Application configuration method, application operation method, application creation method and related equipment
By establishing an association relationship with the language model application development platform in the aPaaS platform application and introducing natural language processing capabilities, the problem of aPaaS platform application lacks AI capabilities, and the application AIization and usage efficiency improvement are achieved.
Patent Information
- Application Number
- CN202411045548.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The applications developed by existing aPaaS platforms lack AI capabilities, especially natural language processing capabilities, which leads developers to modify business processes and write complex code to introduce external language models, increasing development difficulty and cost.
By receiving associated operations in the application configuration page of the aPaaS platform, establishing the association relationship between the aPaaS platform application and the language model application development platform application, using the natural language processing capabilities of the language model application development platform to introduce aPaaS platform application, and implementing aPaaS platform application AI.
Without rebuilding the aPaaS platform application, the natural language processing capabilities of the language model application development platform are directly introduced into the aPaaS platform application, which improves user usage efficiency, simplifies the application's AI capabilities introduction process, and reduces the development difficulty and cost.
Smart Images

Figure CN118939340A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to an application configuration method, an application running method, an application creation method, an electronic device, and a computer-readable storage medium. Background Art
[0002] Application platform as a service (aPaaS) is a cloud computing service model. The aPaaS platform is also called a low-code development platform (LCDP). By providing a graphical interface, developers can quickly develop, deploy and run applications by writing a small amount of code or without writing any code.
[0003] With the continuous development of computer technology, especially machine learning technology, language model application development platforms have emerged. Generally speaking, language model application development platforms are based on various language models, and developers can use language model application development platforms to develop applications with artificial intelligence (AI) capabilities such as natural language processing.
[0004] However, for applications that have been developed, deployed, and run through the aPaaS platform, how to make the above applications also have AI capabilities has become an urgent problem to be solved in the industry. Summary of the invention
[0005] The present application provides an application configuration method. The method can enable applications developed on the aPaaS platform to have AI capabilities and improve the efficiency of application use. The present application also provides an application operation method, an application creation method, an electronic device, a computer-readable storage medium, and a computer program product.
[0006] In a first aspect, the present application provides an application configuration method, which is applied to an application platform as a service (aPaaS) platform, and the method comprises:
[0007] Presenting a configuration page of a first application, where the first application is an application in the aPaaS platform;
[0008] In a configuration page of the first application, receiving an associated 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 natural language processing capabilities;
[0009] According to the association operation, an association relationship between the first application and the second application is established, and the association relationship is used for the first application to call the second application.
[0010] In a second aspect, the present application provides an application running method, which is applied to a first application, where the first application is an application in an application platform as a service (aPaaS) platform, and the method includes:
[0011] In an application page of the first application, receiving request information representing natural language content;
[0012] 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 provides natural language processing capabilities, and the second application is associated with the first application;
[0013] In the application page of the first application, reply information of the request information is presented.
[0014] In a third aspect, the present application provides an application creation method, which is applied to a language model application development platform, wherein the language model application development platform provides natural language processing capabilities, and the method includes:
[0015] Receiving a creation operation for a second application; wherein the second application is used to establish an association relationship with the first application, and the first application is an application in an application platform as a service aPaaS platform;
[0016] 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 range corresponding to the at least one information processing type;
[0017] A configuration operation triggered in the configuration page is received, and the second application is created according to the configuration operation.
[0018] In a fourth aspect, the present application provides an application running method, which is applied to a second application, where the second application is an application in a language model application development platform, and the language model application development platform provides natural language processing capabilities, and the method includes:
[0019] Receiving request information representing natural language content sent by a first application; wherein the first application is an application in an application platform as a service (aPaaS) platform, and the first application is associated with the second application;
[0020] Performing natural language processing on the request information using a language model to generate an intermediate processing result and / or reply information to the request information;
[0021] The intermediate processing result and / or reply information of the request information is sent to the first application.
[0022] In a fifth aspect, the present application provides an electronic device, the electronic device comprising a processor and a memory. The processor and the memory communicate with each other. The processor is used to execute instructions stored in the memory, so that the electronic device executes the application configuration method of the first aspect, or executes the application running method of the second aspect, or executes the application creation method of the third aspect, or executes the application running method of the fourth aspect.
[0023] In a sixth aspect, the present application provides a computer-readable storage medium, in which instructions are stored, and the instructions instruct an electronic device to execute an application configuration method such as the first aspect, or to execute an application running method such as the second aspect, or to execute an application creation method such as the third aspect, or to execute an application running method such as the fourth aspect.
[0024] In the seventh aspect, the present application provides a computer program product comprising instructions, which, when executed on an electronic device, enables the electronic device to execute the application configuration method of the first aspect, or execute the application running method of the second aspect, or execute the application creation method of the third aspect, or execute the application running method of the fourth aspect.
[0025] Based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations.
[0026] It can be seen from the above technical solutions that this application has the following advantages:
[0027] The present application provides an application configuration method, which is applied to an application platform as a service (aPaaS) platform. The method first presents a configuration page of a first application, where the first application is an application in the aPaaS platform. Then, in the configuration page of the first application, an association operation for a second application is received, where the second application is an application in a language model application development platform, and the language model application development platform provides natural language processing capabilities. According to the association operation, an association relationship between the first application and the second application is established, and the association relationship is used for the first application to call the second application.
[0028] In this method, for the first application in the aPaaS platform that does not have AI capabilities, an association relationship is established between the second application in the language model application development platform and the first application. Without rebuilding the first application, the natural language processing capability of the second application is introduced into the first application, thereby improving the user's efficiency in using the first application. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] In order to more clearly illustrate the technical method of the embodiments of the present application, the drawings required for use in the embodiments are briefly introduced below.
[0030] Figure 1 A flowchart of an application configuration method provided in an embodiment of the present application;
[0031] Figure 2 A flowchart of an application operation method provided in an embodiment of the present application;
[0032] FIG. 3A to FIG. 3C A schematic diagram of a process for determining reply information provided in an embodiment of the present application;
[0033] Figure 4 A flowchart of an application creation method provided in an embodiment of the present application;
[0034] Figure 5 A flowchart of an application operation method provided in an embodiment of the present application;
[0035] FIG. 6A to FIG. 6D A page schematic diagram provided for an embodiment of the present application;
[0036] Figure 7 A schematic diagram of the structure of an application configuration system provided in an embodiment of the present application;
[0037] Figure 8 A schematic diagram of the structure of an application running system provided in an embodiment of the present application;
[0038] Fig. 9 A schematic diagram of the structure of an application creation system provided in an embodiment of the present application;
[0039] Fig.10 A schematic diagram of the structure of an application running system provided in an embodiment of the present application;
[0040] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0041] The terms "first" and "second" in the embodiments of the present application are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.
[0042] First, some technical terms involved in the embodiments of the present application are introduced.
[0043] Application platform as a service (aPaaS), also known as low code development platform (LCDP), is a cloud computing service model that provides developers with a development environment that includes a variety of automation functions and integrated services. Developers can quickly and efficiently build, deploy and manage applications through graphical drag and drop, parameterized configuration, etc., with less or no code written.
[0044] Specifically, the aPaaS platform usually 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 is used to manage the flow rules of forms, and the BI engine is used to generate visualization results.
[0045] The language model application development platform can be understood as an application development platform based on various language models. For example, the 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, in the language model application development platform by adding data sources, designing workflows, etc.
[0046] With the continuous development of machine learning technology, more and more developers want applications to have AI capabilities. In related technologies, for applications that have been developed, deployed and run through the aPaaS platform, developers can modify the business process of the application, for example, adding a step to call an external language model in the business process, so that the application can call the external language model during execution and perform preset tasks, such as text translation, copywriting polishing, input information detection, etc., so that the application has AI capabilities.
[0047] However, the above method requires developers to modify the business process of applications developed based on the aPaaS platform, which is costly. In addition, since the aPaaS platform usually does not provide language models, developers need to write their own code related to calling external language models, which makes development difficult.
[0048] In view of this, the present application provides an application configuration method. The method is applied to an application platform as a service aPaaS platform. The method first presents a configuration page of a first application, where the first application is an application in the aPaaS platform. Then, in the configuration page of the first application, an association operation for a second application is received, where the second application is an application in a language model application development platform, where the language model application development platform provides natural language processing capabilities, and an association relationship between the first application and the second application is established according to the association operation, where the association relationship is used for the first application to call the second application.
[0049] In this method, for the first application in the aPaaS platform that does not have AI capabilities, an association relationship is established between the second application in the language model application development platform and the first application. Without rebuilding the first application, the natural language processing capability of the second application is introduced into the first application, thereby improving the user's efficiency in using the first application.
[0050] To facilitate understanding of the technical solution provided by the embodiments of the present application, it will be described below with reference to the accompanying drawings.
[0051] See also Figure 1 The flowchart of an application configuration method provided in the embodiment of the present application is shown, and the method can be applied to the aPaaS platform. The method specifically includes:
[0052] S101: Presenting a configuration page of a first application.
[0053] In the embodiment of the present application, the first application may be an application in the aPaaS platform. That is, the first application may be understood as an application built using the functions and integrated services provided by the aPaaS platform, for example, the first application may be a customer relationship management (CRM) application, a human capital management (HCM) application, an enterprise resource planning (ERP) application, or other business-related applications.
[0054] Specifically, under normal circumstances, the aPaaS platform does not provide AI (such as natural language processing) capabilities. Therefore, the first application created on the 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.
[0055] The configuration page of the first application can be understood as a page provided by the aPaaS platform for configuring the functions related to the first application. Generally, the configuration page of the first application can be a visual page, and the user (for example, the developer of the first application) can perform various operations related to application configuration, such as data model management, form design, workflow design, permission management, connector management, component addition, and application deployment, on the configuration page of the first application.
[0056] S102: In the configuration page of the first application, receiving an association operation for the second application.
[0057] In the embodiment of the present application, the second application may be an application in the language model application development platform. In other words, the second application may be understood as an application constructed using the language model application development platform.
[0058] Specifically, the language model application development platform provides natural language processing capabilities, for example, the language model application development platform can provide components related to natural language processing, or provide functions related to natural language processing. When creating an application in the language model application development platform, the user (for example, a developer of the second application) can use the natural language processing capabilities provided by the language model application development platform to enable the created application to perform natural language processing.
[0059] In some possible implementations, the language model application development platform can call at least one language model. The language model can be a model with natural language processing capabilities and can handle natural language tasks, such as a deep learning model trained with text data. In this way, an application created through the language model application development platform can call at least one language model during operation to perform natural language processing.
[0060] The embodiments of the present application do not limit the deployment methods of the aPaaS platform and the language model application development platform. In some possible implementations, the aPaaS platform and the language model application development platform can both be deployed in an office automation (OA) system. Among them, the OA system, which can also be referred to as a business system, a business platform, an office system, etc., can be understood as an office management system that integrates multiple functional modules. For example, a video conferencing function module, an instant messaging function module, a document function module, a schedule function module, etc. can be provided in the OA system. In other words, the aPaaS platform and the language model application development platform can be used as functional modules of the OA system to provide application development functions to users of the OA system (for example, enterprises). Users of the OA system can use the aPaaS platform or the language model application development platform to achieve rapid application development according to actual business needs.
[0061] In some other possible implementations, the aPaaS platform and the language model application development platform may also be independent software systems, and the aPaaS platform and the language model application development platform may communicate with each other. For example, the aPaaS platform and the language model application development platform may be independent applications (APPs).
[0062] The association operation for the second application can be understood as an operation for establishing an association relationship between the first application and the second application. In other words, the aPaaS platform provides a function for associating a first application without natural language processing capabilities with a second application with natural language processing capabilities, so as to introduce the natural language processing capabilities of the second application into the first application.
[0063] In a specific implementation, an association operation may be received in a configuration page of a first application, and a selection operation for a second application may be received from a plurality of applications in a language model application development platform, thereby receiving an association operation for the second application.
[0064] It is understandable that the language model application development platform may include multiple applications with natural language processing capabilities that can be associated with the first application. When a user (e.g., a developer of the first application) configures the first application, the association operation may be triggered first, and then a specific application to be associated with may be selected from the multiple applications in the language model application development platform.
[0065] In some embodiments, the aPaaS platform provides a component for establishing an association between an application in the aPaaS platform and an application in the language model application development platform. At this time, an add operation of the first component can be received in the configuration page of the first application. The first component can be used to establish an association between the first application and the application in the language model application development platform.
[0066] That is, the user (for example, the developer of the first application) can trigger the association operation by adding the first component in the first application. For example, the user can drag the first component to the first application in the configuration page of the first application to trigger the association operation quickly and conveniently.
[0067] S103: Establishing an association relationship between the first application and the second application according to the association operation.
[0068] In the embodiment of the present application, the association relationship between the first application and the second application can be used for the first application to call the second application. In other words, when there is an association relationship 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 capability of the second application.
[0069] After the association relationship between the first application and the second application is established, the first application and the second application may have at least a partially shared data model.
[0070] Among them, the data model can be used to describe the data structure and relationship of applications in the aPaaS platform or language model application development platform. The data model can include relational data model, hierarchical data model, object-oriented data model, document data model, etc.
[0071] The aPaaS platform or the language model application development platform can provide a form designer. Users can design forms through the form designer according to business needs. The form can be called a data object, and each data object can further include at least one data field. The data model can be used in conjunction with the form designer, and the data objects and data fields defined in the form can be mapped to the data model for storage.
[0072] During the operation of the application in the aPaaS platform or the language model application development platform, business data can be collected by executing the application business process. For example, when the application in the aPaaS platform or the language model application development platform is a CRM application, the business data may be data related to customer information. For another example, when the application in the aPaaS platform or the language model application development platform is an HCM application, the business data may be data related to employee information. For another example, when the application in the aPaaS platform or the language model application development platform is used to manage the operation failure of a system, the business data may be data related to system failure information.
[0073] The data model can be used to store business data recorded by applications in the aPaaS platform or the language model application development platform. For a first application and a second application having an associated relationship, the first application and the second application can share the data model to achieve data sharing.
[0074] In this way, for the first application in the 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, by associating the first application with the second application, the first application can use the AI capabilities of the second application, thereby realizing the AI of the first application.
[0075] In this method, for the first application in the aPaaS platform that does not have AI capabilities, an association relationship is established between the second application in the language model application development platform and the first application. Without rebuilding the first application, the natural language processing capability of the second application is introduced into the first application, thereby improving the user's efficiency in using the first application.
[0076] The above describes the configuration process of the first application in the aPaaS platform, and the following describes the running process of the first application.
[0077] See also Figure 2 The flowchart of an application running method provided in an embodiment of the present application is shown, and the method can be applied to a first application, and the first application is an application in an aPaaS platform. The method specifically includes:
[0078] S201: In an application page of a first application, receiving request information representing natural language content.
[0079] The application page of the first application can be understood as a page displayed to the user during the operation of the first application. Request information generally refers to information input by the user to express a specific instruction.
[0080] In the embodiment of the present application, the user is supported to input request information representing natural language content in the application page of the first application. The user may be a user of the first application (for example, an administrator of the first application), and the request information may represent natural language content. In other words, the user may input request information by inputting natural language in the application page during the use of the first application.
[0081] The request information may indicate the information processing type and the specific data processing scope. Specifically, the request information may include at least one of the following: a request to analyze the first target data in the first application, a request to edit the second target data in the first application, and a request to navigate the target application page in the first application.
[0082] Among them, in the request for analyzing the first target data in the first application, the information processing type may be data analysis, such as growth trend analysis, distribution analysis, data type analysis, etc., and the data processing scope may be the first target data.
[0083] Although the aPaaS platform includes a BI engine, developers can use the BI engine to perform data analysis on the business data recorded by the first application and present the visual results in the application page. However, the data analysis implemented by the developer using the BI engine is determined during the configuration process of the first application. In other words, the user can only view the visual results of the data analysis set up using the BI engine. Therefore, the embodiment of the present application supports the user of the first application to express data analysis requirements by inputting request information. In this way, the user of the first application is not limited to the data analysis functions determined by the BI engine in the first application, and can perform rich, flexible, and multi-type data analysis functions.
[0084] In the request for editing the second target data in the first application, the information processing type may be data editing, such as data modification, data filling, etc., and the data processing scope may be the second target data.
[0085] During the operation of the first application, the user of the first application (for example, the administrator of the first application) can manually edit the business data recorded by the first application, such as adding certain business data to the form of the first application, or modifying certain business data. However, the above data editing requires manual operation by the user of the first application. Usually, the user of the first application needs to first find the form where the data to be edited is located, and then perform specific data editing operations, which is cumbersome. Therefore, the embodiment of the present application supports the user of the first application to express data editing requirements by inputting request information. In this way, there is no need for the user of the first application to manually edit the data, and an automatic and fast data editing function is realized.
[0086] In the request for navigating the target application page in the first application, the information processing type may be page navigation, such as page jump, page positioning, etc., and the data processing scope may be the target application page.
[0087] For a first application with a complex business process, the first application usually includes a large number of application pages. When the user of the first application needs to enter a specific application page, or needs to perform a specific function, but cannot locate the application page corresponding to the specific function, it is usually necessary to search repeatedly in a large number of application pages, and the interaction cost is high. Therefore, the embodiment of the present application supports the user of the first application to express page navigation requirements by inputting request information. In this way, the user of the first application does not need to manually search for the application page, and automatic navigation of the application page is achieved, reducing the interaction cost.
[0088] S202: Calling a second application to perform natural language processing on the request information to determine response information of the request information.
[0089] 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. In other words, the second application has natural language processing capabilities, and through the association between the first application and the second application, the natural language processing capabilities of the second application are introduced into the first application.
[0090] In specific implementation, 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, determine the reply information of the request information in combination with the intermediate processing results returned by the second application, or directly receive the reply information of the request information returned by the second application.
[0091] Different information processing types have different corresponding processing flows, which are described below respectively.
[0092] In some embodiments, the request information includes a request for analyzing the first target data in the first application. Figure 3A As shown, the request information is sent to the second application, and a data analysis statement for the first target data returned by the second application is received. The first application executes the data analysis statement to obtain the first target data, and 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.
[0093] That is, when the request information is a request for analyzing the first target data in the first application, the reply information may be the data analysis result of the first target data, for example, the data analysis result including text and charts. Since the second application cannot directly obtain the specific value of the first target data that needs to be analyzed, the process of determining the reply information may include: using the natural language processing capability of the second application to generate data analysis statements, execute data analysis statements, obtain the first target data, use the second application to perform data analysis on the first target data, and determine the data analysis result of the first target data.
[0094] The data analysis statement can also be called a structured query language (SQL) statement. The first application executes the data analysis statement to obtain the first target data required for the data analysis requirement indicated by the request information from the recorded business data. In this way, the natural language processing capability and data analysis capability of the second application are used to perform data analysis on the first target data to generate data analysis results that meet the data analysis requirements.
[0095] In some other embodiments, the request information includes a request to edit the second target data in the first application. Figure 3B As shown, the request information is sent to the second application, and the editing instruction for the second target data in the first application returned by the second application is received. The first application executes the editing instruction to determine the editing result of the second target data.
[0096] That is to say, when the request information is a request to edit the second target data in the first application, the reply information may be the editing result of 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 that needs to be edited, and can generate editing instructions by performing natural language processing on the request information, such as an editing instruction representing adding a certain value to a certain data field, or an editing instruction representing modifying a certain data field to another value. Therefore, the process of determining the reply information may include: using the natural language processing capability of the second application to generate editing instructions, execute editing instructions, and obtain editing results.
[0097] In some other embodiments, the request information includes a request to navigate to a target application page in the first application. Figure 3C As shown, the request information is sent to the second application, and the page information of the target application page in the first application returned by the second application is received.
[0098] That is, when the request information is a request for navigation to the target application page in the first application, the reply information can be the 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, and can determine the page information of the target application page by performing natural language processing on the request information. Therefore, the process of determining the reply information can be: using the natural language processing capability of the second application to generate the page information of the target application page.
[0099] S203: Presenting reply information to the request information on the application page of the first application.
[0100] After the reply information of the request information is determined, the reply information can be presented in the application page of the first application. In this way, a round of dialogue of inputting the request information and generating the reply information is completed in the first application.
[0101] In some embodiments, the request information and the reply information may be presented in a dialog window. The dialog window may be understood as an interface for human-computer dialogue in the first application. The dialog window may have different presentation forms. For example, the dialog window may be presented in parallel with the application page of the first application, or, for another example, the dialog window may be presented in the form of a floating window component suspended above the application page of the first application.
[0102] 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 capability of the second application is introduced into the first application. In this way, when the user uses the first application, he can have a human-computer dialogue in the application page of the first application, so that the first application has AI capabilities and improves the use efficiency of the first application.
[0103] The foregoing describes the configuration process of the first application and the operation process of the first application. In the present application, the first application and the second application are associated with each other. The following describes the creation process and the operation process of the second application.
[0104] See also Figure 4 The flowchart of an application creation method provided in an embodiment of the present application is shown. The method can be applied to a language model application development platform. The language model application development platform provides natural language processing capabilities. The method specifically includes:
[0105] S401: Receive a creation operation for a second application.
[0106] The creation operation for the second application can be understood as an operation of creating the second application in the language model application development platform, and the second application can be used to establish an association relationship with the first application, and the first application is an application in the aPaaS platform. In other words, the second application can be understood as an application created in the language model application development platform to be associated with the first application.
[0107] In the embodiment of the present application, the aPaaS platform provides a creation entry for the second application. In specific implementation, a creation operation for the second application can be received in the configuration page of the first application.
[0108] In other words, when a user (eg, a developer of a first application) is configuring the first application, a second application to be associated with the first application can be created directly through the configuration page of the first application in the aPaaS platform.
[0109] 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 only through the configuration page of the first application, which simplifies the application creation operation.
[0110] S402: Presenting a configuration page of a second application.
[0111] In an embodiment of the present application, the configuration page can be 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.
[0112] The data model corresponding to at least one information processing type can be understood as a data model that can be processed under the information processing type. In other words, the user can configure different information processing types for the second application and configure different data ranges for each information processing type to meet diverse business needs.
[0113] S403: Receive a configuration operation triggered in the configuration page, and create a second application according to the configuration operation.
[0114] Specifically, receiving the configuration operation triggered in the configuration page may include: receiving a selection operation of an information processing type, and presenting data objects and / or data fields 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.
[0115] That is, the configuration operation can be divided into two levels of configuration: first, the user can select the information processing type of the second application, and then the user can select the target data object and / or target data field, which constitutes a data model corresponding to the information processing type.
[0116] After the user completes the configuration operation, a second application is established in the language model application development platform according to the information processing type carried by the configuration operation and the data model corresponding to the information processing type, so that the second application has the natural language processing capability corresponding to the information processing type.
[0117] In the embodiment of the present application, it is also supported to adjust the application information of the application in the language model application development platform. Specifically, in the language model application development platform, the 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 in the multiple applications, the application information of the target application is modified.
[0118] Among them, the application information of the application in the language model application development platform can be understood as information related to the AI capabilities of the application in the language model application development platform. In other words, users can make corresponding adjustments to the AI capabilities of the application in the language model application development platform based on actual business needs.
[0119] In some embodiments, in response to a new addition operation on a first information processing type of a target application among multiple applications, the first information processing type is added to the target application. In other words, the target application does not originally have the AI capability corresponding to the first information processing type, and through the editing operation on the target application, the first information processing type is added to the target application to enrich the AI capability of the target application.
[0120] In other embodiments, in response to an adjustment operation on the second information processing type of a target application among multiple applications, a prompt template matching the second information processing type is adjusted. In other words, the target application originally has an AI capability corresponding to the second information processing type, and through an editing operation on the target application, the prompt template is adjusted to improve the accuracy under the second information processing type.
[0121] In this method, a second application is created in a language model application development platform to be associated with a first application in an aPaaS platform. By configuring an information processing type and a data model that matches the information processing type, after an association relationship between the first application and the second application is established, the first application and the second application can share part of the data model, thereby introducing the natural language processing capability of the second application into the first application.
[0122] See also Figure 5 The flowchart of an application running method provided in an embodiment of the present application is shown. The method can be applied to a second application, where the second application is an application in a language model application development platform. The language model application development platform provides natural language processing capabilities. The method specifically includes:
[0123] S501: Receive request information representing natural language content sent by a first application.
[0124] The request information can be understood as information input by the user during the operation of the first application and used to express a specific instruction. The first application is an application in the aPaaS platform, and the first application has an association relationship with the second application.
[0125] Since the first application is associated with the second application, the first application does not have natural language processing capabilities, but the second application has natural language processing capabilities. Therefore, the second application can receive request information representing natural language content and perform natural language processing on the request information.
[0126] S502: Perform natural language processing on the request information using a language model to generate an intermediate processing result and / or reply information of the request information.
[0127] Specifically, the natural language processing capability provided by the language model application development platform can be implemented by calling the language model. In other words, the second application in the language model application development platform can perform natural language processing on the request information by calling the language model.
[0128] In some possible implementations, the second application may extract metadata information from the request information, determine a prompt template that matches the information processing type based on the information processing type indicated by the request information, and 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 reply information of the request information returned by the language model.
[0129] The metadata information may include information related to data objects and / or data fields. The information related to data objects and / or data fields may include object names of data objects, field names of data fields, description information of data objects, description information of data fields, description information of relationships between multiple data objects, description information of relationships between multiple data fields, etc.
[0130] Different information processing types correspond to different prompt templates. The prompt information (prompt) generated based on the prompt template matching the information processing type can be used to instruct the language model to perform natural language processing on the request information. In other words, through the prompt information, the language model can obtain information related to the data object and / or data field, the information processing type and the specific information processing requirements. Combined with the prompt capability of the prompt information, the language model can generate intermediate processing results and / or reply information of the request information.
[0131] Since the request information can represent different information processing types, and different information processing types can have different processing flows, the second application can generate an intermediate processing result or directly generate reply information of the request information after performing natural language processing on the request information using the language model.
[0132] In some embodiments, the request information is a request for analyzing the first target data in the first application. At this time, the second application uses a language model to perform natural language processing on the request information to generate an intermediate processing result. The intermediate processing result may include a data analysis statement for the first target data.
[0133] like Figure 3A As shown, after the second application extracts metadata information from the request information, it generates prompt information, sends the prompt information to the language model, and the language model returns a data analysis statement to the second application.
[0134] Furthermore, considering that the data model types of the first application and the second application may be different, after the second application generates an intermediate processing result, that is, after the second application receives the data analysis statement returned by the language model, the data analysis statement can also be converted into a format that matches the data model type of the first application.
[0135] 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 subsequent 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.
[0136] In other embodiments, the request information is a request to edit the 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 to generate an intermediate processing result. The intermediate processing result may include editing instructions for the second target data in the first application.
[0137] like Figure 3B As shown, after the second application extracts metadata information from the request information, it generates prompt information, sends the prompt information to the language model, and the language model returns the editing instruction to the second application.
[0138] Furthermore, the user can also confirm or modify the editing instructions to ensure that the editing instructions meet the user's data editing needs.
[0139] In some other embodiments, the request information is a request for navigation 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 to generate reply information of the request information. The reply information of the request information may include page information of the target application page in the first application.
[0140] like Figure 3C As shown, after the second application extracts the metadata information from the request information, it generates prompt information and sends the prompt information to the language model, and the language model returns the page information of the target application page to the second application.
[0141] S503: Send the intermediate processing result and / or reply information of the request information to the first application.
[0142] Taking into account the data permission issue, when the request information is a request for analysis of the first target data in the first application, the second application can return the data analysis statement and the requester identity carried in the request information to the first application, so that the first application can execute the data analysis statement as the requester who sent the request information (i.e., the user of the first application) to obtain the first target data, thereby avoiding data acquisition failure due to data permissions.
[0143] 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) to complete the data editing and avoid data editing failures due to data permissions.
[0144] In this method, since the first application in the aPaaS platform is associated with the second application in the language model application development platform, the AI capability of the second application is used to perform natural language processing on the request information entered by the user in the first application, and the generated intermediate processing results or reply information are returned to the first application, thereby realizing the intelligent operation of the first application.
[0145] The following will describe the pages related to the first application and the second application in the embodiment of the present application in combination with specific application scenarios.
[0146] like Fig. 6A As shown, in the aPaaS platform, the configuration page of the first application (not shown in the figure) can provide a creation entry 601 for the second application. In the creation entry 601 of the second application, introduction information related to the language model application and a creation control 602 are displayed, and the user can trigger the creation control 602 to create the second application.
[0147] like Figure 6B As shown, the aPaaS platform provides a first component 604 for establishing an association relationship between an application in the aPaaS platform and an application in the language model application development platform. The user can add the first component 604 by dragging in the configuration page 603 of the first application. Further, after the user adds the first component 604 to the first application, an area 605 for establishing an association relationship may be presented in the configuration page 603 of the first application. The user can select a second application from multiple applications in the language model application development platform in the area 605 for establishing an association relationship to establish an association relationship between the first application and the second application.
[0148] like Figure 6C As shown, the user can create a second application in the second application configuration page 606. For example, the user can select an avatar of the second application, set a name for the second application, select an information processing type, and select a data model corresponding to the information processing type in the second application configuration page 606.
[0149] like Fig.6DAs shown, after the association relationship between the first application and the second application is established, the AI capability of the second application is introduced into the first application, and the user of the first application can conduct a human-computer dialogue in the application page 607 of the first application. Specifically, a dialogue window 608 can be presented in the form of a floating window component in the application page 607 of the first application, and the user of the first application can enter request information in the dialogue window 608, for example, "this year's customer distribution", and the first application uses the second application to perform natural language processing on the request information, and determines the reply information of the request information based on the intermediate processing result or reply information returned by the second application, and presents the reply information in the dialogue window 608. For example, the reply information can be information including a distribution map of the industry to which the customer belongs, so as to realize a round of human-computer dialogue.
[0150] In the embodiment of the present application, the first application developed by the aPaaS platform can only view and analyze data through a graphical user interface (GUI). After establishing the association between the first application and the second application, the AI capability is introduced into the first application without modifying the original business process of the first application. The user of the first application can complete information processing through a conversational user interface (CUI), enriching the way users use the first application, reducing the difficulty of use, and improving the efficiency of use. In addition, it supports users to customize and adjust the information processing type of the second application, so that the second application can better meet the business needs of the first application.
[0151] Combination of the above Figure 1 Figure 6 provides a detailed introduction to the application configuration method, application running method and application creation method provided in the embodiment of the present application. The system and device provided in the embodiment of the present application will be introduced in conjunction with the accompanying drawings below.
[0152] See also Figure 7 The schematic diagram of the structure of the application configuration system shown in the figure is that the system 70 is deployed on the application platform as a service aPaaS platform, and the system 70 includes:
[0153] A presentation module 701 is used to present a configuration page of a first application, where the first application is an application in the aPaaS platform;
[0154] A receiving module 702 is used to receive an associated operation for a second application in a configuration page of the first application; wherein the second application is an application in a language model application development platform, and the language model application development platform provides natural language processing capabilities;
[0155] The establishing module 703 is used to establish an association relationship between the first application and the second application according to the association operation, and the association relationship is used for the first application to call the second application.
[0156] The application configuration system 70 according to the embodiment of the present application may correspond to executing the application configuration method described in the embodiment of the present application, and the above and other operations and / or functions of each module / unit of the application configuration system 70 are respectively to implement Figure 1 For the sake of brevity, the corresponding processes of each method in the illustrated embodiment are not described in detail here.
[0157] See also Figure 8 The schematic diagram of the structure of the application running system shown in the figure, the system 80 is deployed in the first application, the first application is an application in the application platform as a service aPaaS platform, and the system 80 includes:
[0158] The receiving module 801 is used to receive request information representing natural language content in the application page of the first application;
[0159] A determination module 802 is used to call 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 provides natural language processing capabilities, and the second application is associated with the first application;
[0160] The presentation module 803 is used to present the reply information of the request information in the application page of the first application.
[0161] The application running system 80 according to the embodiment of the present application may correspond to executing the application running method described in the embodiment of the present application, and the above and other operations and / or functions of each module / unit of the application running system 80 are respectively to implement Figure 2 For the sake of brevity, the corresponding processes of each method in the illustrated embodiment are not described in detail here.
[0162] See also Fig. 9 The schematic diagram of the structure of the application creation system shown in FIG. 9 is deployed on a language model application development platform, and the language model application development platform provides natural language processing capabilities. The system 90 includes:
[0163] The receiving module 901 is used to receive a creation operation for a second application; wherein the second application is used to establish an association relationship with the first application, and the first application is an application in an application platform as a service aPaaS platform;
[0164] A presentation module 902 is used to present 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 range corresponding to the at least one information processing type;
[0165] The creation module 903 is used to receive the configuration operation triggered in the configuration page, and create the second application according to the configuration operation.
[0166] The application creation system 90 according to the embodiment of the present application may correspond to executing the application creation method described in the embodiment of the present application, and the above and other operations and / or functions of each module / unit of the application creation system 90 are respectively to implement Figure 4 For the sake of brevity, the corresponding processes of each method in the illustrated embodiment are not described in detail here.
[0167] See also Fig.10 The schematic diagram of the structure of the application running system shown in the figure, the system 100 is deployed in the second application, the second application is an application in the language model application development platform, the language model application development platform provides natural language processing capabilities, the system 100 includes:
[0168] The receiving module 1001 is used to receive request information representing natural language content sent by a first application; wherein the first application is an application in an application platform as a service aPaaS platform, and the first application is associated with the second application;
[0169] A generating module 1002 is used to perform natural language processing on the request information using a language model to generate an intermediate processing result and / or reply information of the request information;
[0170] The sending module 1003 is used to send the intermediate processing result and / or the reply information of the request information to the first application.
[0171] The application running system 100 according to the embodiment of the present application may correspond to executing the method described in the embodiment of the present application, and the above and other operations and / or functions of each module / unit of the application running system 100 are respectively to implement Figure 5 For the sake of brevity, the corresponding processes of each method in the illustrated embodiment are not described in detail here.
[0172] The present application also provides an electronic device. The electronic device is specifically used to implement Figure 7 The functions of the application configuration system 70 in the embodiment shown may be used to implement the following Figure 8 In the embodiment shown, the function of the application operation system 80 may be used to implement the following Fig. 9 In the embodiment shown, the function of the application creation system 90 may be used to implement the following Fig.10The functions of the application running system 100 are shown in the embodiment shown.
[0173] Fig.11 A schematic diagram of the structure of an electronic device 1100 is provided. Fig.11 As shown, 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.
[0174] The bus 1101 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.11 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0175] The processor 1102 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).
[0176] The communication interface 1103 is used for communicating with the outside. For example, the communication interface 1103 can be used for communicating with a terminal.
[0177] The memory 1104 may include a volatile memory, such as a random access memory (RAM). The memory 1104 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).
[0178] The memory 1104 stores executable codes, and the processor 1102 executes the executable codes to perform the aforementioned application configuration method, application running method, or application creation method.
[0179] The following description is made by taking the processor 1102 executing the application configuration method as an example. Figure 5 In the case of the embodiment shown, and Figure 7 When each module or unit of the application configuration system 70 described in the embodiment is implemented by software, the execution Figure 7 The software or program code required for the functions of each module / unit in the application may be partially or completely stored in the memory 1104. The processor 1102 executes the program code corresponding to each unit stored in the memory 1104 to perform the aforementioned application configuration method.
[0180] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by the computing device or a data storage device such as a data center that contains one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute the above-mentioned application configuration method applied to the application configuration system 70, or execute the above-mentioned application running method applied to the application running system 80, or execute the above-mentioned application creation method applied to the application creation system 90, or execute the above-mentioned application running method applied to the application running system 100.
[0181] The embodiment of the present application further provides a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the process or function described in the embodiment of the present application is generated in whole or in part.
[0182] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. 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, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.
[0183] When the computer program product is executed by a computer, the computer executes any of the aforementioned application configuration method, application running method, or application creation method. The computer program product may be a software installation package, and when any of the aforementioned application configuration method, application running method, or application creation method is needed, the computer program product may be downloaded and executed on a computer.
[0184] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to each embodiment of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0185] The units involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the unit / module does not, in some cases, constitute a limitation on the unit itself.
[0186] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0187] In the context of the present application embodiment, machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable medium can include but is not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.
[0188] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the system or device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0189] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers 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 mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0190] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0191] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
[0192] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be 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 the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. An application configuration method, characterized in that: Applied to an application platform as a service (aPaaS) platform, the method comprises: Presenting a configuration page of a first application, where the first application is an application in the aPaaS platform; In a 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 natural language processing capabilities; According to the association operation, an association relationship between the first application and the second application is established, and the association relationship is used for the first application to call the second application.
2. The method according to claim 1, characterized in that The first application and the second application have at least partially shared data models.
3. The method according to claim 1, characterized in that The receiving, in the configuration page of the first application, an association operation for the second application includes: In a configuration page of the first application, an association operation is received; and a selection operation for a second application is received from a plurality of applications in the language model application development platform.
4. The method according to claim 3, characterized in that The receiving, in the configuration page of the first application, an associated operation includes: In the configuration page of the first application, an adding operation of a first component is received, and the first component is 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, characterized in that: Applied to a first application, the first application being an application in an application platform as a service (aPaaS) 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 provides natural language processing capabilities, and the second application is associated with the first application; In the application page of the first application, reply information of the request information is presented.
6. The method according to claim 5, characterized in that The request information includes at least one of the following: 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 to a target application page in the first application.
7. The method according to claim 5, characterized in that The request information includes a request for analyzing the first target data in the first application, and the calling of the second application performs natural language processing on the request information to determine the response information of the request information, including: Sending the request information to a second application, and receiving a data analysis statement for the first target data returned by the second application; Execute the data analysis statement to obtain the first target data; The first target data is sent to the second application, and a data analysis result of the first target data returned by the second application is received.
8. The method according to claim 5, characterized in that The request information includes a request for editing the second target data in the first application, and the calling of the second application performs natural language processing on the request information to determine the reply information of the request information, including: 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; The editing instruction is executed to determine the editing result of the second target data.
9. The method according to claim 5, characterized in that The request information includes a request for navigating a target application page in the first application, and the calling of the second application performs natural language processing on the request information to determine response information of the request information, including: The request information is sent to the second application, and page information of the target application page in the first application returned by the second application is received.
10. A method for creating an application, characterized in that: Applied to a language model application development platform, the language model application development platform provides natural language processing capabilities, the method comprising: Receiving a creation operation for a second application; wherein the second application is used to establish an association relationship with the first application, and the first application is an application in an application platform as a service aPaaS 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; A configuration operation triggered in the configuration page is received, and the second application is created according to the configuration operation.
11. The method according to claim 10, characterized in that The receiving a creation operation for the second application includes: In the configuration page of the first application, a creation operation for the second application is received.
12. The method according to claim 10, characterized in that The receiving a configuration operation triggered in the configuration page includes: receiving a selection operation of an information processing type; and, The data objects and / or data fields included in the first application are presented, a selection operation for a target data object among the data objects is received, and / or a selection operation for a target data field among the data fields is received.
13. The method according to claim 10, characterized in that The method further comprises: Presenting application information of multiple applications in the language model application development platform; In response to an editing operation on a target application among the multiple applications, application information of the target application is modified.
14. The method according to claim 13, characterized in that The modifying the application information of the target application in response to the editing operation on the target application among the multiple applications includes: In response to a new adding operation on a first information processing type of a target application among the multiple applications, adding the first information processing type to the target application; In response to an adjustment operation on a second information processing type of a target application among the multiple applications, a prompt template matching the second information processing type is adjusted.
15. A method for running an application, characterized in that: Applied to a second application, the second application is an application in a language model application development platform, the language model application development platform provides natural language processing capabilities, the method includes: Receiving request information representing natural language content sent by a first application; wherein the first application is an application in an application platform as a service (aPaaS) platform, and the first application is associated with the second application; Performing natural language processing on the request information using a language model to generate an intermediate processing result and / or reply information to the request information; The intermediate processing result and / or reply information of the request information is sent to the first application.
16. The method according to claim 15, characterized in that The using a language model to perform natural language processing on the request information to generate an intermediate processing result and / or reply information of the request information includes: Extracting metadata information from the request information, wherein the metadata information includes information related to a data object and / or a data field; Determining, according to the information processing type indicated by the request information, a prompt template matching the information processing type; Generate prompt information based at least on the metadata information and a prompt template matching the information processing type, wherein the prompt information is used to indicate a process of performing natural language processing on the request information by a language model; The prompt information is sent to the language model, and an intermediate processing result and / or reply information of the request information returned by the language model is received.
17. The method according to claim 15, characterized in that When the request information is a request for analyzing first target data in the first application, the intermediate processing result includes a data analysis statement for the first target data; When the request information is a request for editing the second target data in the first application, the intermediate processing result includes an editing instruction for the second target data in the first application; When the request information is a request for navigating a target application page in the first application, the response information of the request information includes page information of the target application page in the first application.
18. The method according to claim 17, characterized in that The request information is a request for analyzing the first target data in the first application, the intermediate processing result includes a data analysis statement for the first target data, and after the natural language processing is performed on 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 includes: The data analysis statement is converted into a format matching the data model type of the first application.
19. An electronic device, characterized in that: The electronic device comprises a processor and a memory; The processor is used to execute instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1 to 4, or executes the method as described in any one of claims 5 to 9, or executes the method as described in any one of claims 10 to 14, or executes the method as described in any one of claims 15 to 18.
20. A computer-readable storage medium, characterized in that: The method comprises instructions, wherein the instructions instruct the electronic device to execute the method as claimed in any one of claims 1 to 4, or execute the method as claimed in any one of claims 5 to 9, or execute the method as claimed in any one of claims 10 to 14, or execute the method as claimed in any one of claims 15 to 18.
Citation Information
Patent Citations
Business data processing method and device and computer equipment
CN117076881A
Data processing method and device, medium and computing equipment
CN117539893A
Enterprise data visual analysis method, device, equipment and medium
CN118245543A
Method and device for creating digital assistant, equipment and storage medium
CN118410133A
Cited By
Application configuration method, application running method, application creation method, and device and medium
WO2026026008A1
