information may include at least one of the following: a request to analyze first target data in a first application, a request to edit second target data in a first application, or a request to navigate to a target application page in a first application.

[0080] For example, in a request to analyze the first target data in the first application, the information processing type can be data analysis, such as growth trend analysis, distribution analysis, data type analysis, etc., and the data processing scope can be the first target data.

[0081] Although the aPaaS platform includes a BI engine, allowing developers to perform data analysis on business data recorded by the first application and present the visualization results on the application page, the data analysis implemented by the developers using the BI engine is determined during the configuration process of the first application. In other words, users can only view the visualization results of the data analysis set using the BI engine. Therefore, this embodiment of the disclosure supports users of the first application in expressing their data analysis needs by inputting request information. Thus, it is not limited to the data analysis functions already determined by the BI engine in the first application; users of the first application can perform rich, flexible, and multi-type data analysis functions.

[0082] In a request to edit the second target data in the first application, the information processing type can be data editing, such as data modification or data entry, and the data processing scope can be the second target data.

[0083] During the operation of the first application, users (e.g., administrators) can manually edit the business data recorded by the application, such as adding or modifying business data in a form. However, this data editing requires manual operation from the user. Typically, the user must first locate the form containing the data to be edited and then perform the specific editing operation, which is cumbersome. Therefore, this embodiment of the disclosure allows users to express their data editing needs by inputting request information. This eliminates the need for manual data editing by the user, achieving automatic and rapid data editing functionality.

[0084] In a request to navigate to a target application page in the first application, the information processing type can be page navigation, such as page jump or page location, and the data processing scope can be the target application page.

[0085] For applications with complex business processes, these applications typically include numerous application pages. When a user needs to access a specific application page or perform a specific function but cannot locate the corresponding application page, they usually have to repeatedly search through a large number of application pages, resulting in high interaction costs. Therefore, embodiments of this disclosure support users of the application to express their page navigation needs by inputting request information. This eliminates the need for users to manually search for application pages, enabling automatic navigation and reducing interaction costs.

[0086] S202: Call the second application to perform natural language processing on the request information and determine the response information to the request information.

[0087] For example, the second application is an application within a language model application development platform, which provides natural language processing capabilities. The second application is related to the first application. In other words, the second application has natural language processing capabilities, and through the relationship between the first and second applications, these capabilities are introduced into the first application.

[0088] In practice, for request information representing natural language content, the first application can call the second application, use the natural language processing capabilities of the second application to process the request information, and determine the response information of the request information by combining the intermediate processing results returned by the second application, or directly receive the response information of the request information returned by the second application.

[0089] Different information processing types have different processing procedures, which will be explained below.

[0090] In some embodiments, the request information includes a request to analyze first target data in a first application. As shown in FIG3A, the request information is sent to a second application, and the second application returns a data analysis statement for the first target data. The first application executes the data analysis statement, obtains the first target data, sends the first target data to the second application, and receives the data analysis result of the first target data returned by the second application.

[0091] In other words, when the request is for analyzing the first target data in the first application, the response can be the data analysis result of the first target data, such as a data analysis result including text and charts. Since the second application cannot directly obtain the specific numerical value of the first target data that needs to be analyzed, the process of determining the response can include: using the natural language processing capabilities of the second application to generate a data analysis statement, executing the data analysis statement to obtain the first target data, using the second application to perform data analysis on the first target data, and determining the data analysis result of the first target data.

[0092] For example, a data analysis statement, also known as a Structured Query Language (SQL) statement, is executed by a first application. This allows the first application to retrieve the primary target data required for the data analysis needs indicated by the requested information from the recorded business data. Then, the second application utilizes its natural language processing and data analysis capabilities to perform data analysis on the primary target data, generating data analysis results that meet the data analysis requirements.

[0093] In other embodiments, the request information includes a request to edit second target data in the first application. As shown in Figure 3B, the request information is sent to the second application, and the first application receives an editing instruction for the second target data in the first application. The first application executes the editing instruction and determines the editing result of the second target data.

[0094] In other words, when the request is for editing second target data in the first application, the response can be the result of editing the second target data, such as the modified second target data or the newly added second target data. When the information processing type is data editing, the second application does not need to obtain the specific value of the second target data to be edited. By performing natural language processing on the request information, it can generate editing instructions, such as an editing instruction to add a value to a data field or an editing instruction to modify a data field to another value. Therefore, the process of determining the response information can include: using the natural language processing capabilities of the second application to generate editing instructions, execute editing instructions, and obtain editing results.

[0095] In some other embodiments, the request information includes a request to navigate to a target application page in the first application. As shown in Figure 3C, the request information is sent to a second application, and the second application returns page information of the target application page in the first application.

[0096] In other words, when the request is for navigation to a target application page in the first application, the response can be page information of the target application page, such as a link to the target application page. When the information processing type is page navigation, the second application does not need to obtain the specific business data recorded in the target application page. By performing natural language processing on the request information, the page information of the target application page can be determined. Therefore, the process of determining the response can be: using the natural language processing capabilities of the second application to generate the page information of the target application page.

[0097] S203: On the application page of the first application, the response information for the requested information is presented.

[0098] After determining the response to the request, the response can be displayed on the application page of the first application. This completes one round of dialogue—from inputting the request to generating the response—within the first application.

[0099] In some embodiments, request and response information may be presented in a dialog window. For example, a dialog window can be understood as an interface for human-computer dialogue in a first application. The dialog window may have different presentation formats. For example, the dialog window may be presented side-by-side with the application page of the first application, or it may float above the application page of the first application as a floating window component.

[0100] In this method, the first application in the aPaaS platform is associated with the second application in the language model application development platform, and the natural language processing capabilities of the second application are introduced into the first application. Thus, while using the first application, users can engage in human-computer dialogue within the application's interface, enabling the first application to possess AI capabilities and improving its efficiency.

[0101] The configuration and operation processes of the first application have been described above. In this embodiment, the first application and the second application are related. The creation and operation processes of the second application will be described below.

[0102] Referring to Figure 4, a flowchart illustrating an application creation method provided in this embodiment of the present disclosure is shown. This method can be applied to a language model application development platform, which provides natural language processing capabilities. The method specifically includes:

[0103] S401: Receive the creation operation for the second application.

[0104] The creation of the second application can be understood as the creation of a second application within the language model application development platform. This second application can be used to establish a relationship with the first application, which is an application within the aPaaS platform. In other words, the second application can be understood as an application created within the language model application development platform that is to be associated with the first application.

[0105] In this embodiment of the disclosure, the aPaaS platform provides an entry point for creating a second application. Specifically, the creation operation for the second application can be received in the configuration page of the first application.

[0106] In other words, while a user (e.g., the developer of the first application) is configuring the first application, they can directly create a second application to be associated with the first application through the configuration page of the first application in the aPaaS platform.

[0107] In this way, the aPaaS platform and the language model application development platform are connected, and users do not need to switch between the two platforms. They can create the second application simply through the configuration page of the first application, simplifying the application creation process.

[0108] S402: Presents the configuration page for the second application.

[0109] In this embodiment of the disclosure, the configuration page can be used to configure at least one information processing type of the second application and the data model corresponding to the at least one information processing type.

[0110] For example, a data model corresponding to at least one information processing type can be understood as a data model that can be processed under that information processing type. In other words, users can configure different information processing types for a second application, and configure different data ranges for each information processing type to meet diverse business needs.

[0111] S403: Receive configuration operations triggered in the configuration page, and create a second application based on the configuration operations.

[0112] Specifically, the configuration operations triggered in the configuration page may include: selecting the type of information processing to receive, presenting the data objects and / or data fields included in the first application, receiving a selection operation for a target data object in the data objects, and / or receiving a selection operation for a target data field in the data fields.

[0113] In other words, the configuration operation can be divided into two levels. First, the user can select the information processing type of the second application. Then, the user can select the target data object and / or target data field, which constitute the data model corresponding to that information processing type.

[0114] After the user completes the configuration operation, based on the information processing type carried by the configuration operation and the data model corresponding to the information processing type, a second application is established in the language model application development platform, so that the second application has natural language processing capabilities corresponding to the information processing type.

[0115] In this embodiment of the disclosure, it is also supported to adjust the application information of applications in the language model application development platform. Specifically, in the language model application development platform, application information of multiple applications in the language model application development platform is presented, and in response to the editing operation of the target application among the multiple applications, the application information of the target application is modified.

[0116] For example, the application information in a language model application development platform can be understood as information related to the AI ​​capabilities of the application within that platform. In other words, users can adjust the AI ​​capabilities of the application in the language model application development platform according to their actual business needs.

[0117] In some embodiments, in response to a new operation on a first information processing type for a target application among multiple applications, the first information processing type is added to the target application. That is, the target application originally did not have the AI ​​capabilities corresponding to the first information processing type, but through an editing operation on the target application, the first information processing type is added to the target application, enriching the AI ​​capabilities of the target application.

[0118] In other embodiments, in response to an adjustment operation for a second information processing type of a target application across multiple applications, a prompt template matching the second information processing type is adjusted. That is, the target application originally possesses AI capabilities corresponding to the second information processing type; by adjusting the prompt template through editing operations on the target application, the accuracy under the second information processing type is improved.

[0119] In this method, a second application is created in the language model application development platform to associate with the first application in the aPaaS platform. By configuring the information processing type and the data model that matches the information processing type, after establishing the association between the first application and the second application, the first application and the second application can share part of the data model, and the natural language processing capabilities of the second application are introduced into the first application.

[0120] Referring to Figure 5, which shows a flowchart of another application running method provided in this embodiment of the present disclosure, this method can be applied to a second application, which is an application in a language model application development platform. The language model application development platform provides natural language processing capabilities, and the method specifically includes:

[0121] S501: Receive the request information representing natural language content sent by the first application.

[0122] The request information can be understood as information input by the user during the operation of the first application to express a specific instruction. The first application is an application within the aPaaS platform, and it is related to the second application.

[0123] Since the first application and the second application are related, the first application does not have natural language processing capabilities, while the second application does. Therefore, the second application can receive request information representing natural language content and perform natural language processing on the request information.

[0124] S502: Use a language model to perform natural language processing on the request information to generate intermediate processing results and / or response information to the request information.

[0125] Specifically, the natural language processing capabilities provided by the language model application development platform can be implemented by calling the language model. In other words, a second application in the language model application development platform can perform natural language processing on the requested information by calling the language model.

[0126] In some possible implementations, the second application can extract metadata information from the request information, determine a prompt template that matches the information processing type according to the information processing type indicated by the request information, then generate prompt information based at least on the metadata information and the prompt template that matches the information processing type, send the prompt information to the language model, and receive the intermediate processing results and / or the response information to the request information returned by the language model.

[0127] For example, metadata information may include information related to data objects and / or data fields. Information related to data objects and / or data fields may include the object name of the data object, the field name of the data field, the description of the data object, the description of the data field, descriptions of relationships between multiple data objects, and descriptions of relationships between multiple data fields.

[0128] Different information processing types correspond to different prompt templates. The prompt information generated based on the prompt template that matches the information processing type can be used to instruct the language model on the natural language processing process of the requested information. In other words, through the prompt information, the language model can learn about the information related to the data object and / or data field, the information processing type, and the specific information processing requirements. Combined with the prompt information's prompting capabilities, the language model can generate intermediate processing results and / or response information to the requested information.

[0129] Since request information can represent different information processing types, and different information processing types can have different processing flows, the second application can use a language model to perform natural language processing on the request information to generate intermediate processing results or directly generate response information to the request information.

[0130] In some embodiments, the request information is a request to analyze first target data in a first application. In this case, the second application uses a language model to perform natural language processing on the request information and generates intermediate processing results. The intermediate processing results may include data analysis statements for the first target data.

[0131] As shown in Figure 3A, after the second application extracts metadata information from the request information, it generates a prompt message and sends the prompt message to the language model. The language model then returns a data analysis statement to the second application.

[0132] Furthermore, considering that the data model types of the first application and the second application may be different, after the second application generates the intermediate processing result, that is, after the second application receives the data analysis statement returned by the language model, it can also convert the data analysis statement into a format that matches the data model type of the first application.

[0133] For example, when the data model type of the first application is an object-oriented data model and the data model type of the second application is a relational data model, the data analysis statement returned by the language model can be an SQL statement. In order to facilitate the execution of the data analysis statement by the first application, the second application can convert the SQL statement into an object query language (OQL) statement that matches the object-oriented data model.

[0134] In other embodiments, the request information is a request to edit second target data in the first application. In this case, the second application uses a language model to perform natural language processing on the request information and generates intermediate processing results. The intermediate processing results may include editing instructions for the second target data in the first application.

[0135] As shown in Figure 3B, after the second application extracts metadata information from the request information, it generates a prompt message and sends the prompt message to the language model. The language model then returns an editing instruction to the second application.

[0136] Furthermore, users can confirm or modify editing instructions to ensure that the instructions meet their data editing needs.

[0137] In some other embodiments, the request information is a request to navigate to a target application page in the first application. In this case, the second application uses a language model to perform natural language processing on the request information and generates a response to the request information. The response to the request information may include page information of the target application page in the first application.

[0138] As shown in Figure 3C, after the second application extracts metadata information from the request information, it generates a prompt message and sends the prompt message to the language model. The language model then returns the page information of the target application page to the second application.

[0139] S503: Send the response information of the intermediate processing results and / or request information to the first application.

[0140] Considering data permission issues, when the request information is a request to analyze the first target data in the first application, the second application can return the data analysis statement and the requester's identity carried in the request information to the first application. This allows the first application to execute the data analysis statement and obtain the first target data as the requester who sent the request information (i.e., the user of the first application), thus avoiding data acquisition failure due to data permission issues.

[0141] Similarly, when the request information is a request to edit the second target data in the first application, the second application can also return the editing instructions and the requester identifier carried in the request information to the first application, so that the first application can execute the editing instructions as the requester who sent the request information (i.e., the user of the first application) and complete the data editing, thus avoiding data editing failure due to data permissions.

[0142] In this method, since the first application in the aPaaS platform is related to the second application in the language model application development platform, the second application uses its AI capabilities to perform natural language processing on the request information entered by the user in the first application, and returns the generated intermediate processing results or reply information to the first application, thereby realizing the intelligent operation of the first application.

[0143] The following will describe the pages related to the first and second applications in this embodiment of the disclosure, taking into account specific application scenarios.

[0144] As shown in Figure 6A, in the aPaaS platform, the configuration page of the first application (not shown in the figure) can provide an entry point 601 for creating the second application. The entry point 601 for creating the second application displays introductory information related to the language model application and a creation control 602, which the user can trigger to create the second application.

[0145] As shown in Figure 6B, the aPaaS platform provides a first component 604 for establishing associations between applications in the aPaaS platform and applications in the language model application development platform. Users can add the first component 604 by dragging and dropping it into the configuration page 603 of the first application. Furthermore, after adding the first component 604 to the first application, the configuration page 603 of the first application displays an area 605 for establishing associations. Users can select a second application from among multiple applications in the language model application development platform within this area 605 to establish an association between the first and second applications.

[0146] As shown in Figure 6C, users can create a second application on the configuration page 606 of the second application. For example, on the configuration page 606 of the second application, users can select the avatar of the second application, set the name of the second application, select the information processing type, and select the data model corresponding to the information processing type.

[0147] As shown in Figure 6D, after establishing the association between the first application and the second application, the AI ​​capabilities of the second application are introduced into the first application. Users of the first application can then engage in human-computer dialogue on the application page 607 of the first application. Specifically, the application page 607 of the first application can present a dialogue window 608 in the form of a floating window component. Users of the first application can input request information in the dialogue window 608, such as "customer distribution this year". The first application utilizes the second application to perform natural language processing on the request information. Based on the intermediate processing results or response information returned by the second application, the first application determines the response information for the request information and presents the response information in the dialogue window 608. For example, the response information can include information such as a distribution map of the customer's industry, thus realizing one round of human-computer dialogue.

[0148] In this embodiment, the first application developed by the aPaaS platform could originally only view and analyze data through a graphical user interface (GUI). After establishing the association between the first and second applications, AI capabilities are introduced into the first application without modifying its original business processes. Users of the first application can then process information through a conversational user interface (CUI), enriching their experience, reducing difficulty, and improving efficiency. Furthermore, it supports custom configuration and adjustments for the information processing types in the second application, making it better suited to the business needs of the first application.

[0149] The application configuration method, application running method, and application creation method provided by the embodiments of this disclosure have been described in detail above with reference to Figures 1 to 6. The system and device provided by the embodiments of this disclosure will be described below with reference to the accompanying drawings.

[0150] Referring to the structural diagram of the application configuration system shown in Figure 7, system 70 is deployed on the Application Platform as a Service (aPaaS) platform, and system 70 includes:

[0151] The presentation module 701 is used to present the configuration page of the first application, which is an application in the aPaaS platform.

[0152] The receiving module 702 is used to receive associated operations for the second application in the configuration page of the first application; wherein the second application is an application in the language model application development platform, and the language model application development platform provides natural language processing capabilities.

[0153] Module 703 is established to establish an association between the first application and the second application based on the association operation. The association is used by the first application to call the second application.

[0154] The application configuration system 70 according to the embodiments of this disclosure can correspond to the execution of the application configuration method described in the embodiments of this disclosure, and the above and other operations and / or functions of each module / unit of the application configuration system 70 are respectively to implement the corresponding processes of each method in the embodiment shown in FIG1. ​​For the sake of brevity, they will not be described again here.

[0155] Referring to the structural diagram of the application running system shown in Figure 8, the system 80 is deployed on the first application, which is an application in the Application Platform as a Service (aPaaS) platform. The system 80 includes:

[0156] The receiving module 801 is used to receive request information representing natural language content in the application page of the first application;

[0157] The determination module 802 is used to call the second application to perform natural language processing on the request information and determine the response information to the request information; wherein, the second application is an application in the language model application development platform, the language model application development platform provides natural language processing capabilities, and the second application is related to the first application;

[0158] The presentation module 803 is used to present the response information to the request information in the application page of the first application.

[0159] The application running system 80 according to the embodiments of this disclosure can correspond to the application running method described in the embodiments of this disclosure, and the above and other operations and / or functions of each module / unit of the application running system 80 are respectively to implement the corresponding processes of each method in the embodiment shown in FIG2. For the sake of brevity, they will not be described again here.

[0160] Referring to Figure 9, which shows a schematic diagram of the application creation system, this system is deployed on a language model application development platform. This platform provides natural language processing capabilities. The system 90 includes:

[0161] The receiving module 901 is used to receive a creation operation for the second application; wherein the second application is used to establish an association with the first application, and the first application is an application in the application platform as a service (aPaaS) platform.

[0162] The presentation module 902 is used to present the configuration page of the second application; wherein the configuration page is used to configure at least one information processing type of the second application and the data range corresponding to the at least one information processing type.

[0163] Create module 903 to receive configuration operations triggered in the configuration page and create a second application based on the configuration operations.

[0164] The application creation system 90 according to the embodiments of this disclosure can correspond to the application creation method described in the embodiments of this disclosure, and the above and other operations and / or functions of each module / unit of the application creation system 90 are respectively for implementing the corresponding processes of each method in the embodiment shown in FIG4. For the sake of brevity, they will not be described again here.

[0165] Referring to the structural diagram of the application running system shown in Figure 10, system 100 is deployed in a second application, which is an application in a language model application development platform. The language model application development platform provides natural language processing capabilities. System 100 includes:

[0166] The receiving module 1001 is used to receive request information representing natural language content sent by the first application; wherein the first application is an application in the application platform as a service (aPaaS) platform, and the first application is associated with the second application.

[0167] The generation module 1002 is used to perform natural language processing on the request information using a language model to generate intermediate processing results and / or response information to the request information;

[0168] The sending module 1003 is used to send the intermediate processing results and / or the response information of the request information to the first application.

[0169] The application running system 100 according to the embodiments of this disclosure can correspond to the execution of the methods described in the embodiments of this disclosure, and the above and other operations and / or functions of each module / unit of the application running system 100 are respectively for implementing the corresponding processes of each method in the embodiment shown in FIG5. For the sake of brevity, they will not be described again here.

[0170] This disclosure also provides an electronic device. Specifically, this electronic device is used to implement the functions of the application configuration system 70 in the embodiment shown in FIG. 7, or to implement the functions of the application running system 80 in the embodiment shown in FIG. 8, or to implement the functions of the application creation system 90 in the embodiment shown in FIG. 9, or to implement the functions of the application running system 100 in the embodiment shown in FIG. 10.

[0171] Figure 11 provides a schematic diagram of the structure of an electronic device 1100. As shown in Figure 11, the electronic device 1100 includes a bus 1101, a processor 1102, a communication interface 1103, and a memory 1104. The processor 1102, the memory 1104, and the communication interface 1103 communicate with each other via the bus 1101.

[0172] Bus 1101 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one thick line is used in Figure 11, but this does not indicate that there is only one bus or one type of bus.

[0173] The processor 1102 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0174] The communication interface 1103 is used for external communication. For example, the communication interface 1103 can be used to communicate with a terminal.

[0175] Memory 1104 may include volatile memory, such as random access memory (RAM). Memory 1104 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0176] The memory 1104 stores executable code, and the processor 1102 executes the executable code to perform the aforementioned application configuration method, application running method, or application creation method.

[0177] Taking the application configuration method executed by processor 1102 as an example, in the case of implementing the embodiment shown in FIG5, and where each module or unit of the application configuration system 70 described in the embodiment of FIG7 is implemented by software, the software or program code required to execute the functions of each module / unit in FIG7 can be partially or entirely stored in memory 1104. Processor 1102 executes the program code corresponding to each unit stored in memory 1104 to execute the aforementioned application configuration method.

[0178] This disclosure also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the application configuration method applied to the application configuration system 70, or the application running method applied to the application running system 80, or the application creation method applied to the application creation system 90, or the application running method applied to the application running system 100.

[0179] This disclosure also provides a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this disclosure are generated.

[0180] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0181] When the computer program product is executed by a computer, the computer performs any of the aforementioned application configuration method, application running method, or application creation method. The computer program product can be a software installation package; when any of the aforementioned application configuration method, application running method, or application creation method is required, the computer program product can be downloaded and executed on the computer.

[0182] 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 a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, may 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.

[0183] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units / modules do not necessarily limit the specific unit itself.

[0184] 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.

[0185] In the context of embodiments of this disclosure, a machine-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 machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0186] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0187] It should be understood that in this disclosure, "at least one item" means one or more, and "more than one" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0188] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0189] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0190] The above description of the disclosed embodiments enables those skilled in the art to make or use this disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An application configuration method applied to an application platform as a service platform, the method comprising: presenting a configuration page of a first application, the first application being an application in the application platform as a service platform; in the configuration page of the first application, receiving an association operation for a second application; wherein the second application is an application in a language model application development platform, the language model application development platform providing natural language processing capability; according to the association operation, establishing an association relationship between the first application and the second application, the association relationship being used for the first application to call the second application.

2. The method of claim 1, wherein, The first application and the second application have at least partially shared data models.

3. The method of claim 1 or 2, wherein, The receiving, in the configuration page of the first application, of the association operation for the second application comprises: in the configuration page of the first application, receiving an association operation; and receiving a selection operation for a second application from a plurality of applications in the language model application development platform.

4. The method of claim 3, wherein, The receiving, in the configuration page of the first application, of the association operation comprises: in the configuration page of the first application, receiving an addition operation of a first component, the first component being used to establish an association relationship between the first application and an application in the language model application development platform.

5. An application running method applied to a first application, the first application being an application in an application platform as a service platform, the method comprising: in an application page of the first application, receiving request information representing natural language content; calling a second application to perform natural language processing on the request information to determine reply information of the request information; wherein the second application is an application in a language model application development platform, the language model application development platform providing natural language processing capability, and the second application has an association relationship with the first application; in the application page of the first application, presenting the reply information of the request information.

6. The method of claim 5, wherein, The request information comprises at least one of: a request for analyzing first target data in the first application; a request for editing second target data in the first application; a request for navigating a target application page in the first application.

7. The method of claim 5, wherein, The request information comprises the request for analyzing the first target data in the first application, and the calling of the second application to perform natural language processing on the request information to determine the reply information of the request information comprises: sending the request information to the second application, and receiving a data analysis statement for the first target data returned by the second application; executing the data analysis statement to obtain the first target data; sending the first target data to the second application, and receiving a data analysis result of the first target data returned by the second application.

8. The method of claim 5, wherein, The request information comprises the request for editing the second target data in the first application, and the calling of the second application to perform natural language processing on the request information to determine the reply information of the request information comprises: sending the request information to the second application, and receiving an editing instruction returned by the second application for the second target data in the first application; executing the editing instruction to determine an editing result of the second target data.

9. The method of claim 5, wherein, The request information includes a request for navigating a target application page in the first application, and the second application performs natural language processing on the request information to determine reply information of the request information, including: sending the request information to the second application, and receiving page information of the target application page in the first application returned by the second application.

10. An application creation method applied to a language model application development platform, the language model application development platform providing natural language processing capability, the method comprising: receiving a creation operation for a second application; wherein the second application is used to establish an association relationship with a first application, and the first application is an application in an application program platform as a service platform; presenting a configuration page of the second application; wherein the configuration page is used to configure at least one information processing type of the second application and a data model corresponding to the at least one information processing type; receiving a configuration operation triggered in the configuration page, and creating the second application according to the configuration operation.

11. The method of claim 10, wherein, The receiving of the creation operation for the second application comprises: receiving the creation operation for the second application in a configuration page of the first application.

12. The method of claim 10 or 11, wherein, The receiving of the configuration operation triggered in the configuration page comprises: receiving a selection operation of an information processing type; and presenting a data object and / or a data field included in the first application, receiving a selection operation for a target data object in the data object, and / or receiving a selection operation for a target data field in the data field.

13. The method of any one of claims 10-12, further comprising: presenting application information of a plurality of applications in the language model application development platform; in response to an editing operation for a target application in the plurality of applications, modifying application information of the target application.

14. The method of claim 13, wherein, The modifying of the application information of the target application in response to the editing operation for the target application in the plurality of applications comprises: in response to an adding operation of a first information processing type for the target application in the plurality of applications, adding the first information processing type to the target application; in response to an adjusting operation of a second information processing type for the target application in the plurality of applications, adjusting a prompt template matched with the second information processing type.

15. An application running method applied to a second application, the second application being an application in a language model application development platform, the language model application development platform providing natural language processing capability, the method comprising: receiving request information representing natural language content sent by a first application; wherein the first application is an application in an application program platform as a service platform, and the first application has an association relationship with the second application; performing natural language processing on the request information by using a language model to generate an intermediate processing result and / or reply information of the request information. send the intermediate processing result and / or reply information of the request information to the first application.

16. The method of claim 15, wherein, The natural language processing of the request information by using the language model comprises: extracting metadata information from the request information, the metadata information comprising information related to data objects and / or data fields; determining a prompt template matched with the information processing type according to the information processing type indicated by the request information; generating prompt information based on at least the metadata information and the prompt template matched with the information processing type, the prompt information being used to indicate the processing procedure of the natural language processing of the request information by the language model; sending the prompt information to the language model, and receiving the intermediate processing result and / or reply information of the request information returned by the language model.

17. The method of claim 15 or 16, wherein, The request information is a request for analyzing first target data in the first application, and the intermediate processing result comprises a data analysis statement for the first target data. The request information is a request for editing second target data in the first application, and the intermediate processing result comprises an editing instruction for the second target data in the first application. The request information is a request for navigating a target application page in the first application, and the reply information of the request information comprises page information of the target application page in the first application.

18. The method of claim 17, wherein, The request information is a request for analyzing first target data in the first application, and the intermediate processing result comprises a data analysis statement for the first target data. After the natural language processing of the request information by using the language model to generate the intermediate processing result and / or the reply information of the request information, the method further comprises: converting the data analysis statement into a format matched with a data model type of the first application. 19.An electronic device comprising a processor and a memory; wherein, The processor is configured to execute instructions stored in the memory, so that the electronic device performs the method of any one of claims 1 to 4, or performs the method of any one of claims 5 to 9, or performs the method of any one of claims 10 to 14, or performs the method of any one of claims 15 to 18.

20. A computer-readable storage medium comprising instructions, wherein, The instructions instruct the electronic device to perform the method of any one of claims 1 to 4, or perform the method of any one of claims 5 to 9, or perform the method of any one of claims 10 to 14, or perform the method of any one of claims 15 to 18.

Images