Application creation method and device, equipment and storage medium

Abstract

The embodiment of the invention provides an application creation method and device, equipment and a storage medium. The method includes: presenting at least one query to clarify a creation demand of the application based on interaction information related to creation of the application, the at least one query indicating at least a function that matches the creation demand; in response to receiving a user response to the at least one query, determining an architecture of the application based on the user response and the interaction information, the architecture at least indicating an association relationship between a plurality of functions of the application; and creating an application based on the architecture, the application including a plurality of function modules corresponding to the plurality of functions, and the function modules in the plurality of function modules being configured to support implementation of the corresponding functions. A large model may be utilized to implement the above application setup process, such as using the large model to clarify requirements, determine architectures, or create applications. In this way, the integrity and accuracy of conversion from requirements to functions can be ensured, and then the accuracy of application building can be ensured.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to application creation methods, apparatus, devices, computer-readable storage media, and computer program products. Background Technology

[0002] With the advancement of software development and machine learning technologies, automated application development platforms are becoming increasingly widespread. Users only need to input their application development requirements, and these platforms can automatically orchestrate and design the application. However, the efficiency and accuracy of these platforms still need improvement. Summary of the Invention

[0003] In a first aspect of this disclosure, an application creation method is provided. The method includes: presenting at least one query for clarifying application creation requirements based on interaction information related to application creation, the at least one query indicating at least a function matching the creation requirements; in response to receiving a user response to the at least one query, determining an application architecture based on the user response and interaction information, the architecture indicating at least the relationships between multiple functions of the application; and creating the application based on the architecture, the application including multiple functional modules corresponding to the multiple functions, and the functional modules among the multiple functional modules being configured to support the implementation of the corresponding functions.

[0004] In a second aspect of this disclosure, an apparatus for application creation is provided. The apparatus includes: a presentation module configured to present at least one query for clarifying application creation requirements based on interaction information related to application creation, the at least one query indicating at least a function matching the creation requirements; a determination module configured to determine the architecture of the application based on the user response and interaction information received, the architecture indicating at least a relationship between multiple functions of the application; and a creation module configured to create the application based on the architecture, the application including multiple functional modules corresponding to multiple functions, and the functional modules among the multiple functional modules being configured to support the implementation of the corresponding functions.

[0005] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of this disclosure, a computer program product is provided, including computer-executable instructions, wherein when executed by a processor, the computer-executable instructions implement the method according to a first aspect of this disclosure.

[0008] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram is shown of an example environment in which embodiments of the present disclosure may be implemented;

[0011] Figures 2A to 2C Schematic diagrams of example interfaces for application creation according to some embodiments of the present disclosure are shown respectively;

[0012] Figure 3 A flowchart illustrating an example process of requirements clarification and architecture generation according to some embodiments of this disclosure is shown;

[0013] Figure 4 A flowchart illustrating the process of creating an application according to some embodiments of this disclosure is shown;

[0014] Figure 5 A schematic structural block diagram of an example device for application creation according to some embodiments of the present disclosure is shown; and

[0015] Figure 6 A block diagram of an electronic device capable of implementing several embodiments of the present disclosure is shown. Detailed Implementation

[0016] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0017] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based 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 also be included below.

[0018] In this document, unless explicitly stated otherwise, performing a step in response to A does not mean that the step is performed immediately after A, but may include one or more intermediate steps.

[0019] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0020] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and user authorization should be obtained.

[0021] For example, in response to receiving a user's active request, a prompt message is sent to the user to clearly inform the user that the requested operation will require the acquisition and use of the user's personal information, thereby enabling the user to choose whether to provide personal information to the software or hardware such as electronic devices, applications, servers or storage media that perform the operation of the technical solution disclosed herein, based on the prompt message.

[0022] As an optional but non-restrictive implementation, in response to a user's active request, a prompt message can be sent to the user, such as a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0023] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0024] As used in this paper, the term "model" refers to a model that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. Model generation can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs using multiple layers of processing units. A neural network model is an example of a deep learning-based model. In this paper, "model" may also be referred to as a "machine learning model," "learning model," "machine learning network," or "learning network," and these terms are used interchangeably.

[0025] A neural network is a machine learning network based on deep learning. A neural network processes input and provides a corresponding output, typically consisting of an input layer, an output layer, and one or more hidden layers between the input and output layers. Neural networks used in deep learning applications often include many hidden layers, thus increasing the network's depth. The layers of a neural network are connected sequentially, so that the output of the previous layer is provided as the input to the next layer. The input layer receives the input to the neural network, while the output layer's output serves as the final output. Each layer of a neural network includes one or more nodes (also called processing nodes or neurons), each node processing the input from the layer above.

[0026] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. Environment 100 relates to an application management platform 110, which can support the creation and / or execution of applications. In some embodiments, the portion of the application management platform 110 used to support application creation may also be referred to as an application creation portion 111. In some embodiments, the portion of the application management platform 110 used to support application execution may also be referred to as an application execution portion 112.

[0027] like Figure 1 As shown, the application creation section 111 provides an environment for user 105 to create and publish applications. User 105 may be referred to as the application creation user or creator. In some embodiments, the application creation section 111 may be a low-code platform that provides a collection of tools for application creation. The application creation section 111 can support visual development of various types of applications, allowing developers to skip the manual coding process and accelerate the application development cycle and reduce costs. The application creation section 111 can support any suitable platform for users to develop one or more types of applications, such as an application platform as a service (aPaaS) based platform. Such a platform enables users to efficiently develop applications, enabling operations such as application creation and application function adjustment.

[0028] The application creation component 111 can be deployed locally on the user 105's terminal device and / or supported by a server. For example, the user 105's terminal device can run a client with the application creation component 111, which can support interaction between the user and the application creation component 111 provided by the server. When the application creation component 111 runs locally on the user's terminal device, the user 105 can directly interact with the local application creation component 111 using the terminal device. When the application creation component 111 runs on a server, the server can provide services to the client running on the terminal device based on the communication connection with the terminal device. The application creation component 111 can present a corresponding interface 130 to the user 105 based on the user 105's operations, to output and / or receive application creation-related information from the user 105.

[0029] In some embodiments, the application creation section 111 may be associated with a corresponding database, which stores the data or information required for the application creation process supported by the application creation section 111. For example, the database may store the code and description information corresponding to the various functional modules that make up the application. The application creation section 111 may also perform operations such as calling, adding, deleting, and updating the functional modules in the database. The database may also store operations that can be performed on different functional blocks. For example, in a scenario where an application needs to be created, the application creation section 111 can call the corresponding functional blocks from the database to build the application.

[0030] In embodiments of this disclosure, user 105 can create application 120 (also referred to as application to be created) as needed on application creation section 111 and publish application 120. Application 120 can be published to any appropriate application runtime section 112, as long as application runtime section 112 can support the operation of application 120.

[0031] After release, application 120' becomes available. Application 120' can be operated by one or more end users 145. End users 145 can operate application 120' through associated terminal devices 146 and thus interact with application management platform 110. End users 145 can be referred to as end users of application 120'. In some embodiments, application 120' may include or be implemented as a digital assistant.

[0032] Digital assistants can be configured to have intelligent conversational capabilities. They can be integrated into application 120' as part of application 120' to assist in task processing within application 120'. In other examples, digital assistants can be configured to run as standalone applications, such as web applications or other types of applications. In such examples, the digital assistant and application 120' can be considered as the same application. Digital assistants are provided to assist users with various task processing needs in different applications and scenarios. During interaction with the digital assistant, the user inputs interactive messages, and the digital assistant responds to the user's input by providing reply messages. Typically, digital assistants support users inputting questions in natural language and perform tasks and provide responses based on their understanding of natural language input and logical reasoning capabilities.

[0033] In some embodiments, the digital assistant can interact with end user 145 as a contact. For example, the digital assistant can be implemented in an instant messaging (IM) application. The digital assistant can interact with end user 145 in a one-on-one chat session. In some embodiments, the digital assistant can interact with multiple users in a group chat session that includes multiple users.

[0034] For each end user 145, the client of the application runtime portion 112 can present an interaction window 142 of the application 120' or a digital assistant in the client interface, such as a conversation window with the digital assistant. The end user 145 can enter conversation messages in the conversation window, and the application 120' can determine the digital assistant's response message 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 application 120', the interaction messages with the application 120' can include multimodal messages, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and so on.

[0035] Similar to the application creation component 111, the application execution component 112 can be deployed locally on each end user's (145's) terminal device and / or supported by a server. For example, the end user's (145's) terminal device can run a client with the application execution component 112, which can support interaction between the user and the application execution component 112 provided by the server. When the application execution component 112 runs locally on the user's terminal device, the end user (145) can directly interact with the local application execution component 112 using the terminal device. When the application execution component 112 runs on a server, the server can provide services to the client running on the terminal device based on the communication connection with the terminal device. The application execution component 112 can present corresponding application pages to the end user (145) based on the end user's (145's) actions, to output and / or receive application-related information from the end user (145).

[0036] In some embodiments, the implementation of at least some of the functionality of application 120', and / or the implementation of at least some of the functionality of the digital assistant in application 120', may be based on models. During the creation or operation of application 120', one or more models 155 may be invoked, such as the capabilities of model 155. In application 120', the digital assistant may utilize model 155 to understand user input and provide responses to the user based on the output of model 155.

[0037] During the creation process, the application management platform 110 needs to use model 155 to test the application 120 to determine whether the application 120's running results meet expectations. During operation, in response to different operation requests from users of application 120', the application running part 112 may need to use model 155 to determine the response results to users.

[0038] Although shown as independent of the application management platform 110, one or more models 155 may run on the application management platform 110 or other remote servers. In some embodiments, model 155 may be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, model 155 may include a large model or be based on a large model. A large model may be a large language model. A large language model is capable of question answering by learning from a large corpus. Alternatively or additionally, a large model may be a multimodal model capable of handling multiple modal inputs (e.g., text input, visual input). Model 155 may also be based on other suitable models.

[0039] Application management platform 110 can run on suitable electronic devices. These electronic devices can be any type of computing device, including terminal devices or servers. Terminal devices 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 system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. Servers can include, for example, computing systems / servers, such as mainframes, edge computing nodes, computing devices in cloud environments, and so on. In some embodiments, application management platform 110 can be implemented based on cloud services.

[0040] It should be understood that the structure and function of environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure. For example, although a single user interacting with application creation section 111 and a single user interacting with application execution section 112 are illustrated, in practice multiple users can access application management platform 110 to each create a digital assistant, and each digital assistant can be used to interact with multiple users.

[0041] As mentioned above, with the development of software development and machine learning technologies, automated application development platforms based on machine learning models are becoming increasingly widespread. Users only need to input their application development requirements, and these platforms can then use machine learning models to orchestrate and design the application. However, users often describe their application development requirements using vague, unstructured natural language. The platform needs to accurately determine the required functionality to ensure accurate application creation. In traditional technologies, on the one hand, the platform may need to repeatedly interact with the user to confirm the application's development requirements, resulting in low interaction efficiency and high interaction costs. On the other hand, vague development requirements may not be effectively captured by the platform, leading to a mismatch between the created application and the user's needs, affecting the accuracy of application development.

[0042] In view of this, embodiments of the present disclosure propose an improved scheme for application creation. In this improved scheme, based on interaction information related to application creation, at least one query is presented to clarify the application creation requirements, the at least one query indicating at least the functionality matching the creation requirements. If a user response to the at least one query is received, the application architecture is determined based on the user response and interaction information, the architecture indicating at least the relationships between multiple functions of the application. The application is then created based on the architecture, the application including multiple functional modules corresponding to multiple functions, and the functional modules among the multiple functional modules are configured to support the implementation of the corresponding functions.

[0043] In the embodiments of this disclosure, interactive information that may contain ambiguous expressions is transformed into clarifications (i.e., inquiries) about functions, and then the user's clarifications about functions are transformed into the application's architecture. Utilizing the architecture allows for a structured expression of the relationships between functions, ensuring the completeness and accuracy of the transformation from requirements to functions, and consequently ensuring the accuracy of the application's construction.

[0044] The following description will continue with reference to the accompanying drawings, which will provide some exemplary embodiments of this disclosure. Figures 2A to 2C Schematic diagrams are shown of example interfaces 200A to 200C (also referred to simply as examples 200A to 200C) for application creation according to some embodiments of the present disclosure. It should be understood that the interfaces shown in the drawings are merely examples, and various interface designs may actually exist. The various graphic elements in the interface 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. Embodiments of the present disclosure are not limited in this respect.

[0045] The interfaces shown in Examples 200A to 200C can be presented at the application management platform 110, but these are merely exemplary. In some embodiments, operations performed on the application management platform 110 can be completed with the assistance of other devices. For ease of discussion, reference will be made to... Figure 1 Environment 100 is used to describe Examples 200A to 200C.

[0046] In some embodiments of this disclosure, the application management platform 110 presents at least one query to clarify the creation requirements of the application 120 based on interaction information related to the creation of the application 120. This interaction information can be understood as interaction information between the user 105 and the application management platform 110, and may include input content from the user 105 (also referred to as a "question"). Alternatively or additionally, the interaction information may also include feedback content from the application management platform 110 in response to the user 105's input content. This interaction information may include relevant information generated from the interaction between the user 105 and the digital assistant or intelligent assistant provided by the application management platform 110.

[0047] As an example, combined Figure 2A As shown, the application management platform 110 can present an example interface 200A. The example interface 200A may include a first area 202 (e.g., a session window) for interaction with user 105. The first area may include a dialog box 204. User 105 can provide input to the application management platform 110 using the dialog box 204. The application management platform 110 can present user 105's input in the first area. For example, if user 105 wants to develop an "XXX customer management system," user 105 can send input 206 to the application management platform using the dialog box 204: "Help me develop a XXX customer management system. User role A manages their own customers in the system, and user role B can view user role B's performance and customer status." If the application management platform 110 does not need to generate feedback content for user 105's input, the application management platform 110 can present at least one query to clarify the creation requirements of application 120 based on the input content. In this case, the interactive information may include user 105's input content.

[0048] The application management platform 110 can display feedback content for the input content 206 of user 105 in the first area 202, such as "Regarding your question, I have supplemented some data XXXX for you. Please confirm whether the supplemented content meets your expectations?" In this case, the interaction information can include the input content 206 of user 105 and the feedback content of the application management platform 110. It is understood that for the creation of application 120, user 105 may need to have one or more rounds of dialogue with the application management platform 110. If user 105 has multiple rounds of dialogue with the application management platform 110, the interaction information can include the input content and feedback content of the multiple rounds of dialogue.

[0049] The at least one query is used to clarify the creation requirements of application 120, and the at least one query indicates at least the functionality that matches the creation requirements. This functionality may indicate the tasks that the application can perform, the services it can provide, or the uses it can achieve, etc. The queries and functionality will be illustrated below with examples.

[0050] Figure 3 A flowchart illustrating an example process 300 for requirements clarification and architecture generation according to some embodiments of this disclosure is shown. In some embodiments, such as Figure 3As shown, in box 302, the application management platform 110 can obtain interaction information between user 105 and the application management platform 110. In box 304, the application management platform 110 can present a clarification list of creation requirements based on the interaction information. This clarification list can include one or more queries, each query including a question and one or more recommendations for that question. The question in the query can be a question posed for various creation requirements of application 120, and the one or more recommendations can indicate the responses provided for the corresponding questions. As an example, continuing with... Figure 2A As shown, the application management platform 110 can present a clarification form 210 for the creation requirements of application 120 based on the input content 206 of user 105. The clarification form 210 may include questions 212, 214, 216, and 218, and may also include multiple recommended items for each question. Using a clarification list including questions and recommended items to clarify the application's creation requirements clearly demonstrates these requirements, ensuring the completeness and accuracy of the transformation from potentially ambiguous interactive information to creation requirements.

[0051] The questions in the inquiry can be any appropriate questions posed in response to the creation requirements, and the corresponding recommendations can indicate any appropriate content that matches the question. Examples of questions can include, but are not limited to, questions regarding the application's functionality, how data is presented, or the appearance of the interface (e.g., style, color scheme). Examples of corresponding recommendations can include, but are not limited to, answers to the application's creation requirements regarding functionality, presentation, or appearance.

[0052] In some embodiments, the first of the at least one queries is used to clarify the functionality of application 120. Application management platform 110 may present a question in the first query regarding the functionality of application 120, along with one or more recommendations for that question. The one or more recommendations may include a description of one or more recommended functions. Examples of such descriptions may include, but are not limited to, a title of the function, phrases or statements describing the function, etc.

[0053] As an example, continue to combine Figure 2AAs shown, the application management platform 110 can present a clarification form 210 for the creation requirements of application 120 based on the input content 206 of user 105. The clarification form 210 may include questions 212, 214, 216, and 218, and may also include multiple recommended items for each question. Question 212 is used to clarify the functions of application 120, and recommended items 222 to 224 for question 212 respectively include descriptions of the corresponding recommended functions. For example, recommended item 222 includes a title "Function A" and an option box corresponding to "Function A". In this way, the functions required by application 120 can be clearly listed. Of course, the clarification form 210 may also include questions for clarifying other creation requirements of application 120, such as questions 214 and 216 for clarifying the "Performance Analysis Dimension" and "Customer Analysis Dimension" of application 120, respectively. It should be understood that the above questions and recommended items are merely exemplary, and the embodiments of this disclosure do not limit the specific content of the questions and recommended items.

[0054] In some embodiments, the presentation style of a recommendation item may include a presentation style indicating that the recommendation item is selected (e.g., referred to as a "first style") and a presentation style indicating that the recommendation item is not selected (e.g., referred to as a "second style"). The presentation style of at least some of the recommendations for a problem indicates that at least some of the recommendations are selected by default. That is, while presenting a problem, the application management platform 110 may select at least some of the recommendations for that problem by default, and present the default-selected recommendations through, for example, the first style. This allows the application management platform 110 to recommend default recommendations to the user 105, which helps ensure the integrity and accuracy of the application 120 creation and reduces the input burden on the user 105.

[0055] The presentation styles indicating whether a recommendation is selected and unselected can be any two appropriate styles. In some examples, a recommendation may include an option box and a description of the recommended content. The option box may include a selected style indicating that the recommendation is selected and an unselected style indicating that the recommendation is not selected. As an example, such as Figure 2A As shown, the recommended option 222 for question 212 may include an option box 226 and a description 228 for "Function A". The application management platform 110 selects "Function A" by default and presents option box 226 as shown below. Figure 2A The selected style is shown below. Recommendation 224 includes option box 232 and description 234 for "Function D". Application management platform 110 does not select "Function D" by default, and presents option box 234 as shown below. Figure 2A The selected state is shown.

[0056] It should be noted that the above presentation style is merely exemplary. In practical applications, any other appropriate presentation style can be used to indicate whether a recommendation item is selected or not. For example, the application management platform 110 can use different colors or fonts to present selected and unselected recommendations; for instance, selected recommendations can be presented in bold font, and unselected recommendations can be presented in non-bold font. The embodiments of this disclosure do not limit the presentation style of recommendations.

[0057] In some embodiments, the application management platform 110 can determine the at least one query based on interaction information and the application scenario of application 120, using a trained machine learning model 155. This allows the powerful natural language understanding capabilities of the machine learning model 155 to break down the user 105's creation request, improving the completeness and accuracy of the creation request transformation. In some examples, the application management platform 110 can determine the questions in the clarification list, the recommended items for each question, and the default selected recommended item among one or more recommended items for each question, based on interaction information, the application scenario of application 120, and historical data related to application 120, using the machine learning model 155. Of course, the above-described methods for determining queries are merely exemplary; queries for clarifying creation requests can also be determined through other methods, such as semantic matching. The embodiments of this disclosure do not limit the method of query determination.

[0058] In some embodiments, the application management platform 110 may also present an entry point for adding functions to the application 120 in association with the first query, for receiving a description of the added functions. If the user 105 determines that the application 120 should have other functions besides the recommended functions, the user 105 can use the entry point to add a description of the functions to supplement other functions not listed in the recommended functions. If the application management platform 110 receives a description of the added functions via the entry point, the application management platform 110 may present a description of the added functions in association with the first query. Of course, the application management platform 110 may also present entry points for adding other creation requirements for the application 120 in association with other queries, for receiving a description of the added other creation requirements, such as the way data is displayed, its style, or its color scheme, etc.

[0059] As an example, such as Figure 2AAs shown, the application management platform 110 can present add entry points 236, 238, and 240 in the clarification list 210, which are respectively associated with questions 212, 214, and 216. If user 105 determines that the functionality of application 120 needs to be supplemented, add entry point 236 can be triggered (e.g., single click, double click, long press, etc.). In response to the triggering of add entry point 236, application management platform 110 can present an input box corresponding to add entry point 236. User 105 can enter a description of the functionality into the input box. If a description of the functionality is received via add entry point 236, application management platform 110 can present a description of the added functionality below question 212. It is understood that user 105 can also use add entry point 238 or add entry point 240 to add, for example, "performance analysis dimension" or "customer analysis dimension," etc., in a similar way. In this way, if user 105 determines that the creation requirements presented in the clarification list 210 are incomplete, user 105 can use the add entry points to supplement and improve the creation requirements, which helps to maintain the integrity of the requirement transformation. It should be noted that the above-described method of clarifying creation requirements is merely exemplary. Inquiries may also include other information related to the creation requirements, or they may only include a description of the functionality; the embodiments of this disclosure do not limit this.

[0060] In some embodiments of this disclosure, if a user response to the at least one query is received, the application management platform 110 can determine the architecture of the application 120 based on the user response and interaction information. This architecture at least indicates the relationships between multiple functions of the application. It is understood that the user response matches the content contained in the at least one query, and the user response may differ if the content contained in the at least one query is different.

[0061] In some embodiments, the user response may include confirmation of the creation requirements clarified by the at least one inquiry. Since the at least one inquiry at least indicates a function matching the creation requirements, the user response includes at least confirmation of the function indicated by the at least one inquiry. In some examples, if the at least one inquiry includes a first inquiry clarifying the functionality of application 120, and the first inquiry includes a question about the functionality of application 120 and one or more recommendations for that question, the user response may include selection and confirmation of at least some of the recommendations. That is, user 105 may select at least some recommendations from one or more recommendations as needed. User 105 may then trigger confirmation of the selected recommendations. Of course, user 105 may also select corresponding recommendations for other inquiries in the at least one inquiry (i.e., inquiries other than the first inquiry) as needed.

[0062] In some embodiments, if the query (e.g., a first query) includes a question about the creation requirements of application 120 and one or more recommendations for the question, and at least some of the recommendations are selected by default, the user response may include confirmation of the default-selected recommendations. This confirmation may be expressed in any suitable manner. In some examples, the application management platform 110 may present a confirmation control associated with the at least one query. If a triggering of the confirmation control is detected, the application management platform 110 may determine that a user response to the at least one query has been received. As an example, in conjunction with... Figure 2A As shown, the clarification form 210 may include a confirmation control 242. If user 105 determines that the content presented in the clarification form 210 meets the creation requirements of application 120, user 105 may trigger the confirmation control 242. In response to the triggering of the confirmation control 242, application management platform 110 may determine that it has received confirmation of the recommended item that is selected by default in the clarification form.

[0063] In some examples, if a dialog message indicating confirmation of the default selected recommendation is received, the application management platform 110 can determine that a user response to at least one inquiry has been received. As an example, combined with... Figure 2A and Figure 2B As shown, if user 105 determines that the content presented in clarification form 210 meets the creation requirements of application 120, user 105 can input text such as "Please check the content I submitted" or "Confirm, continue" through dialog box 204 to express confirmation of the recommended item selected by default in clarification form 210 (which can also be understood as confirmation of clarification form 210). In this case, application management platform 110 can determine that it has received confirmation of the recommended item selected by default in clarification form. It should be understood that user 105 is not limited to expressing confirmation of the inquiry through text; user 105 can also express confirmation of the inquiry through other modal data such as voice, images, etc. The embodiments of this disclosure do not limit this.

[0064] In some embodiments, the user response may also include an update to the creation requirements clarified by the at least one query. That is, if user 105 determines that there is a difference between the creation requirements clarified by the at least one query and the creation requirements expected by user 105, user 105 may trigger an update to the at least one query. In some examples, if the first query includes a question about the functionality of application 120 and one or more recommendations for that question, and user 105 determines that application 120 should have additional functionality beyond the recommended functionality, user 105 may provide user input to application management platform 110 describing the functionality to be added to application 120.

[0065] As an example, combined Figure 2A As shown, if the application management platform 110 presents an entry point 236 for adding a function in association with the first query, the user 105 can use the entry point 236 to add a description of the function. The application management platform 110 can receive the description of the function via the entry point 236 and use the description as at least part of the user response. Alternatively or additionally, the user 105 can also input a description of the added function via, for example, a dialog box 204, such as "Please add function X" or "Please add function Y," etc. In this case, the application management platform 110 can receive the description of the function via the dialog box 204 and use the description as at least part of the user response. Of course, the above user input is only exemplary, and user input can also include other modal input content such as voice content. That is, the user 105 can also express the addition of a function in other ways, and the embodiments of this disclosure are not limited thereto.

[0066] In some embodiments, the inquiry (e.g., the first inquiry) may include a question about the creation requirements of application 120 and one or more recommendations for the question, with at least some of the recommendations being selected by default. In this case, user 105 may trigger the deselection of the default-selected recommendations, or user 105 may select recommendations that are not selected by default. Application management platform 110 may include the selection of recommendations that are not selected by default, or the deselection of recommendations that are selected by default, as at least part of the user response.

[0067] As an example, such as Figure 2A As shown, the recommended item indicating "Function C" is selected by default. If user 105 determines that "Function C" is redundant, user 105 can trigger the deselection of the recommended item. The application management platform 110 can determine that at least part of the user response has been received. Alternatively or additionally, the recommended item 224 indicating "Function D" is not selected by default. If user 105 determines that "Function D" matches the creation requirement, user 105 can trigger the selection corresponding to "Function D," and the application management platform 110 can include the selection of the recommended item as at least part of the user response. It should be understood that the above user responses are merely exemplary, and user responses may differ when the content of the query is different. The embodiments of this disclosure do not specifically limit the user responses.

[0068] In some embodiments, combined with Figure 3As shown, if a user response is received to the clarification form presented in box 304, process 300 can proceed to box 306. In box 306, application management platform 110 can determine whether the creation requirements of application 120 are clear. For example, application management platform 110 can use machine learning model 155 to determine whether the creation requirements of application 120 are clear based on the content and interaction information confirmed by user 105 in the clarification form. If it is determined that the creation requirements of application 120 are clear, process 200 can proceed to box 310. If it is determined that the creation requirements of application 120 are unclear, application management platform 110 can update the clarification form and use the updated clarification form to clarify the creation requirements of application 120 again.

[0069] In some embodiments, the architecture may indicate at least one user role of the application, at least one page provided for each user role, and at least one function indicated by each page. Each user role may indicate a type of user of the application 120. For example, the at least one user role may include the provider, maintainer, and end user of the application 120. Also, for example, as... Figure 2A As shown, the customer management system may include user role A (e.g., "Marketing Consultant") and user role B (e.g., "Marketing Director"). A page can be understood as a separate part of application 120 used to present information or provide functionality.

[0070] In some embodiments, combined with Figure 3 As shown in box 310, the application management platform 110 can determine at least one user role of the application 120 based on user response and interaction information.

[0071] In box 312, the application management platform 110 can determine at least one page to be provided for each of the at least one user role. As an example, combined with... Figure 2B As shown, the application management platform 110 can determine at least one page (e.g., page A, page B, page C, and page D) required for the customer management system for user role A and at least one page required for the customer management system for user role B.

[0072] In box 314, for each of the at least one pages, the application management platform 110 can determine at least one function supported by that page. As an example, continuing with... Figure 2B As shown, page A can provide "Function A", "Function B" and "Function C", page B can provide "Function D", "Function E", "Function F" and "Function G", and so on.

[0073] In box 316, the application management platform 110 can generate the architecture of application 120. This architecture can indicate the relationships between user roles, pages, and functions. In some examples, it combines... Figure 2B As shown, the application management platform 110 can present an architecture 246 in the first area 202. The architecture 246 may include description information 248 for each user role, description information 250 for each page, description information 252 for each function, indications 254 of the hierarchical relationship between user roles and pages, and indications 256 of the hierarchical relationship between pages and functions. Examples of indications 254 and 256 may include, but are not limited to, connecting lines or branch lines, etc.

[0074] In some embodiments, the application management platform 110 can determine multiple functions supported by the application 120 based on user responses and interaction information. The application management platform 110 can also determine at least one user role of the application 120, and at least one page provided for each user role. Then, the application management platform 110 can decompose the multiple functions into each page for each user role, thereby determining at least one function supported by each page. It should be understood that the application management platform 110 can determine user roles, pages, and functions in a predetermined order. The application management platform 110 can also determine user roles, pages, and functions independently, and then determine the relationships between user roles, pages, and functions. The embodiments of this disclosure do not limit this.

[0075] In some embodiments, the application management platform 110 can determine the model input for the machine learning model 155 based on user responses and interaction information. The application management platform 110 can provide the model input to the machine learning model 155, instructing the machine learning model 155 to determine at least one user role of the application 120, at least one page provided by each user role, and at least one function supported by each page, to obtain the model output of the machine learning model 155. Then, the application management platform 110 can determine the architecture of the application 120 based on the model output. It should be noted that the application management platform 110 is not limited to using machine learning models to determine the architecture; the application management platform 110 can also use, for example, rule-based algorithms to determine the relationships between user roles, pages, and functions, thereby determining the architecture of the application 120.

[0076] It is understood that the application management platform 110 is not limited to decomposing functions based on user roles and pages. The application management platform 110 can also decompose functions based on any other suitable method and construct an architecture indicating the relationships between multiple functions. In some embodiments, the application management platform 110 can determine the multiple functions supported by the application 120 and the hierarchical relationships between these functions based on user responses and interaction information. The application management platform 110 can also construct the architecture of the application 120 based on the hierarchical relationships between multiple functions. As an example, the architecture may include a tree structure, which may include multiple levels, each level may include at least one node, and each node may have a corresponding function. Of course, the above architecture is merely exemplary, and any other suitable architecture can be selected according to actual needs. The embodiments of this disclosure do not limit this.

[0077] In some embodiments of this disclosure, the application management platform 110 creates application 120 based on the architecture. Application 120 may include multiple functional modules corresponding to multiple functions, and the functional modules among the multiple functional modules are configured to support the implementation of the corresponding functions. Here, a functional module can be understood as a pre-built unit or component capable of implementing one or more functions.

[0078] In some embodiments, if the architecture indicates the relationships between multiple functions, the application management platform 110 can determine multiple functional modules corresponding to the multiple functions based on the architecture. The application management platform 110 can then create an application 120 based on the determined multiple functional modules. As an example, the application management platform 110 can pre-build a database of candidate functional modules. Based on the architecture, the application management platform 110 can utilize a functional module recommendation algorithm to select multiple functional modules from the multiple candidate functional modules provided in the database that match the multiple functions respectively. The application management platform 110 can also configure multiple functional modules based on a data flow configuration algorithm between functional modules to obtain the created application 120.

[0079] In some embodiments, the architecture indicates the relationships between at least one user role in the application, at least one page provided for each user role, and at least one function supported by each page. In this case, the application management platform 110 can determine the page structure of at least one page based on the architecture, the page structure indicating the layout of the at least one function provided by the page within the page. The application management platform 110 can determine at least one functional module for implementing the at least one function supported by the page. The application management platform 110 can then create the page in the application 120 based on the page structure and the at least one functional module.

[0080] In some examples, the architecture may include descriptive information for each page. The application management platform 110 may pre-build a database of candidate page structures. For a page within the at least one page, the application management platform 110 may select the page structure from multiple candidate page structures provided in the database based on the page's descriptive information. As an example, combined with... Figure 2B As shown, architecture 246 may include description information 250 for page A. Application management platform 110 can select the page structure of page A from multiple candidate page structures provided by the database based on the description information 250 of page A.

[0081] In some embodiments, the architecture includes description information of the page and at least one description of information corresponding to at least one function supported by the page. For at least one function, the application management platform 110 can determine the functional module for implementing the function from a plurality of candidate functional modules based on the description information of the page and the description information corresponding to the function.

[0082] As an example, combined Figure 2B As shown, the application management platform 110 can select functional module A from multiple candidate functional modules provided by the database to implement function A based on the description information 250 of page A and the description information 252 of function A. By repeating the above selection operation of functional modules, the application management platform 110 can also select functional module B to implement function B and functional module C to implement function C from multiple candidate functional modules. The application management platform 110 can create page A of application 120 based on the page structure of page A, functional module A, functional module B, and functional module C. For each page of application 120 (e.g., page B, page C, and page D), the application management platform 110 can repeat the above page creation process to complete the creation of application 120.

[0083] In some embodiments, the application management platform 110 can generate application code based on architecture-related information using a machine learning model 155. This code may include code segments corresponding to multiple functional modules. In other words, the application code may include multiple code segments, and each functional module may include at least one code segment. In some examples, architecture-related information may include information about the architecture itself, such as descriptions of user roles, page descriptions, or function descriptions, indications of the relationships between user roles and pages, or indications of the relationships between pages and functions, etc. Alternatively or additionally, architecture-related information may include other relevant information besides the architecture, such as reference information related to user roles, information indicating page structure, information indicating the coding method of functional modules, etc. Alternatively or additionally, architecture-related information may include architecture-related reference code, such as reference code for pages, reference code for functional modules, etc.

[0084] As an example, the application management platform 110 can determine a candidate page structure matching each page as a reference page structure from a database of candidate page structures. The application management platform 110 can also determine a candidate functional module matching each function as a reference functional module from a database of candidate functional modules. Based on the architecture (e.g., descriptions of user roles, pages, or functions), the reference page structure corresponding to each page (e.g., descriptions of the page structure or reference code), and the reference functional module corresponding to each function (e.g., code of the reference functional module), the application management platform 110 can generate model input for the machine learning model 155. The application management platform 110 can then provide the model input to the machine learning model 155 to obtain the model output of the machine learning model 155. Afterwards, the application management platform 110 can determine the code for the application 120 based on the model output. Thus, the architecture, reference page structure, and reference functional module can be used to instruct the machine learning model 155 to write the code for the application 120, which not only ensures the accuracy of the application 120 development but also improves the development efficiency of the application 120. It should be noted that the content provided to the machine learning model 155 above is merely exemplary. In practical application scenarios, the model input can be constructed based on the architecture and any appropriate content related to the creation of application 120. The embodiments of this disclosure do not limit this.

[0085] In some embodiments, the application management platform 110 can present the created application 120. As an example, combined with... Figure 2CAs shown, the application management platform 110 can display the created application 120 in the second area 258 of the example interface 200C. The application management platform 110 can display page identifiers 260, 262, 264, and 266 corresponding to pages A, B, C, and D of application 120 in the second area 258. The application management platform 110 can respond to the selection of a page identifier among page identifiers 260, 262, 264, and 266, and display the corresponding page in the second area. For example, combined with... Figure 2C As shown, page identifier 260 is selected, and application management platform 110 can display page 268 (i.e., page A). Page 268 may include functional module 270, functional module 272 and functional module 274.

[0086] In some embodiments, the application management platform 110 may also present an indication of the creation progress of the application 120. As an example, combined with... Figure 2C As shown, the application management platform 110 can respond to the completion of page A creation by displaying an instruction 276 indicating that page A has been created. The application management platform 110 can also respond to the completion of page B creation by displaying an instruction 278 indicating that page B has been created. In this way, user 105 can understand the creation progress of application 120.

[0087] In summary, in the embodiments of this disclosure, interactive information that may contain ambiguous expressions is transformed into clarifications (i.e., inquiries) about functions, and then the user's clarifications about functions are transformed into the application's architecture. Utilizing the architecture allows for a structured expression of the relationships between functions, ensuring the completeness and accuracy of the transformation from requirements to functions, and consequently ensuring the accuracy of the application's development.

[0088] Figure 4 A flowchart of an application creation process 400 according to some embodiments of the present disclosure is shown. Process 400 can be applied to an application management platform 110. Reference will be made below. Figure 1 The environment 100 describes the process 400.

[0089] In box 410, the application management platform 110 presents at least one query to clarify the application creation requirements based on interaction information related to the creation of the application, and the at least one query indicates at least a function that matches the creation requirements.

[0090] In box 420, in response to receiving a user response to at least one query, the application management platform 110 determines the architecture of the application based on the user response and interaction information, the architecture indicating at least the relationships between multiple functions of the application.

[0091] In box 430, the application management platform 110 creates an application based on the architecture. The application includes multiple functional modules corresponding to multiple functions, and the functional modules among the multiple functional modules are configured to support the implementation of the corresponding functions.

[0092] In some embodiments, a first question in at least one query is used to clarify the functionality of the application, and presenting at least one query includes: presenting a question in the first query about the functionality of the application and one or more recommendations for the question, wherein the one or more recommendations include a description of one or more recommended functions.

[0093] In some embodiments, presenting at least one query further includes: presenting an entry point for adding functionality to the application associated with the first query, for receiving a description of the added functionality.

[0094] In some embodiments, the presentation style of at least some of the recommendations indicates that at least some of the recommendations are selected by default.

[0095] In some embodiments, the user response includes at least one of the following: selecting a recommendation that is not selected by default among one or more recommendations, deselecting a recommendation that is selected by default among one or more recommendations, confirming a recommendation that is selected by default among one or more recommendations, or user input describing a function to be added to the application.

[0096] In some embodiments, at least one query is determined by using a trained machine learning model based on interaction information and the application scenario of the application.

[0097] In some embodiments, the architecture refers to at least one user role of the application, at least one page provided for each user role, and at least one function supported by each page.

[0098] In some embodiments, creating an application based on architecture includes: determining, for a page in at least one page, a page structure based on architecture, the page structure indicating the layout of at least one function provided by the page in the page; determining at least one functional module for implementing at least one function supported by the page; and creating the page in the application based on the page structure and the at least one functional module.

[0099] In some embodiments, the architecture includes description information of the page and at least one description information corresponding to at least one function supported by the page, and determining at least one functional module includes: for a function among at least one function, determining a functional module for implementing the function from a plurality of candidate functional modules based on the description information of the page and the description information corresponding to the function.

[0100] In some embodiments, creating an application based on an architecture includes: generating application code using a machine learning model based on architecture-related information, the code including code segments corresponding to multiple functional modules.

[0101] Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes. Figure 5 A schematic structural block diagram of an example device 500 for application creation according to certain embodiments of the present disclosure is shown. Device 500 may be implemented as or included in application management platform 110. Various modules / components in device 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0102] like Figure 5 As shown, the apparatus 500 includes: a presentation module 510 configured to present at least one query for clarifying the creation requirements of the application based on interaction information related to the creation of the application, wherein the at least one query indicates at least a function matching the creation requirements; a determination module 520 configured to determine the architecture of the application based on the user response and interaction information in response to receiving a user response to the at least one query, wherein the architecture indicates at least the relationships between multiple functions of the application; and a creation module 530 configured to create the application based on the architecture, wherein the application includes multiple functional modules corresponding to multiple functions, and the functional modules among the multiple functional modules are configured to support the implementation of the corresponding functions.

[0103] In some embodiments, the first question in at least one query is used to clarify the functionality of the application, and the presentation module 510 is further configured to: present the question in the first query about the functionality of the application and one or more recommendations for the question, wherein the one or more recommendations include a description of one or more recommended functions.

[0104] In some embodiments, the presentation module 510 is further configured to: present an entry point for adding a function to the application in association with the first query, for receiving a description of the added function.

[0105] In some embodiments, the presentation style of at least some of the recommendations indicates that at least some of the recommendations are selected by default.

[0106] In some embodiments, the user response includes at least one of the following: selecting a recommendation that is not selected by default among one or more recommendations, deselecting a recommendation that is selected by default among one or more recommendations, confirming a recommendation that is selected by default among one or more recommendations, or user input describing a function to be added to the application.

[0107] In some embodiments, the presentation module 510 is further configured to: determine at least one query based on the interaction information and the application scenario of the application using a trained machine learning model.

[0108] In some embodiments, the architecture refers to at least one user role of the application, at least one page provided for each user role, and at least one function supported by each page.

[0109] In some embodiments, the creation module 530 is further configured to: determine the page structure of at least one page based on the architecture, the page structure indicating the layout of at least one function provided by the page in the page; determine at least one functional module for implementing at least one function supported by the page; and create the page in the application based on the page structure and at least one functional module.

[0110] In some embodiments, the architecture includes description information of the page and at least one description of information corresponding to at least one function supported by the page, and the creation module 530 is further configured to: for a function of at least one function, determine a functional module for implementing the function from a plurality of candidate functional modules based on the description information of the page and the description information corresponding to the function.

[0111] In some embodiments, the creation module 530 is further configured to: generate application code based on architecture-related information and using a machine learning model, the code including code segments corresponding to each of multiple functional modules.

[0112] The units and / or modules included in device 500 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units and / or modules in device 500 can be implemented at least partially by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), and so on.

[0113] Figure 6 A block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that... Figure 6 The electronic device 600 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 6The illustrated electronic device 600 may include or be implemented as Figure 1 Application management platform 110, or Figure 5 The device 500.

[0114] like Figure 6 As shown, electronic device 600 is in the form of 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 640, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processor 610 may be a physical or virtual processor and is capable of performing various processes according to computer-executable instructions stored in memory 620. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 600.

[0115] Electronic device 600 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 620 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 640 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 600.

[0116] Electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 6 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 620 may include computer program product 625 having one or more computer-executable instruction modules configured to perform various methods or actions of various embodiments of this disclosure.

[0117] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 600 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 600 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0118] Input device 650 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 660 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 600 can also communicate with one or more external devices (not shown) via communication unit 640 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 600, or with any device that enables electronic device 600 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0119] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable storage medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0120] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-executable instructions.

[0121] These computer-executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-executable instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable storage medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0122] Computer-executable instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0123] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer-executable instruction products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, executable instruction, or portion of instructions, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0124] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they 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 chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An application creation method, comprising: Based on interaction information related to the creation of the application, at least one query is presented to clarify the creation requirements of the application, and the at least one query indicates at least a function that matches the creation requirements; In response to receiving a user response to the at least one query, the architecture of the application is determined based on the user response and the interaction information, the architecture indicating at least the relationships between multiple functions of the application; as well as An application is created based on the architecture, the application includes multiple functional modules corresponding to the multiple functions, and the functional modules among the multiple functional modules are configured to support the implementation of the corresponding functions.

2. The method of claim 1, wherein the first question in the at least one query is used to clarify the functionality of the application, and presenting the at least one query includes: The first query presents a question about the functionality of the application and one or more recommendations for the question, wherein the one or more recommendations include a description of one or more recommended functions.

3. The method of claim 2, wherein presenting the at least one inquiry further comprises: The first query is associated with an entry point for adding functionality to the application, which is used to receive a description of the added functionality.

4. The method of claim 2, wherein the presentation style of at least some of the recommended items indicates that the at least some recommended items are selected by default.

5. The method of claim 2, wherein the user response comprises at least one of the following: The selection of a recommendation item that is not selected by default from the one or more recommended items. Deselecting the default selected recommendation item from the one or more recommended items. Confirmation of the default selected recommendation among the one or more recommended items, or User input describing the functionality added to the application.

6. The method of claim 1, wherein the at least one inquiry is determined by: Based on the interaction information and the application scenario of the application, the at least one query is determined using a trained machine learning model.

7. The method of claim 1, wherein the architecture indicates at least one user role of the application, at least one page provided for each user role, and at least one function supported by each page.

8. The method of claim 7, wherein creating the application based on the architecture comprises: For each of the at least one pages, the page structure of the page is determined based on the architecture, and the page structure indicates the layout of at least one function provided by the page in the page; Identify at least one functional module used to implement at least one function supported by the page; as well as Based on the page structure and the at least one functional module, the page in the application is created.

9. The method of claim 8, wherein the architecture includes description information of the page and at least one description piece of information corresponding to at least one function supported by the page, and determining the at least one functional module includes: For each of the at least one functions, based on the description information of the page and the description information corresponding to the function, a functional module for implementing the function is determined from multiple candidate functional modules.

10. The method of claim 1, wherein creating the application based on the architecture comprises: Based on information related to the architecture, a machine learning model is used to generate the application's code, which includes code segments corresponding to each of the multiple functional modules.

11. An apparatus for application creation, comprising: The presentation module is configured to present at least one query to clarify the creation requirements of the application based on interactive information related to the creation of the application, the at least one query indicating at least a function that matches the creation requirements; A determination module is configured to, in response to receiving a user response to the at least one query, determine the architecture of the application based on the user response and the interaction information, the architecture indicating at least the relationships between multiple functions of the application; as well as A module is created and configured to create an application based on the architecture. The application includes multiple functional modules corresponding to the multiple functions, and the functional modules among the multiple functional modules are configured to support the implementation of the corresponding functions.

12. An electronic device, comprising: At least one processor; as well as At least one memory, coupled to the at least one processor and storing instructions for execution by the at least one processor, which, when executed by the at least one processor, cause the electronic device to perform the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having stored thereon computer-executable instructions that can be executed by a processor to implement the method according to any one of claims 1 to 10.

14. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 10.

Images