Application creation method and apparatus, device, and storage medium

By adding functional instances to the target application and using the model to perform data operations, the terminal user's natural language query is supported, and the problem of low query service quality in the existing technology is solved, efficient and rapid application creation and data processing is achieved, and user experience is improved.

WO2025107890A1PCT designated stage expired Publication Date: 2025-05-30BEIJING ZITIAO NETWORK TECH CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/122419
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-11-22
Filing Date
2024-09-29
Publication Date
2025-05-30

AI Technical Summary

Technical Problem

The prior art is difficult to improve the quality of query services applied in terminal devices, especially when users perform functional operations such as adding, deleting, modifying, and checking through natural language. The traditional UI form input method is costly and has poor experience.

Method used

By adding functional instances to the target application, using the model to perform data operations, supporting end-user natural language queries, and processing user queries through digital assistants, generating and presenting corresponding forms to achieve data operations.

Benefits of technology

It realizes efficient and rapid application creation and data processing, supports users to operate data through natural language, and improves the quality of query services and user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024122419_30052025_PF_FP_ABST
    Figure CN2024122419_30052025_PF_FP_ABST
Patent Text Reader

Abstract

Embodiments of the present disclosure provide an application creation method and apparatus, a device, and a storage medium. The method comprises: receiving a function adding request for adding a function for a target application; receiving first configuration information for a first function, wherein the first configuration information at least indicates the type of the first function and first data that is associated with the first function, and the first function is configured to at least call a first model to execute task processing based on the first data; and adding the first function in the target application on the basis of the first configuration information. Thus, creation of a function required in the target application can be completed, so that efficient and rapid application creation can be realized.
Need to check novelty before this filing date? Find Prior Art

Description

Method, apparatus, device and storage medium for application creation

[0001] This application claims priority to the Chinese invention patent application entitled “Methods, Apparatus, Devices and Storage Medium for Application Creation” filed on November 22, 2023, with application number 202311570251.9, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for creating applications. Background Art

[0003] With the development of information technology, various terminal devices can provide people with a variety of services in work and life. Applications that provide these services can be deployed on these devices. These applications present content and interact with users through their user interfaces, meeting their needs. In some cases, users may initiate queries within applications. Therefore, improving the quality of query services provided to users is a key concern.

[0004] Summary of the Invention

[0005] In a first aspect of the present disclosure, a method for creating an application is provided. The method includes: receiving a function addition request for adding a function to a target application; receiving first configuration information for a first function, the first configuration information indicating at least a type of the first function and first data associated with the first function, the first function being configured to at least invoke a first model to perform task processing based on the first data; and adding the first function to the target application based on the first configuration information.

[0006] In a second aspect of the present disclosure, a method for data processing is provided. The method includes: in creating a target application, in response to a first add request for a data operation function, providing a first configuration page for the data operation function, wherein the data operation function is configured to provide at least one type of data operation; receiving first function configuration information for the data operation function via the first configuration page, wherein the first function configuration information at least indicates at least a portion of a first data object; and creating a first function instance of the data operation function in the target application based on the first function configuration information, wherein the first function instance is configured to perform one or more types of data operations of at least one type on at least a portion of the first data object.

[0007] In a third aspect of the present disclosure, a method for data processing is provided. The method includes: receiving a user query for a target application; processing the user query using a first function instance in the target application, the first function instance being configured to perform one or more types of data operations on at least a portion of a first data object; and presenting a form corresponding to the user query, the form including at least one field in the first data object associated with the user query.

[0008] In a fourth aspect of the present disclosure, there is provided an apparatus for application creation, comprising: an addition request receiving module configured to receive a function addition request for adding a function to a target application; a configuration information receiving module configured to receive first configuration information for a first function, the first configuration information at least indicating a type of the first function and first data associated with the first function, the first function being configured to at least call a first model to perform task processing based on the first data; and a first function adding module configured to add the first function in the target application based on the first configuration information.

[0009] In a fifth aspect of the present disclosure, a device for data processing is provided. The device includes: a page configuration module configured to, in creating a target application, provide a first configuration page for a data operation function in response to a first add request for the data operation function, wherein the data operation function is configured to be able to provide at least one type of data operation; a configuration information receiving module configured to receive first function configuration information for the data operation function via the first configuration page, wherein the first function configuration information at least indicates at least a portion of a first data object; and a function instance creation module configured to create a first function instance of the data operation function in the target application based on the first function configuration information, wherein the first function instance is configured to perform one or more types of data operations of at least one type on at least a portion of the first data object.

[0010] In a sixth aspect of the present disclosure, a device for data processing is provided. The device includes: a user query receiving module configured to receive a user query for a target application; a processing module configured to process the user query using a first function instance in the target application, the first function instance being configured to perform one or more types of data operations on at least a portion of a first data object; and a form presentation module configured to present a form corresponding to the user query, the form including at least one field in the first data object associated with the user query.

[0011] In a seventh aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the electronic device to perform the method of the first aspect, and / or the method of the second aspect, and / or the method of the third aspect.

[0012] In an eighth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the medium, and when the computer program is executed by a processor, the computer program implements the method of the first aspect, and / or the method of the second aspect, and / or the method of the third aspect.

[0013] In a ninth aspect of the present disclosure, a computer program product is provided. The computer program product is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method of the first aspect, and / or the method of the second aspect, and / or the method of the third aspect.

[0014] It should be understood that the content described in this section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0016] FIG1A shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0017] 1B to 1F illustrate schematic diagrams of example interfaces according to some embodiments of the present disclosure;

[0018] 2A to 2D illustrate schematic diagrams of example interfaces according to some embodiments of the present disclosure;

[0019] FIG3 shows a schematic diagram of an example interface according to some embodiments of the present disclosure;

[0020] FIG4A shows a flowchart of a process for application creation according to some embodiments of the present disclosure;

[0021] FIG4B shows a flowchart of a process for data processing according to other embodiments of the present disclosure;

[0022] FIG4C shows a flowchart of a process for data processing according to other embodiments of the present disclosure;

[0023] FIG5A shows a schematic structural block diagram of an apparatus for creating an application according to some embodiments of the present disclosure;

[0024] FIG5B shows a schematic structural block diagram of an apparatus for data processing according to some embodiments of the present disclosure;

[0025] FIG5C shows a schematic structural block diagram of an apparatus for data processing according to some embodiments of the present disclosure; and

[0026] FIG6 shows a block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION

[0027] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0028] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below.

[0029] Herein, unless explicitly stated otherwise, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0030] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0031] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the type, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and authorization should be obtained from relevant users in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.

[0032] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to the software or hardware such as the electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0033] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message may be sent to the relevant user in the form of a pop-up window, in which the prompt message may be presented in text form. Furthermore, the pop-up window may also include a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0034] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure. The activation of the digital assistant-related functions of the embodiment of the present disclosure, the data obtained, the processing and storage of the data, etc., shall all obtain the prior authorization of the user and other rights holders associated with the user, and shall comply with the provisions of relevant laws and regulations and the rules of agreement between rights holders.

[0035] As used herein, the term "model" can learn the association between corresponding inputs and outputs from training data, so that after training is completed, corresponding outputs can be generated for given inputs. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.

[0036] FIG1A illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. Environment 100 includes an application management platform 110, which can support the creation and / or execution of applications. In some embodiments, the portion of application management platform 110 that supports application creation can also be referred to as an application creation portion. In some embodiments, the portion of application management platform 110 that supports application execution can also be referred to as an application execution portion.

[0037] As shown in Figure 1A, the application creation part can provide a user 105 with an environment for creating and publishing applications. User 105 can be referred to as an application creation user or creator. In some embodiments, the application creation part can be a low-code platform that provides a collection of tools for application creation. The application creation part can support visual development of various types of applications, allowing developers to skip the manual coding process and speed up the application development cycle and cost. The application creation part can support any appropriate platform for users to develop one or more types of applications, for example, it can include a platform based on Application Platform as a Service (aPaaS). Such a platform can support users to efficiently develop applications and implement operations such as application creation and application function adjustment.

[0038] The application creation part can be deployed locally on the terminal device of user 105, and / or can be supported by a server-side device. For example, the terminal device of user 105 can run a client of the application creation part, which can support the interaction between the user and the application creation part provided by the server. In the case where the application creation part runs locally on the user's terminal device, user 105 can directly use the terminal device to interact with the local application creation part. In the case where the application creation part runs on the server-side device, the server-side device can realize the service provision of the client running in the terminal device based on the communication connection between the terminal device. The application creation part can present a corresponding page 130 to the user 105 based on the operation of the user 105 to output and / or receive information related to application creation to the user 105 and / or from the user 105.

[0039] In some embodiments, the application creation portion can be associated with a corresponding database, which stores the data or information required for the application creation process supported by the application creation portion. For example, the database can store the code and description information corresponding to each functional module used to make up the application. The application creation portion can also perform operations such as calling, adding, deleting, and updating the functional modules in the database. The database can also store operations that can be performed on different functional blocks. For example, in a scenario where an application is to be created, the application creation portion can call the corresponding functional blocks from the database to build the application.

[0040] In an embodiment of the present disclosure, the user 105 can create a target application 120 as needed in the application creation part and publish the target application 120. The target application 120 can be published to any appropriate application running part, as long as the application running part can support the operation of the target application 120. After publishing, the target application 120 can be used to be operated by one or more terminal users 145. The terminal user 145 can operate the target application 120 through an associated terminal device 146 and thereby interact with the application management platform 110. The terminal user 145 can be referred to as the terminal user of the target application 120. In some embodiments, the target application 120 may include or be implemented as a digital assistant 122.

[0041] The digital assistant 122 can be configured to have the ability to have intelligent conversations. In the example shown in Figure 1A, the digital assistant 122 can be integrated into the target application 120 and assist in executing task processing within the target application 120 as part of the target application 120. In other examples, the digital assistant 122 can be configured as an independently running application, such as a web application or other types of applications. In such an example, the digital assistant 122 and the target application 120 can be regarded as the same application. The digital assistant 122 is provided to assist users with various task processing needs in different applications and scenarios. During the interaction with the digital assistant 122, the user inputs an interactive message, and the digital assistant 122 provides a reply message in response to the user input. Generally, the digital assistant 122 can support users to input questions in natural language, and perform tasks and provide replies based on the understanding of natural language input and logical reasoning ability.

[0042] In some embodiments, digital assistant 122 can interact with end user 145 as a contact of end user 145. For example, digital assistant 122 can be implemented in an instant messaging (IM) application. Digital assistant 122 can interact with end user 145 in a single chat session with end user 145. In some embodiments, digital assistant 122 can interact with multiple users in a group chat session including multiple users.

[0043] For each terminal user 145, the client of the application running portion can present an interaction window 142 of the target application 120 or the digital assistant 122 in the client interface, such as a conversation window with the digital assistant 122. The terminal user 145 can enter a conversation message in the conversation window, and the target application 120 can determine a reply message of the digital assistant 122 based on the created configuration information and present it to the user in the interaction window 142. In some embodiments, depending on the configuration of the target application 120, the interaction message with the target application 120 can include messages in multimodal forms, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and the like.

[0044] Similar to the application creation part, the application running part can be deployed locally on the terminal device of each terminal user 145, and / or can be supported by a server-side device. For example, the terminal device of the terminal user 145 can run a client with the application running part, which can support the interaction between the user and the application running part provided by the server. In the case where the application running part runs locally on the user's terminal device, the terminal user 145 can directly use the terminal device to interact with the local application running part. In the case where the application running part runs on the server-side device, the server-side device can, based on the communication connection with the terminal device, implement service provision for the client running in the terminal device. The application running part can present the corresponding application page to the terminal user 145 based on the operation of the terminal user 145, so as to output and / or receive information related to the use of the application to the terminal user 145 and / or receive information from the terminal user 145.

[0045] In some embodiments, at least some of the functionality of the target application 120 and / or at least some of the functionality of the digital assistant 122 in the target application 120 can be implemented based on a model. During the creation or execution of the target application 120, one or more models 155, such as the capabilities of the models 155, can be invoked. In the target application 120, the digital assistant 122 can utilize the models 155 to understand user input and provide responses to the user based on the output of the models 155.

[0046] During the creation process, the application management platform 110 tests the target application 120 using the model 155 to ensure that the target application 120's operating results meet expectations. During operation, in response to various user operation requests of the target application 120, the application execution component may need to use the model 155 to determine the user's response results.

[0047] Although shown as being independent of the application management platform 110, one or more models 155 can run on the application management platform 110 or other remote servers. In some embodiments, the model 155 can be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model can be based on a language model (LM). A language model can have question-answering capabilities by learning from a large amount of corpus. The model 155 can also be based on other appropriate models.

[0048] The application management platform 110 can run on appropriate electronic devices. The electronic devices here can be any type of device with computing capabilities, including terminal devices or server devices. The terminal device can be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can, for example, include a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. In some embodiments, the management platform 110 can be implemented based on cloud services.

[0049] It should be understood that the structure and functionality of the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure. For example, although FIG1A illustrates a single user interacting with the application creation portion and a single user interacting with the application execution portion, in practice multiple users may access the application management platform 110 to each create a digital assistant, and each digital assistant may be used to interact with multiple users.

[0050] For application creators, how to efficiently and conveniently build applications with various functions for creating and updating applications, including data manipulation capabilities, is an issue that application creators are very concerned about.

[0051] In an embodiment of the present disclosure, an improved solution for application creation is provided. In this solution, the following steps are included: receiving a function addition request for adding a function to a target application; receiving first configuration information for a first function, the first configuration information at least indicating the type of the first function and first data associated with the first function, the first function being configured to at least call a first model to perform task processing based on the first data; and adding the first function to the target application based on the first configuration information. In this way, the user 105 can create various types of functions in the target application and associate corresponding data with these functions. These functions can perform task processing for the user 105 by calling the model based on the capabilities of artificial intelligence, thus enabling efficient and rapid application creation.

[0052] In the embodiment of the present disclosure, an improved data processing scheme is provided. In this scheme, it includes: in the creation of the target application, in response to the first addition request for the data operation function, providing a first configuration page for the data operation function, the data operation function is configured to be able to provide at least one type of data operation; receiving first function configuration information for the data operation function via the first configuration page, the first function configuration information at least indicating at least a part of the first data object; and based on the first function configuration information, creating a first function instance of the data operation function in the target application, the first function instance is configured to perform one or more types of data operations of at least one type on at least a part of the first data object. In this way, when creating the target application, one or more function instances can be independently created by the user 105 based on the data operation function, and each instance is associated with at least a part of a data object. This can support the user to complete the creation of the functions required in the target application by simply selecting the data object and configuring other function information as needed, so as to achieve efficient and fast application creation.

[0053] The following example illustrates a scenario to which the present disclosure is applicable. The following example is merely illustrative, and the embodiments of the present disclosure are not limited in this respect.

[0054] When following up on business opportunities and clients, a sales user needs an assistant to quickly record follow-up records for opportunities and clients. To enable this, the creator needs to create a target application. The creator needs to prepare a data object for opportunity follow-up records, specify the fields in the data object, define the field types, and provide field descriptions. The creator then enables the data manipulation feature in the target application and configures the feature as follows: Configure the data object to be created. Then, the creator enables the skill in the target application and completes debugging. The creator then publishes the target application.

[0055] After the target app is released, a sales user can initiate a conversation with the target app in a private or group chat, stating, "I visited customer XX today, and the follow-up record is: xxxxxxx." The target app then returns a form containing all fields in the data object that need to be updated. The form also contains the object values ​​identified from the user input. After the user confirms the details and completes the form, they click Submit. This completes the form submission, and the new record is added to the data object.

[0056] Some example embodiments of the present disclosure will be described in detail below with reference to the examples in the accompanying drawings. It should be understood that the pages shown in the accompanying drawings are merely examples, and a variety of page designs may exist. The various graphical elements in a page may have different arrangements and different visual representations, one or more elements may be omitted or replaced, and one or more other elements may also be present. The embodiments of the present disclosure are not limited in this respect.

[0057] 1B to 1F illustrate schematic diagrams of example interfaces during an application creation process according to some embodiments of the present disclosure.

[0058] In some embodiments, the application management platform 110 receives a function adding request for adding functions to the target application 120. The user 105 may add one or more functions to the target application 120, and the application management platform 110 may receive the function adding request from the user 105.

[0059] In some embodiments, the application management platform 110 receives first configuration information for a first function. The first configuration information indicates at least the type of the first function and first data associated with the first function. The first function is configured to at least invoke a first model to perform task processing based on the first data. The target application 120 may provide multiple types of functions for the user 105 to add, so the first configuration information needs to indicate the type of the first function. Furthermore, the first function requires first data for processing the first data.

[0060] In some embodiments, after receiving the function addition request, the application management platform 110 provides a function configuration page in response to receiving the function addition request. For example, in the diagram 101 shown in FIG1B , the application management platform 110 provides a function configuration page 123 in response to the user 105 clicking on the function 112.

[0061] In some embodiments, the application management platform 110 receives first configuration information via a function configuration page. As shown in FIG1B , the user 105 can click the add control 114 to add a first function to the target application 120. When adding a function, the user 105 needs to specify the type of the first function and the first data associated with the first function. The first function can utilize artificial intelligence capabilities to execute task processing based on the first data by invoking a first model.

[0062] In some embodiments, the application management platform 110 receives a selection of a first function type from a plurality of predetermined function types. The target application 120 may provide functions of the plurality of predetermined function types for the user 105 to add. The execution logic and the first model of the call of different types of functions may differ. The user 105 may select the type of the first function from the plurality of predetermined function types.

[0063] In some embodiments, the application management platform 110 receives first configuration information corresponding to the type of the first function in response to selecting the type of the first function. For example, the predetermined function types provided by the target application 120 include Type A, Type B, and Type C. If the user 105 selects Type A as the type of the first function, the application management platform 110 may receive first configuration information corresponding to Type A of the first function.

[0064] In some embodiments, the multiple predetermined function types include at least one of the following: data processing, question-and-answer, and data analysis. For example, the data processing function can automatically provide user 105 with services such as creating, deleting, updating, and querying data. The question-and-answer function can respond to user 105's questions and return corresponding results. For example, if the user asks "How can I quickly master a language?", the question-and-answer function can answer user 105's question based on information stored in the knowledge base. The data analysis function can mine and analyze data in the database to discover its meaning.

[0065] In some embodiments, the application management platform 110 receives a selection of a first data source from among the one or more data sources. The user 105 also needs to select a data source for the added function so that the added function performs task processing based on the data source. Therefore, the application management platform 110 receives the user 105's selection of the first data source from among the one or more data sources.

[0066] In some embodiments, the application management platform 110 provides options for one or more data objects in a first data source and receives a selection of a first data object from the one or more data objects as at least a portion of the first data. For example, in the schematic diagram 102 shown in FIG1C , the application management platform 110 provides a data source selection interface 124 in response to a user 105 clicking on Data & Knowledge 113. In the data source selection interface 124, the user can click on a data table 115 to select the data table as the first data source. After clicking on the data table 115, the application management platform 110 provides a data object selection page 126 and provides options for one or more data objects from the first data source on the data object selection page. For example, the application management platform 110 may provide a Reference xxx Shared Data 127 to allow the user 105 to reference shared data from other systems, or may provide a Quick Table Create Based on External System 128 to allow the user 105 to create a new data table. The application management platform 110 may then receive the selection of the first data object from the one or more data objects as at least a portion of the first data.

[0067] In some embodiments, the one or more data sources include at least one of the following types of data sources: data tables, analysis tables, knowledge bases, data streams, and term bases. For example, data tables are primarily used to store online business data and support operations such as creating, deleting, updating, and querying data by user 145. Analysis tables are primarily used in offline analysis scenarios; user 145 can only read data in analysis tables and cannot edit the data in them. A term base includes professional terms and their corresponding explanations. In some embodiments, the content in the term base can help machine learning better understand user intent.

[0068] In some embodiments, the first function of the application management platform 110 may have a corresponding first workflow. The first function may perform task processing in the form of a workflow.

[0069] In some embodiments, the application management platform 110 receives node configuration information for the first working node in response to a creation request for the first working node in the first workflow, where the node configuration information indicates the input parameters, output parameters, and the first operation to be performed of the first working node. A workflow may include multiple working nodes, and when the workflow runs to a specific working node, the operation corresponding to the working node is executed. For example, in the schematic diagram 103 shown in FIG1D , the user 105 can click on the start node 131 to configure the input parameters, and can also click on the end node 132 to configure the output parameters. And the user 105 can also configure the first operation to be performed, for example, the user 105 can configure the first operation to be performed in the first operation configuration page 133, and the first operation includes one of the following: calling the first model, a data processing operation based on the first data, the processing logic of the first working node, sending a notification message, and calling a function that has been created in the target application.

[0070] In some embodiments, the application management platform 110 adds a first function to the target application 120 based on the first configuration information.

[0071] In some embodiments, a group of functions including a first function has been added to the target application 120, and the application management platform 110 may also receive a function scheduling configuration that indicates the scheduling of the group of functions. User 105 may have added a group of functions including the first function to the target application 120, and the application management platform 110 may also receive the user 105's scheduling configuration for this group of functions. Based on this, the application management platform 110 can run the different functions in the target application 120 in a reasonable order, thereby improving coordination between the different functions.

[0072] In some embodiments, the application management platform 110 receives second configuration information for a plurality of work nodes in a second workflow, the second configuration information indicating that at least one of the plurality of work nodes is associated with one or more functions in the set of functions. The work nodes in the second workflow correspond to the one or more functions, and the second workflow defines a scheduling relationship between the functions.

[0073] In some embodiments, the application management platform 110 receives a prompt word, and when executing a processing request for a target application, the prompt word is provided to the second model to determine that at least one function in the set of functions is scheduled to execute the processing request. For example, in the schematic diagram 104 shown in Figure 1E, the user 105 can send a prompt word 134 to the application management platform 110. The content in the prompt word 134 is used to prompt the target application 120 of the function that needs to be executed. After receiving the prompt word, the application management platform 110 can provide the prompt word to the second model to determine that at least one function is scheduled to process the processing request for the target application 120. Based on this, the target application 120 can correctly schedule different functions based on its own intelligent capabilities to meet the user's processing request.

[0074] In some embodiments, the application management platform 110 may also provide a model configuration page, and receive a selection of at least one model via the model configuration page, and the at least one model is called when executing a processing request for the target application. For example, in the schematic diagram 106 shown in Figure 1F, the application management platform 110 provides a model configuration page 136 in response to the user 105 clicking on the model setting 135. Exemplarily, the user 105 can click on model A 137, so that the target application 120 calls model A to process the request. The user 105 can also click on model B 138, so that the target application 120 calls model B to process the request. The application management platform 110 can receive the user 105's selection of at least one model via the model configuration page 136, and the at least one model is called when executing a processing request for the target application.

[0075] Figures 2A to 2D illustrate schematic diagrams of example interfaces according to some embodiments of the present disclosure. It should be understood that the application interfaces shown in the accompanying drawings are merely examples, and various interface designs may exist. The various graphical elements in the interface may have different arrangements and different visual representations, one or more of which may be omitted or replaced, and one or more other elements may also be present. The embodiments of the present disclosure are not limited in this respect.

[0076] The digital assistant creation process described in the embodiments of the present disclosure can be implemented on an assistant creation platform, a terminal device installed with the assistant creation platform and / or a server corresponding to the assistant creation platform. In the examples below, for the purpose of discussion, it is described from the perspective of the target application creation platform, such as the application management platform 110 shown in Figure 1A. The page presented by the application management platform 110 can be presented via the terminal device of the user 105, and user input can be received via the terminal device of the user 105. In this article, the user 105 who creates the target application is sometimes also referred to as an assistant creator, assistant developer, etc.

[0077] In some embodiments, the application management platform 110 responds to a first request to add a data operation function 212 during the creation of the target application 120. When creating the target application 120, the application management platform 110 receives the request to add the data operation function 212. At this point, the application management platform 110 provides the user 105 with a first configuration page 130 for the data operation function 212, allowing the user to create a function instance of the data operation function 212 in the current application. The data operation function is configured by the user 105 to provide at least one type of data operation 222.

[0078] Data operations 222 may include: adding corresponding field values ​​of one or more fields, reading corresponding field values ​​of one or more fields, modifying corresponding field values ​​of one or more fields, or deleting corresponding field values ​​of one or more fields. For example, adding data, deleting data, modifying data, querying data, etc.

[0079] In one example, during the process of creating the target application 120, the application management platform 110 responds to the user 105 clicking a first add request for the data operation function 212 and provides a first configuration page 130 for the data operation function 212. For example, the application management platform 110 presents the first configuration page 130 based on the user 105 clicking an "add" control 214.

[0080] In some embodiments, the application management platform 110 receives first function configuration information for the data operation function 212 via the first configuration page 130. The first function configuration information at least indicates at least a portion of the first data object.

[0081] The first function configuration information may include, but is not limited to, various information entered by user 105, such as adding a data function. Based on the first configuration information, application management platform 110 may determine the first data object that user 105 needs to operate on. The first data object may indicate certain fields from among several fields included in a data object set. For example, in example 204 of FIG2D , fields 242 are set to allow operations, and user 105 may select the fields to be configured.

[0082] For example, the field types included in the first function configuration information may be: text, integer, floating point number, date, contact information, options (including single selection and multiple selection), Boolean type value, and the like.

[0083] In some embodiments, the application management platform 110 creates a first function instance of a data operation function 212 in the target application 120 based on the first function configuration information. The first function instance is configured by the user 105 to perform one or more data operations 222 of at least one type on at least a portion of the first data object. For example, the first function instance is for entering employee information.

[0084] For example, application management platform 110, based on the add data function, creates an employee information entry function in target application 120. When new employee information is entered into the first function instance, the first function instance is configured to perform one or more data operations 222 of at least one type, using at least a portion of the first data object selected by user 105. For example, if user 105 currently configures the first function instance only to implement data addition, deletion, and modification, and not query functionality, this can be selected based on user 105's needs.

[0085] In some embodiments, the application management platform 110 receives first function configuration information for the data operation function 212, including: the application management platform 110 receives, through the first configuration page 130, a selection of a first data object from the set of candidate data objects. The application management platform 110 receives, through the first configuration page 130, a selection of at least one field in the first data object.

[0086] The application management platform 110 selects a first data object based on the user 105 on the first configuration page 130 , and then selects at least one field in the first data object.

[0087] The first function configuration information includes but is not limited to: one or more types of data operations 222 in at least one type, such as adding data, deleting data, modifying data, and querying data. The name of the first function instance, such as employee information entry, employee information analysis, employee performance calibration, policy Q&A, etc. Descriptive information of the first function instance, for example, descriptive information of employee information entry: basic information that needs to be entered after a new employee joins the company, descriptive information of employee information analysis: analyzing employee information, understanding employee work status, satisfaction, salary level, performance, etc. Descriptive information of policy Q&A: helping users quickly understand the company's HR policies. Descriptive information of employee performance calibration: performing employee performance calibration on employee performance. One or more example user inputs for the first function instance.

[0088] The description information of the first function instance is provided to a machine learning model (e.g., model 155 of FIG. 1A ) for use by the machine learning model in determining how to perform a user query for the first function instance. One or more example user inputs are used to determine a user query that matches the first function instance.

[0089] In some embodiments, the application management platform 110 provides a second configuration page for the data operation function 212 in response to a second request to add the data operation function 212. The application management platform 110 receives the request to add the data operation function 212 when creating the target application 120. At this point, the application management platform 110 provides the user 105 with a second configuration page for creating another instance of the data operation function 212 in the current application. The application management platform 110 receives second configuration information for the data operation function via the second configuration page. The second configuration information indicates at least a portion of the second data object.

[0090] Based on the second function configuration information, the application management platform 110 creates a second function instance of the data operation function in the target application. The second function instance is configured to perform one or more data operations of at least one type on at least a portion of a second data object. The second data object can be the same as the first data object, and the second function instance can be configured to perform data operations on different portions of the same data object, or different types of data operations on the same portion of the data object.

[0091] For example, user 105 can configure different function instances for the same data manipulation function, such as a first function instance, a second function instance, and so on. The second function instance indicates a second data object, which may be in the same data object set as the first data object, but user 105 selects different fields for the first and second data objects. In other words, relying on the data manipulation functions provided by application management platform 110, application creators can simply configure different function instances by selecting data objects based on application creation needs, thereby implementing various types of data operations on different data objects.

[0092] User 105 can debug data manipulation function 212. In example 201 shown in FIG2A , user 105 can perform debugging in conversation window 215 on the right side of example 201. For example, during the debugging process, application management platform 110 will present a guidance message from the digital assistant, such as, "I am a digital assistant. I will answer your questions based on your questions..." User 105 can send a certain input message 216, and the digital assistant will reply with a message card 217 related to the input message 216. User 105 can then debug data manipulation function 212 based on the judgment of message card 217.

[0093] Currently, terminal devices present corresponding content and interact with users through the user interface of the application, meeting various user needs. However, in general scenarios, they cannot meet the user's needs for functional operations such as adding, deleting, modifying, and querying using natural language. The traditional solution is to use a user interface (UI) form input method, but for users, the UI form input method is costly and has a poor user experience. In some embodiments of the present disclosure, after the target application 120 is released, user queries represented by natural language from the terminal user 145 can be supported. After the target application 120 is released, the terminal user 145 can query in the form of natural language. For example, the terminal user 145 can initiate a user query to the target application 120 in the form of natural language text, voice, etc. The terminal user 145 can use natural language to ask the digital assistant to add, delete, modify, or query the associated data objects. In some embodiments, the target application 120 can use a digital assistant to receive the user query of the terminal user 145 and use the digital assistant to provide the terminal user 145 with the execution results corresponding to the user query. In this way, in the conversation window between the terminal user and the digital assistant, the user can freely trigger and execute various functions in the target application and obtain the corresponding function execution results directly from the conversation window.

[0094] Figure 3 shows a schematic diagram of an example interface 300 according to some embodiments of the present disclosure, in which a conversation window 310 is provided between the terminal user 145 and the digital assistant in the target application 120 via the terminal device 146. It should be understood that the application interface shown in the accompanying drawings is merely an example, and various interface designs may actually exist. The various graphical elements in the interface may have different arrangements and different visual representations, one or more of which may be omitted or replaced, and one or more other elements may also exist. The embodiments of the present disclosure are not limited in this respect. When the conversation window 310 is triggered to be presented, a guide message 312 may be provided to introduce the functions of the target application or the digital assistant therein to the user.

[0095] In the following example, for the sake of discussion, it is assumed that after the target application is published and is running, the application management platform 110 shown in FIG1A is still used to support the application operation. The page 142 presented by the application management platform 110 can be presented via a terminal device 146 of an end user 145, and user input can be received via the terminal device of the end user 145.

[0096] Application management platform 110 receives and processes a user query from end user 145 of target application 120. In some embodiments, depending on the configuration of target application 120, a machine learning model, such as model 155, may be invoked to help understand the user query and determine which function instance in target application 120 to invoke to match the user query. While processing the user query, if it is determined that the user query matches a first function instance, and a first type of data operation is determined from one or more types of data operations to be used to execute the user query, application management platform 110 first determines whether the query from end user 145 hits the first function instance.

[0097] In some embodiments, application management platform 110 determines at least one field associated with the user query from at least a portion of the first data object. After determining that the query of end user 145 matches the first function instance, application management platform 110 identifies the intent of end user 145, such as the data operation desired by end user 145. Application management platform 110 then extracts the matching fields from the first data object.

[0098] After determining that the query of the terminal user 145 matches the first function instance, the application management platform 110 determines at least one field associated with the user query from at least a portion of the first data object. For example, the first data object may include many fields, but the fields associated with the user query may be, among the many fields, a name field, an age field, and a years of service field.

[0099] In some embodiments, the application management platform 110 performs a first type of data operation on at least one field. For example, the application management platform 110 performs a data operation of adding data on at least one field.

[0100] In one example, the application management platform 110 provides a form to the end user 145. As shown in FIG3 , the application management platform 110 presents a reply card 316 from the digital assistant, in which at least one field is presented. After the application management platform 110 receives confirmation of the form from the end user 145, it performs a first type of data operation on at least one field presented in the form. As shown in the example interface 300 of FIG3 , in the conversation window 310 between the end user 145 and the digital assistant in the target application 120, in response to a user query 314 from the end user 145, the application management platform 110, after calling a first function instance to determine the execution result of the corresponding type of data operation, can present the execution result of the data operation in the form of a message from the digital assistant. For example, the application management platform 110 presents a reply message card 316 from the digital assistant in the conversation window 310. The reply message card 316 can provide at least one field that matches the user query 314 in the form of a form.

[0101] In some examples, if the application management platform 110 cannot determine the field value from the query of the terminal user 145, the application management platform 110 will present the field value of the field as blank in the form. As shown in Figure 3, the application management platform 110 presents a field blank 316-1 in the reply message card 316.

[0102] For example, application management platform 110 receives a query from terminal user 145, "Enter information: Name XX, Age X, Salary XXXX." Application management platform 110 presents a digital assistant reply message card 316: The entered information is: XXX. However, application management platform 110 may be unable to determine a field based on terminal user 145's query. In this case, a field 316-1 is displayed as missing in reply message card 316. Terminal user 145 can then confirm reply message card 316. Application management platform 110 then receives terminal user 145's confirmation of reply message card 316 and performs the data operation performed by terminal user 145 on the missing field 316 in message card 316.

[0103] In some embodiments, application management platform 110 receives corresponding field values ​​for one or more fields in at least one field from terminal user 145. Based on the received corresponding field values ​​for the one or more fields, application management platform 110 performs a first type of data operation on the at least one field. For example, application management platform 110 presents message 318 from a digital assistant based on employee entry information sent by terminal user 145: "Hello, I'm here to help you..., do you need to enter any more information?" Terminal user 145 may resend the corresponding field values ​​for one or more fields in the field, and application management platform 110 performs the first type of data operation on the one or more fields in the field resent by terminal user 145.

[0104] In one example, the application management platform 110 presents a message 318 from a digital assistant based on the employee input information sent by the terminal user 145: "Hello, I am here to help you..., do you need to enter any further information?" The terminal user 145 can also fill in the corresponding field values ​​of one or more fields in a field in the message 318, and the application management platform 110 performs a first type of data operation on the one or more fields in a field resent by the terminal user 145.

[0105] In some embodiments, the first type of data operation includes an update operation of at least one field. In response to receiving a determination of the execution result by the end user 145 , the application management platform 110 updates at least one field in the first data object.

[0106] For example, various data operations, such as adding or modifying data, will update data objects during the execution of application management platform 110. When end user 145 confirms the execution result of application management platform 110, application management platform 110 will update the data object. However, if end user 145 only requests a query and does not confirm the execution result of application management platform 110, application management platform 110 will not update the data object.

[0107] For example, when the data operation involves increasing the corresponding field values ​​of one or more fields, the application management platform 110 can determine the intention of the end user 145 based on the message, context, data object, field, etc. currently input by the end user 145. If the application management platform 110 does not collect all required fields, the structure of the message card is returned: the follow-up question text, a form for collected fields, a form for uncollected fields, a save button, and an exit dialog button.

[0108] If the application management platform 110 has collected all the required fields, it returns the structure of the message card. In the returned message card, the terminal user 145 can be asked to confirm the text, the collected fields form, the save button, and the exit dialog button.

[0109] If end user 145 clicks Exit, the data operation function is exited and an exit message is returned. If end user 145 clicks Save, the creation operation is attempted. If successful, a success message is sent. If end user 145 does not have permission to create objects, an error message indicating that the permission is denied is returned. If end user 145's creation fails, the error reason is returned.

[0110] For example, when a data operation modifies the corresponding field values ​​of one or more fields, the application management platform 110 can determine the intention of the end user 145 based on the message currently input by the end user 145, the context message, the data object, the field, etc. If there are fields that need to be modified by the end user 145, the application management platform 110 returns a confirmation message card including text for the end user 145 to confirm, the fields that need to be modified by the end user 145, the modified content, a save button, and an exit dialog button.

[0111] If end user 145 clicks Exit, the data manipulation function is exited and an exit message is returned. If end user 145 clicks Save, an edit operation is attempted. If successful, a success message is sent. If end user 145 does not have permission to modify the field, an error message indicating that the user does not have permission to modify the field is returned. If end user 145's modification fails, the error reason is returned.

[0112] The above describes that the application management platform 110 creates the target application 120 . After the target application 120 is released, the application management platform 110 can receive a user query represented by natural language from the terminal user 145 through the terminal device 146 and perform data operations based on the user query.

[0113] The following describes how the application management platform 110 presents a form corresponding to a user query by looking back at FIG. 3 .

[0114] In some examples, the application management platform 110 receives a user query for a target application 120. The application management platform 110 processes the user query by utilizing a first function instance in the target application 120. The first function instance is configured to perform one or more types of data operations on at least a portion of a first data object.

[0115] In some examples, application management platform 110 first determines that a user query matches a first function instance in target application 120, and then determines a first type of data operation from one or more types of data operations, the first type of data operation being used to execute the user query. Application management platform 110 needs to determine at least one field associated with the user query from at least a portion of the first data object.

[0116] In some embodiments, the application management platform 110 presents a user query form based on the user query. As shown in FIG3 , the application management platform 110 presents the user query form, such as a reply message card 316 from the digital assistant, in a conversation window 310 between the end user 145 and the digital assistant in the target application 120. The form includes at least one field of the first data object associated with the user query.

[0117] In some embodiments, the application management platform 110 may also receive confirmation of the form from the user and perform a first type of data operation based on at least one field in the form after the user's confirmation. Furthermore, the application management platform 110 presents the execution result of the first type of data operation.

[0118] In some examples, application management platform 110 receives a query from end user 145 titled "Enter information XXXX." Application management platform 110 presents a digital assistant reply message card 316: The entry information is: XXX. However, application management platform 110 may be unable to determine a field based on end user 145's query. In this case, a field 316-1 may be displayed as missing in reply message card 316. In this case, end user 145 can confirm reply message card 316. Application management platform 110 then receives end user 145's confirmation of reply message card 316 and performs the data operation performed by end user 145 on the missing field 316 in message card 316.

[0119] In some embodiments, the application management platform 110 can determine at least one field associated with the user query from at least a portion of the first data object by providing the user query and information related to at least a portion of the first data object to a target model, and receiving an output from the target model. In some examples, the information related to at least a portion of the first data object can include a header of the first data object (e.g., a data table), names of various fields in at least a portion, and the like.

[0120] In some examples, the first data object may include many fields, but the fields queried by the user may be, among these fields, the name field, age field, and years of work experience field. For example, the first data object corresponding to a certain employee may include not only age and years of work experience, but also many fields. However, the end user 145 may only enter the age and years of work experience of the certain employee. The application management platform may then output a form corresponding to the age and years of work experience of the certain employee queried by the end user 145 based on the target model.

[0121] In some embodiments, the generation of forms can also be based on model output. For example, the application management platform 110 receives a user query described in natural language input by the terminal user 145, and generates a data table corresponding to the user query through the target model. The application management platform 110 sends the generated data table corresponding to the user query to the target model (such as LLMS), and uses the target model to perform semantic understanding and analysis on the user query described in natural language sent by the terminal user 145. The target model outputs a form associated with the user query based on the semantic understanding and analysis. The application management platform 110 receives the form associated with the user query output by the target model, and presents it in the conversation window 310 between the terminal user 145 and the digital assistant in the target application 120.

[0122] In some embodiments, the first function instance is further configured to perform one or more types of data operations on at least a portion of the second data object. In some embodiments, the application management platform 110 may first determine a data object associated with the user from the first data object and the second data object. Then, the application management platform 110 may determine at least one field associated with the user query from at least a portion of the associated data objects.

[0123] In some embodiments, the first function instance is further configured to perform one or more types of data operations on at least a portion of the second data object. In some examples, the application management platform 110 may first provide the target model with a user query, information related to at least a portion of the first data object, and at least a portion of the second data object. The application management platform 110 then receives, from the target model, at least one field associated with the user query in the first data object or the second data object.

[0124] The application management platform 110 may also receive input of corresponding field values ​​for one or more fields in at least one field. The form presented by the application management platform 110 in the conversation window 310 between the terminal user 145 and the digital assistant in the target application 120 may include: input boxes for corresponding field values ​​of one or more fields. As shown in FIG3 , the application management platform 310 presents a reply card message 316 from the digital assistant as a form presented by the application management platform, which includes input boxes for corresponding field values ​​of one or more fields, such as an input box 316-1 for the salary field, an input box 316-2 for the name field, and so on.

[0125] The application management platform 110 can receive input for one or more field values ​​in the input box included in the form, and update the form based on the corresponding field values ​​of the one or more fields. In some embodiments, the application management platform can also accept field values ​​that need to be supplemented or modified, sent by the end user 145 in the form of a natural language conversation, and update the form based on the corresponding field values ​​of the one or more fields. In some embodiments, the first type of data operation can also include: an update operation on at least one field. After the application management platform 110 receives confirmation of the form from the end user 145, it can trigger an update of at least one field in the first data object.

[0126] In this way, users can use natural language to ask the digital assistant to add, delete, modify, and query related data objects. In response to the input of the end user 145, the application management platform 110 uses intent recognition and field extraction to render the hit form and present it to the end user 145 for secondary confirmation.

[0127] FIG4A shows a flowchart of a process 401 for application creation according to some embodiments of the present disclosure. The process 401 may be implemented at the application management platform 110. The process 401 is described below with reference to FIG1A.

[0128] In block 402 , the application management platform 110 receives a function addition request to add a function to a target application.

[0129] In block 403 , the application management platform 110 receives first configuration information for a first function, where the first configuration information indicates at least a type of the first function and first data associated with the first function, and the first function is configured to at least call a first model to perform task processing based on the first data.

[0130] In block 404 , the application management platform 110 adds the first function to the target application based on the first configuration information.

[0131] In some embodiments, receiving the first configuration information includes: providing a function configuration page in response to receiving a function adding request; and receiving the first configuration information via the function configuration page.

[0132] In some embodiments, receiving first configuration information for the first function includes: receiving a selection of a type of the first function from a plurality of predetermined function types; and in response to the selection of the type of the first function, receiving first configuration information corresponding to the type of the first function.

[0133] In some embodiments, the plurality of predetermined function types include at least one of the following: data processing function, question-and-answer function, and data analysis function.

[0134] In some embodiments, receiving first configuration information for a first function includes: receiving a selection of a first data source from one or more data sources; providing options for one or more data objects from the first data source; and receiving a selection of a first data object from one or more data objects as at least a portion of the first data.

[0135] In some embodiments, the one or more data sources include at least one of the following types of data sources: a data table, an analysis table, a knowledge base, a data stream, and a term base.

[0136] In some embodiments, receiving first configuration information for a first function includes: creating a first workflow corresponding to the first function; and in response to a creation request for a first work node in the first workflow, receiving node configuration information for the first work node, the node configuration information indicating input parameters, output parameters and a first operation to be performed of the first work node, the first operation including one of the following: calling a first model, a data processing operation based on the first data, the processing logic of the first work node, sending a notification message, and calling a function that has been created in the target application.

[0137] In some embodiments, a group of functions including the first function has been added to the target application, and the method further includes: receiving a function scheduling configuration, where the function scheduling configuration indicates scheduling of the group of functions.

[0138] In some embodiments, receiving the function scheduling configuration includes: receiving second configuration information for multiple work nodes in a second workflow, the second configuration information indicating that at least one work node among the multiple work nodes is associated with one or more functions in a set of functions.

[0139] In some embodiments, receiving the function scheduling configuration includes receiving a prompt word, wherein when executing a processing request for a target application, the prompt word is provided to the second model to determine that at least one or more functions in a set of functions are scheduled to execute the processing request.

[0140] In some embodiments, process 401 further includes: providing a model configuration page; and receiving a selection of at least one model via the model configuration page, wherein the at least one model is invoked when executing a processing request for the target application.

[0141] 4B shows a flow chart of a process 400 for data processing according to some embodiments of the present disclosure. The process 400 may be implemented at the application management platform 110. The process 400 is described below with reference to FIG1A.

[0142] In block 410 , the application management platform 110 provides a first configuration page for the data operation function in response to a first add request for the data operation function during creation of the target application. The data operation function is configured to provide at least one type of data operation.

[0143] In block 420 , the application management platform 110 receives first function configuration information for a data operation function via a first configuration page, where the first function configuration information indicates at least a portion of a first data object.

[0144] In block 430 , the application management platform 110 creates a first function instance of the data operation function in the target application based on the first function configuration information, where the first function instance is configured to perform one or more data operations of at least one type on at least a portion of the first data object.

[0145] In some embodiments, receiving first function configuration information for the data operation function includes: receiving, via a first configuration page, a selection of a first data object in a set of candidate data objects; and receiving, via the first configuration page, a selection of at least one field in the first data object.

[0146] In some embodiments, the first function configuration information further indicates at least one of the following: one or more types of data operations in at least one type, a name 232 of the first function instance, description information 234 of the first function instance, the description information is provided to the machine learning model for executing the user query for the first function instance, or one or more example 236 user inputs of the first function instance, the one or more example user inputs are used to determine the user query that matches the first function instance.

[0147] In some embodiments, process 400 also includes: providing a second configuration page for the data operation function in response to a second add request for the data operation function; receiving second function configuration information for the data operation function via the second configuration page, the second function configuration information at least indicating at least a portion of the second data object; and creating a second function instance of the data operation function in the target application based on the second function configuration information, the second function instance being configured to perform one or more types of data operations of at least one type on at least a portion of the second data object.

[0148] In some embodiments, process 400 also includes: after the target application is published, receiving a user query in natural language form from a terminal user; in response to determining that the user query matches the first function instance, determining that a first type of data operation is used to execute the user query from one or more types of data operations; determining at least one field associated with the user query from at least a portion of the first data object; and performing the first type of data operation on the at least one field.

[0149] In some embodiments, process 400 further includes: providing the end user with an execution result of the first type of data operation, where the execution result is presented in the form of at least one field.

[0150] In some embodiments, process 400 further includes: receiving corresponding field values ​​of one or more fields of the at least one field from the end user; and updating the execution result based on the corresponding field values ​​of the one or more fields.

[0151] In some embodiments, the first type of data operation includes an update operation of at least one field, and the method further includes updating the at least one field in the first data object in response to receiving a determination of the execution result by the end user.

[0152] In some embodiments, providing the execution result includes: presenting the execution result in the form of a message from the digital assistant in a conversation window between the terminal user and the digital assistant in the target application.

[0153] In some embodiments, at least one type of data operation includes at least one of the following: adding corresponding field values ​​of one or more fields, reading corresponding field values ​​of one or more fields, modifying corresponding field values ​​of one or more fields, or deleting corresponding field values ​​of one or more fields.

[0154] 4C shows a flow chart of a process 402 for data processing according to some embodiments of the present disclosure. The process 402 may be implemented at the application management platform 110. The process 402 is described below with reference to FIG1A.

[0155] At block 440 , the application management platform 110 receives a user query for a target application.

[0156] In block 450 , the application management platform 110 processes the user query using a first function instance in the target application, where the first function instance is configured to perform one or more types of data operations on at least a portion of a first data object.

[0157] In block 460 , the application management platform 110 presents a form corresponding to the user query, where the form includes at least one field in the first data object associated with the user query.

[0158] In some embodiments, processing the user query using the first functional instance in the target application includes: in response to determining that the user query matches the first functional instance in the target application, determining that a first type of data operation from the one or more types of data operations is used to execute the user query; and determining at least one field associated with the user query from at least a portion of the first data object.

[0159] In some embodiments, process 402 further includes: receiving user confirmation of the form; performing the first type of data operation based on the at least one field in the confirmed form; and presenting the execution result of the first type of data operation.

[0160] In some embodiments, determining at least one field associated with the user query from the at least portion of the first data object includes: providing the user query and information related to the at least portion of the first data object to a target model; and receiving a model output from the target model, the model output indicating at least one field associated with the user query, wherein the form is generated based on the model output.

[0161] In some embodiments, the first function instance is further configured to perform one or more types of data operations on at least a portion of a second data object, and wherein determining at least one field associated with the user query comprises: determining a data object associated with the user from the first data object and the second data object; and determining at least one field associated with the user query from the at least a portion of the associated data objects.

[0162] In some embodiments, the first function instance is further configured to perform one or more types of data operations on at least a portion of a second data object, and wherein determining at least one field associated with the user query comprises: providing the user query, information related to the at least a portion of the first data object, and the at least a portion of the second data object to a target model; and receiving a model output from the target model, the model output indicating at least one field in the first data object or the second data object associated with the user query, wherein the form is generated based on the model output.

[0163] In some embodiments, process 402 further includes: receiving input of corresponding field values ​​for one or more of the at least one field; and updating the form based on the corresponding field values ​​for the one or more fields.

[0164] In some embodiments, the presented form includes an input box for corresponding field values ​​of the one or more fields; and wherein receiving input of corresponding field values ​​of one or more fields of at least one field in the form includes: receiving input of corresponding field values ​​of the one or more fields in the input box in the form.

[0165] In some embodiments, the first type of data operation comprises an update operation on the at least one field, and the method further comprises: in response to receiving a confirmation of the form, triggering an update of the at least one field in the first data object.

[0166] 5A shows a schematic structural block diagram of an apparatus 501 for creating an application according to some embodiments of the present disclosure. Apparatus 501 may be implemented in or included in application management platform 110, for example. Each module / component in apparatus 501 may be implemented by hardware, software, firmware, or any combination thereof.

[0167] As shown in the figure, the apparatus 501 includes an adding request receiving module 502 configured to receive a function adding request for adding a function to a target application.

[0168] The device 501 also includes a configuration information receiving module 503, which is configured to receive first configuration information for a first function, the first configuration information at least indicating the type of the first function and first data associated with the first function, and the first function is configured to at least call a first model to perform task processing based on the first data.

[0169] The apparatus 501 further includes a first function adding module 504 configured to add the first function to the target application based on the first configuration information.

[0170] In some embodiments, the configuration information receiving module 503 is further configured to provide a function configuration page in response to receiving a function adding request; and receive the first configuration information via the function configuration page.

[0171] In some embodiments, the configuration information receiving module 503 is further configured to receive a selection of a first function type from a plurality of predetermined function types; and in response to the selection of the first function type, receive first configuration information corresponding to the first function type.

[0172] In some embodiments, the plurality of predetermined function types include at least one of the following: data processing function, question-and-answer function, and data analysis function.

[0173] In some embodiments, the configuration information receiving module 503 is further configured to receive a selection of a first data source from one or more data sources; provide options for one or more data objects from the first data source; and receive a selection of a first data object from one or more data objects as at least a portion of the first data.

[0174] In some embodiments, the one or more data sources include at least one of the following types of data sources: a data table, an analysis table, a knowledge base, a data stream, and a term base.

[0175] In some embodiments, the configuration information receiving module 503 is also configured to create a first workflow corresponding to the first function; and in response to a creation request for a first work node in the first workflow, receive node configuration information for the first work node, the node configuration information indicating the input parameters, output parameters and first operation to be performed of the first work node, the first operation including one of the following: calling a first model, a data processing operation based on the first data, the processing logic of the first work node, sending a notification message, and calling a function that has been created in the target application.

[0176] In some embodiments, a group of functions including the first function has been added to the target application, and the device 501 further includes a function scheduling configuration receiving module configured to receive a function scheduling configuration indicating scheduling of the group of functions.

[0177] In some embodiments, the function scheduling configuration receiving module is further configured to receive second configuration information for multiple work nodes in a second workflow, the second configuration information indicating that at least one work node among the multiple work nodes is associated with one or more functions in a group of functions.

[0178] In some embodiments, the function scheduling configuration receiving module is further configured to receive a prompt word, and when executing a processing request for a target application, the prompt word is provided to the second model to determine that at least one or more functions in a set of functions are scheduled to execute the processing request.

[0179] In some embodiments, the device 501 further includes a model configuration page providing module configured to provide a model configuration page; and receive a selection of at least one model via the model configuration page, and the at least one model is called when executing a processing request for a target application.

[0180] 5B shows a schematic structural block diagram of an apparatus 500 for creating a digital assistant according to some embodiments of the present disclosure. Apparatus 500 may be implemented in or included in application management platform 110, for example. Each module / component in apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0181] As shown in the figure, the device 500 includes a page configuration module 510, which is configured to provide a first configuration page for the data operation function in response to a first add request for the data operation function during the creation of the target application, and the data operation function is configured to be able to provide at least one type of data operation.

[0182] The apparatus 500 further includes a configuration information receiving module 520 configured to receive first function configuration information for a data operation function via a first configuration page, where the first function configuration information at least indicates at least a portion of a first data object.

[0183] The device 500 also includes a function instance creation module 530, which is configured to create a first function instance of a data operation function in a target application based on the first function configuration information, and the first function instance is configured to perform one or more types of data operations of at least one type on at least a portion of the first data object.

[0184] In some embodiments, the configuration information receiving module 520 is also configured to receive first function configuration information for the data operation function, including: receiving a selection of a first data object in a set of candidate data objects via a first configuration page; and receiving a selection of at least one field in the first data object via the first configuration page.

[0185] In some embodiments, the first function configuration information also indicates at least one of the following: one or more types of data operations in at least one type, the name of the first function instance, descriptive information of the first function instance, the descriptive information is provided to the machine learning model for executing user queries for the first function instance, or one or more example user inputs of the first function instance, the one or more example user inputs are used to determine the user query that matches the first function instance.

[0186] In some embodiments, the page configuration module 510 is further configured to provide a second configuration page for the data operation function in response to a second adding request for the data operation function.

[0187] In some embodiments, the configuration information receiving module 520 is further configured to receive second function configuration information for the data operation function via a second configuration page, where the second function configuration information at least indicates at least a portion of the second data object.

[0188] In some embodiments, the function instance creation module 530 is also configured to create a second function instance of the data operation function in the target application based on the second function configuration information, and the second function instance is configured to perform one or more types of data operations of at least one type on at least a portion of the second data object.

[0189] In some embodiments, after the target application is published, a user query in natural language form is received from a terminal user; in response to determining that the user query matches a first function instance, a first type of data operation is determined from one or more types of data operations to be used to execute the user query; at least one field associated with the user query is determined from at least a portion of a first data object; and the first type of data operation is performed on the at least one field.

[0190] In some embodiments, the execution result of the first type of data operation is provided to the terminal user, and the execution result is presented in the form of at least one field.

[0191] In some embodiments, corresponding field values ​​of one or more fields of the at least one field are received from an end user; and based on the corresponding field values ​​of the one or more fields, the execution result is updated.

[0192] In some embodiments, the first type of data operation includes an update operation of at least one field, and the configuration information receiving module 520 is further configured to update at least one field in the first data object in response to receiving a determination of the execution result by the end user.

[0193] In some embodiments, providing the execution result includes: presenting the execution result in the form of a message from the digital assistant in a conversation window between the terminal user and the digital assistant in the target application.

[0194] In some embodiments, at least one type of data operation includes at least one of the following: adding corresponding field values ​​of one or more fields, reading corresponding field values ​​of one or more fields, modifying corresponding field values ​​of one or more fields, or deleting corresponding field values ​​of one or more fields.

[0195] 5C shows a schematic structural block diagram of an apparatus 502 for creating a digital assistant according to some embodiments of the present disclosure. Apparatus 502 may be implemented in or included in application management platform 110, for example. Each module / component in apparatus 502 may be implemented by hardware, software, firmware, or any combination thereof.

[0196] As shown in the figure, the apparatus 502 includes a user query receiving module 540 configured to receive a user query for a target application.

[0197] The apparatus 502 further includes a processing module 550 configured to process the user query using a first function instance in the target application, wherein the first function instance is at least configured to perform one or more types of data operations on at least a portion of the first data object.

[0198] The apparatus 502 further includes a form presentation module 560 configured to present a form corresponding to the user query, the form including at least one field associated with the user query in the first data object. In some embodiments, processing the user query using the first function instance in the target application includes: in response to determining that the user query matches the first function instance in the target application, determining that a first type of data operation from the one or more types of data operations is used to execute the user query; and determining at least one field associated with the user query from the at least a portion of the first data object.

[0199] In some embodiments, the module 540 for receiving user queries is further configured to receive user confirmation of the form; perform the first type of data operation based on the at least one field in the confirmed form; and present the execution result of the first type of data operation.

[0200] In some embodiments, determining at least one field associated with the user query from the at least portion of the first data object includes: providing the user query and information related to the at least portion of the first data object to a target model; and receiving a model output from the target model, the model output indicating at least one field associated with the user query, wherein the form is generated based on the model output.

[0201] In some embodiments, the first function instance is further configured to perform one or more types of data operations on at least a portion of a second data object, and wherein determining at least one field associated with the user query comprises: determining a data object associated with the user from the first data object and the second data object; and determining at least one field associated with the user query from the at least a portion of the associated data objects.

[0202] In some embodiments, the first function instance is further configured to perform one or more types of data operations on at least a portion of a second data object, and wherein determining at least one field associated with the user query comprises: providing the user query, information related to the at least a portion of the first data object, and the at least a portion of the second data object to a target model; and receiving a model output from the target model, the model output indicating at least one field in the first data object or the second data object associated with the user query, wherein the form is generated based on the model output.

[0203] In some embodiments, the module 540 for receiving a user query is further configured to receive input of corresponding field values ​​of one or more fields of the at least one field; and update the form based on the corresponding field values ​​of the one or more fields.

[0204] In some embodiments, the presented form includes an input box for corresponding field values ​​of the one or more fields; and wherein receiving input of corresponding field values ​​of one or more fields of at least one field in the form includes: receiving input of corresponding field values ​​of the one or more fields in the input box in the form.

[0205] In some embodiments, the first type of data operation includes an update operation on the at least one field, and the processing module 550 is further configured to trigger an update of the at least one field in the first data object in response to receiving a confirmation of the form.

[0206] FIG6 shows a block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 600 shown in FIG6 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 600 shown in FIG6 may include or be implemented as the application management platform 110 of FIG1A, or the apparatus 501, 500, and / or 502 of FIG5A, FIG5B, or FIG5C.

[0207] As shown in FIG6 , electronic device 600 is a general-purpose electronic device. Components of electronic device 600 may include, but are not limited to, one or more processors or processing units 610, memory 620, storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processing unit 610 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 620. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to enhance the parallel processing capabilities of electronic device 600.

[0208] The electronic device 600 typically includes a plurality of computer storage media. Such media can be any accessible media that can be obtained by the electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 620 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 630 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 600.

[0209] The electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG6 , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a “floppy disk”) and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 620 may include a computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0210] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 600 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 600 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0211] The input device 650 may be one or more input devices, such as a mouse, keyboard, or trackball. The output device 660 may be one or more output devices, such as a display, a speaker, or a printer. The electronic device 600 may also communicate with one or more external devices (not shown) through the communication unit 640 as needed, such as a storage device, a display device, or the like, with one or more devices that allow a user to interact with the electronic device 600, or with any device that allows the electronic device 600 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0212] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0213] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0214] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0215] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0216] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes 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 box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0217] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for creating an application, comprising: receiving a feature addition request for adding a feature to a target application; receiving first configuration information for a first function, wherein the first configuration information at least indicates a type of the first function and first data associated with the first function, wherein the first function is configured to at least call a first model to perform task processing based on the first data; as well as Based on the first configuration information, the first function is added to the target application.

2. The method according to claim 1, wherein receiving the first configuration information comprises: In response to receiving the function adding request, providing a function configuration page; The first configuration information is received via the function configuration page.

3. The method according to claim 1, wherein receiving first configuration information for the first function comprises: receiving a selection of a type of the first function from a plurality of predetermined function types; as well as In response to selection of the type of the first function, first configuration information corresponding to the type of the first function is received.

4. The method according to claim 3, wherein the plurality of predetermined function types comprises at least one of the following: Data processing functions, Question and answer function, Data analysis capabilities.

5. The method according to claim 1, wherein receiving first configuration information for a first function comprises: receiving a selection of a first data source from among the one or more data sources; providing options for one or more data objects in the first data source; as well as A selection of a first data object of the one or more data objects is received as at least a portion of the first data.

6. The method of claim 5, wherein the one or more data sources include at least one of the following types of data sources: Datasheet, Analysis table, knowledge base, Data flow, Glossary.

7. The method according to claim 1, wherein receiving first configuration information for a first function comprises: Creating a first workflow corresponding to the first function; as well as In response to a creation request for a first work node in the first workflow, receiving a request for the first work node The node configuration information of the first working node indicates the input parameters, output parameters and a first operation to be performed by the first working node, and the first operation includes one of the following: Call the first model, a data processing operation based on the first data, the processing logic of the first working node, Send a notification message, Call the created function in the target application.

8. The method according to claim 1, wherein a group of functions including the first function has been added to the target application, further comprising: A function scheduling configuration is received, the function scheduling configuration indicating scheduling of the set of functions.

9. The method of claim 8, wherein receiving a functional scheduling configuration comprises: Second configuration information for a plurality of work nodes in a second workflow is received, wherein the second configuration information indicates that at least one work node among the plurality of work nodes is associated with one or more functions among the set of functions.

10. The method according to claim 8, wherein receiving the function scheduling configuration comprises: A hint word is received, and when executing a processing request for the target application, the hint word is provided to a second model to determine that at least one function in the set of functions is scheduled to execute the processing request.

11. The method according to claim 1, further comprising: Provide model configuration page; as well as A selection of at least one model is received via the model configuration page, and the at least one model is invoked when a processing request for the target application is executed.

12. A method for data processing, comprising: In creating a target application, in response to a first adding request for a data operation function, providing a first configuration page for the data operation function, wherein the data operation function is configured to be able to provide at least one type of data operation; Receiving first function configuration information for the data operation function via the first configuration page, the first function configuration information at least indicating at least a portion of a first data object; as well as Based on the first function configuration information, a first function instance of the data operation function is created in the target application, and the first function instance is at least configured to perform one or more types of data operations of the at least one type on at least a portion of the first data object.

13. The method according to claim 12, wherein receiving first function configuration information for the data operation function comprises: Receiving, via the first configuration page, a selection of the first data object from the set of candidate data objects; as well as A selection of at least one field in the first data object is received via the first configuration page.

14. The method according to claim 12, wherein the first function configuration information further indicates at least one of the following: data operations of said one or more types of said at least one type, the name of the first function instance, a description of the first function instance, the description being provided to a machine learning model for executing a user query for the first function instance, or One or more example user inputs of the first functionality instance, the one or more example user inputs being used to determine a user query matching the first functionality instance.

15. The method according to claim 12, further comprising: In response to a second adding request for the data operation function, providing a second configuration page for the data operation function; receiving, via the second configuration page, second function configuration information for the data operation function, the second function configuration information at least indicating at least a portion of a second data object; as well as Based on the second function configuration information, a second function instance of the data operation function is created in the target application, and the second function instance is configured to perform one or more types of data operations of the at least one type on the at least a portion of the second data object.

16. The method according to claim 12, further comprising: After the target application is released, receiving a user query represented by natural language from a terminal user; In response to determining that the user query matches the first function instance, determining a first type of data operation from the one or more types of data operations is used to execute the user query; determining at least one field associated with the user query from the at least a portion of the first data object; as well as The first type of data operation is performed on the at least one field.

17. The method of claim 16, wherein performing the first type of data operation on the at least one field comprises: providing a form to the end user, the form comprising at least the at least one field; as well as In response to receiving a validation of the form, performing the first type of data operation on the at least one field.

18. The method of claim 17, wherein performing the first type of data operation on the at least one field comprises: receiving from the end user corresponding field values ​​for one or more fields of the at least one field; as well as The first type of data operation is performed on the at least one field based on the received corresponding field values ​​of the one or more fields.

19. The method according to claim 16, further comprising: In a conversation window between the terminal user and the digital assistant in the target application, an execution result of the first type of data operation is provided in the form of a message from the digital assistant.

20. The method of claim 16, wherein the first type of data operation comprises an update operation of the at least one field, and the method further comprises: The at least one field is updated in the first data object.

21. The method of claim 12, wherein the at least one type of data operation comprises at least one of: Increase the corresponding field value of one or more fields, Read the corresponding field value of one or more fields. Modify the corresponding field value of one or more fields, or Deletes the corresponding field values ​​for one or more fields.

22. A method of data processing, comprising: receiving user queries for target applications; Processing the user query using a first function instance in the target application, the first function instance being configured at least to perform one or more types of data operations on at least a portion of a first data object; as well as A form corresponding to the user query is presented, the form including at least one field in the first data object associated with the user query.

23. The method of claim 22, wherein processing the user query using the first function instance in the target application comprises: In response to determining that the user query matches the first function instance in the target application, determining that a first type of data operation from the one or more types of data operations is used to execute the user query; as well as At least one field associated with the user query is determined from the at least a portion of the first data object.

24. The method according to claim 23, further comprising: receiving a user confirmation of the form; Based on the at least one field in the confirmed form, perform the first type of data operation; as well as The execution result of the first type of data operation is presented.

25. The method of claim 23, wherein determining at least one field associated with the user query from the at least a portion of the first data object comprises: providing the user query and information associated with the at least a portion of the first data object to a target model; as well as receiving a model output from the target model, the model output indicating at least one field associated with the user query, The form is generated based on the model output.

26. The method of claim 23, wherein the first function instance is further configured to perform one or more types of data operations on at least a portion of a second data object, and wherein determining at least one field associated with the user query comprises: determining a data object associated with the user from the first data object and the second data object; as well as At least one field associated with the user query is determined from the at least a portion of the associated data objects.

27. The method of claim 23, wherein the first function instance is further configured to perform one or more types of data operations on at least a portion of a second data object, and wherein determining at least one field associated with the user query comprises: providing the user query, information related to the at least a portion of the first data object, and the at least a portion of the second data object to a target model; as well as receiving a model output from the target model, the model output indicating at least one field in the first data object or the second data object that is associated with the user query, The form is generated based on the model output.

28. The method of claim 22, further comprising: receiving input of corresponding field values ​​of one or more fields of the at least one field; as well as The form is updated based on corresponding field values ​​of the one or more fields.

29. The method of claim 28, wherein the presented form includes input boxes for respective field values ​​of the one or more fields; and wherein receiving input of respective field values ​​for one or more of the at least one field in the form comprises: Input of corresponding field values ​​of the one or more fields is received in the input box in the form.

30. The method of claim 23, wherein the first type of data operation comprises an update operation on the at least one field, and the method further comprises: In response to receiving a confirmation of the form, an update of the at least one field in the first data object is triggered.

31. A device for application creation, comprising: An adding request receiving module, configured to receive a function adding request for adding a function to a target application; a configuration information receiving module, configured to receive first configuration information for a first function, wherein the first configuration information at least indicates a type of the first function and first data associated with the first function, and the first function is configured to at least call a first model to perform task processing based on the first data; as well as A first function adding module is configured to add the first function to the target application based on the first configuration information.

32. An apparatus for data processing, comprising: a page configuration module configured to, in creating a target application, provide a first configuration page for a data operation function in response to a first adding request for the data operation function, wherein the data operation function is configured to be able to provide at least one type of data operation; a configuration information receiving module, configured to receive first function configuration information for the data operation function via the first configuration page, wherein the first function configuration information at least indicates at least a part of a first data object; as well as A function instance creation module is configured to create a first function instance of the data operation function in the target application based on the first function configuration information, and the first function instance is configured to perform one or more types of data operations of the at least one type on at least a portion of the first data object.

33. An apparatus for data processing, comprising: A user query receiving module is configured to receive a user query for a target application; a processing module, configured to process the user query using a first function instance in the target application, the first function instance being configured to perform one or more types of data operations on at least a portion of a first data object; as well as The form presentation module is configured to present a form corresponding to the user query, wherein the form includes at least one field in the first data object associated with the user query.

34. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory is coupled to at least one processing unit and stores instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, cause the electronic device to execute a method according to any one of claims 1 to 11, and / or to execute a method according to any one of claims 12 to 21, and / or to execute a method according to any one of claims 22 to 30.

35. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement a method according to any one of claims 1 to 11, and / or to perform a method according to any one of claims 12 to 21, and / or to perform a method according to any one of claims 22 to 30.

36. A computer program product, which is tangibly stored in a computer storage medium and includes computer executable instructions, which when executed by a device cause the device to perform a method according to any one of claims 1 to 11, and / or to perform a method according to any one of claims 12 to 21, and / or to perform a method according to any one of claims 22 to 30.

Citation Information

Patent Citations

  • Application creation method and device, equipment and storage medium

    CN119002981A

  • Data processing method and data processing system

    CN106952072A

  • Task deployment method and device, equipment, storage medium and product

    CN114048024A

  • Service configuration method, device and equipment

    CN115220780A

  • Data processing method and device and electronic equipment

    CN116681242A