Application processing method and device, equipment and storage medium
By determining and encapsulating the atomic components and description information of the target function block in the application creation platform, the problem that traditional platforms cannot flexibly build specific functional applications is solved, and more efficient application processing and diversified requirements are achieved.
Patent Information
- Application Number
- CN202310594249.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-24
- Publication Date
- 2024-11-26
AI Technical Summary
Traditional application creation platforms lack flexibility in the database and cannot easily build travel ticket purchase applications from other applications, resulting in the application scenario being limited by database function blocks and being unable to flexibly implement specific functions.
By determining multiple atomic components used to achieve the target function and description information for the target function block, encapsulate them into target function blocks, supplying platform calls to expand the platform's task processing capabilities and user needs to meet.
It realizes that the atomic components that can realize specific functions can be automatically encapsulated as target function blocks in the application creation platform, expands the platform's task processing capabilities, improves processing efficiency, and meets the diversified needs of users.
Smart Images

Figure CN119025149A_ABST
Abstract
Description
Technical Field
[0001] 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 application processing. Background Art
[0002] With the rapid development of Internet technology, various applications have become important tools in people's daily lives. Different applications have different functions, and users can use specific applications with specific functions to achieve specific services. Application creation platforms, especially low-code platforms, can support users to develop applications efficiently and realize operations such as application creation and application function adjustment. Summary of the invention
[0003] In a first aspect of the present disclosure, an application processing method is provided. The method includes: determining multiple atomic components for implementing a target function, the multiple atomic components are provided by an application creation platform; determining description information for a target function block, the description information at least including a semantic description of the target function; and encapsulating the multiple atomic components and the description information into a target function block for the application creation platform to call to execute the target function.
[0004] In a second aspect of the present disclosure, a device for application processing is provided. The device includes: a composition determination module configured to determine multiple atomic components for implementing a target function block, wherein the multiple atomic components are provided by an application creation platform; a description determination module configured to determine description information for the target function block, wherein the description information at least includes a semantic description of the target function; and an encapsulation module configured to encapsulate the multiple atomic components and the description information into a target function block for the application creation platform to call to execute the target function.
[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the electronic device executes the method of the first aspect.
[0006] In a fourth 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 method of the first aspect is implemented.
[0007] 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
[0008] 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:
[0009] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;
[0010] Figure 2 A flowchart showing an application processing process according to some embodiments of the present disclosure is shown;
[0011] Figure 3 A schematic diagram showing a process of encapsulating functional blocks according to some embodiments of the present disclosure;
[0012] Figure 4 A schematic diagram showing the packaging of functional blocks according to some embodiments of the present disclosure;
[0013] Figure 5 A schematic structural block diagram of an apparatus for application processing according to some embodiments of the present disclosure is shown; and
[0014] Figure 6 A block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented is shown. DETAILED DESCRIPTION
[0015] Embodiments of the present disclosure will be described in more detail below 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 being limited to the embodiments set forth herein. On the contrary, 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 only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0016] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "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 also be included below.
[0017] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.
[0018] 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.
[0019] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scopes of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and their authorization should be obtained 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.
[0020] 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 software or hardware such as an electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.
[0021] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message is sent to the relevant user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.
[0022] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.
[0023] The application creation platform can call function blocks to perform tasks such as development, creation, and adjustment of applications. Traditionally, the application creation platform provides pre-coded function blocks in the database. During the application development process, developers rely on the function blocks currently available on the platform or encode function blocks in a custom manner to build the desired application. For example, if you want to create a travel ticket purchase application, the application creation platform in the traditional solution can only call these function blocks from the database to create a travel ticket purchase application if the database contains function blocks associated with travel ticket purchase. If the database does not contain function blocks associated with travel ticket purchase, the application creation platform in the traditional solution cannot easily build such function blocks from existing function blocks in other applications or through other means. This will cause the application scenarios of the traditional solution to be restricted by the database, and it is impossible to flexibly implement application processing.
[0024] According to an embodiment of the present disclosure, an improved solution for application processing is provided. According to the solution, multiple atomic components for realizing a target function are determined, and description information for a target function block is determined. Multiple atomic components and description information are encapsulated into a target function block for the application creation platform to call to execute the target function. In this way, some atomic components that can realize specific functions can be automatically encapsulated into a target function block that can be called as a whole during the use of the application creation platform. This can expand the task processing capability of the application creation platform, improve the efficiency of subsequent processing, and meet the diversified needs of users.
[0025] Figure 1 1 is a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. Figure 1 As shown, the application creation platform 110 can provide an application development and deployment environment. In some embodiments, the application creation platform 110 can be a low-code platform that provides a collection of tools for application development. The application creation platform 110 can support visual development of applications, so that developers can skip the manual coding process and speed up the application development cycle and cost. The application creation platform 110 can support any appropriate platform for users to develop applications, such as a platform based on application platform as a service (aPaaS).
[0026] The application creation platform 110 can be 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 include, for example, 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 application creation platform 110 can be implemented based on cloud services.
[0027] The application creation platform 110 may be deployed locally on the user's terminal device, and / or may be supported by a remote server. In some embodiments, the terminal device may run a client of the application creation platform 110, which may support the user's interaction with the application creation platform 110. In the case where the application creation platform 110 runs locally on the user's terminal device, the user may directly use the client to interact with the local application creation platform 110. In the case where the application creation platform 110 runs on a server device, the server device may provide services to the client running in the terminal device based on the communication connection with the terminal device.
[0028] The application creation platform 110 may be deployed with a digital assistant 120. The user 140 may interact with the digital assistant 120 via the application creation platform 110. The digital assistant 120 is used for dialogue with the user 140. The client of the application creation platform 110 may present an interaction window between the user 140 and the digital assistant 120, such as a conversation window, in the client interface. As an intelligent assistant, the digital assistant 120 has intelligent dialogue and information processing capabilities. The user 140 may enter a conversation message in the conversation window, and the digital assistant 120 provides a reply message in response to the user's conversation message.
[0029] In the application creation platform 110, the digital assistant 120 can be called or awakened by an appropriate method (e.g., a shortcut key, a button, or a voice) to present a conversation window with the user. In some embodiments, the digital assistant 120 can be included in the contact list of the current user in the application creation platform 110 as a contact of the user, or included in the information flow of the chat component. By selecting the digital assistant 120, a conversation window with the digital assistant 120 can be opened. In some embodiments, the digital assistant 120 can also be started in one or more components supported by the application creation platform 110, thereby presenting a conversation window with the digital assistant 120.
[0030] The application creation platform 110 can obtain the interaction information between the user 140 and the digital assistant 120 in the conversation window (including conversation messages from the user and reply messages from the digital assistant 120). In some embodiments, the application creation platform 110 can use the model 125 to understand the user's conversation messages and determine the next operation to be performed. The application creation platform 110 can interact with the model 125 to provide model input to the model 125 and obtain corresponding model output from the model 125. The model 125 can run locally on the application creation platform 110 or on a remote server. In some embodiments, the model 125 can be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model 125 can be based on a language model (LM). The language model can have question-and-answer capabilities by learning from a large amount of corpus. The model 125 can also be based on other appropriate models.
[0031] The database 130 is used to store data or information required for application processing operations to be performed by the application creation platform 110. For example, the database 130 can store various functional blocks used to form an application. The application creation platform 110 can also perform operations such as calling, adding, deleting, and updating the functional blocks in the database 130. The database 130 can also store operations that can be performed on different functional blocks. Exemplarily, in a scenario where an application 150 is to be created, the application creation platform 110 can call the corresponding functional blocks from the database 130 to build the application 150.
[0032] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.
[0033] Some example embodiments of the present disclosure will be described in detail below with reference to examples of the accompanying drawings.
[0034] Figure 2 1 is a flowchart of a process 200 of application processing according to some embodiments of the present disclosure. The process 200 may be implemented at the application creation platform 110. For ease of discussion, reference will be made to Figure 1 The process 200 is described with reference to the environment 100 of FIG.
[0035] In block 210 , the application creation platform 110 determines a plurality of atomic components for implementing a target function. The determined plurality of atomic components are provided by the application creation platform 110 .
[0036] Atomic components can also be referred to as atomic modules, and functional blocks can also be referred to as function points or applets. Functional blocks as a whole can be used to perform specific functions, and thus can be used to combine applications (APPs) to provide specific services or complete specific tasks. For example, the ticket query function can be used to query tickets from the departure point to the destination, the book borrowing function can be used to implement book borrowing in the library, the book search function block can be used to implement book search in the library, and so on. Atomic components can be more granular components in functional blocks. Atomic components can include, for example, pages of functional blocks, components of each operating control in the page, data forms, data flows, role permission configurations, application interfaces (APIs), and so on. In general, the application creation platform 110 can provide a variety of atomic components and support users (such as application developers) to operate and define each atomic component so as to combine them to implement a function in a specific application or task.
[0037] As will be described in detail later, since multiple atomic components can be used to perform the target function as a whole, it is expected that these atomic components are encapsulated into a target function block for the application creation platform 110 to call. The triggering of the encapsulation of the target function block, or the determination of the atomic components included therein, can be implemented in various operation stages of the application creation platform 110. In some embodiments, the application creation platform 110 can disassemble the application that has been created and accessible to the platform to encapsulate multiple atomic components that can realize specific functions defined in the application into functional blocks. In some embodiments, the application creation platform 110 can also interact with the user 140 with the help of the digital assistant 120 (and also with the help of the model 125) to use the platform capabilities to complete the tasks that the user needs to perform. In such a process, the application creation platform 110 can determine multiple atomic components for performing a certain function of the task. It is understandable that in this process, the application for task execution may be created, or may not be created but temporarily used. In any case, during the interaction process, the application creation platform 110 can obtain knowledge about which atomic components can realize which function, so that it can be determined to encapsulate these atomic components into a single functional block. The following will describe in detail the specific implementation methods of disassembling existing applications and determining functions based on interactions.
[0038] In some embodiments, the application creation platform 110 may select one or more created target applications from the database 130. The application creation platform 110 may identify a target function block for executing a target function from the target application. Specifically, the application creation platform 110 may obtain the logical architecture information of the target application, and based on the logical architecture information, identify the target function block from the target application. The logical architecture information here may indicate the processing logic and call relationship in the target application. The application creation platform 110 may determine one or more function blocks included in the target application based on the logical architecture information. The application creation platform 110 may determine to encapsulate one, some or all of the function blocks. The function blocks to be encapsulated may be considered as "target function blocks".
[0039] In some embodiments, the application creation platform 110 may use a preset identification rule to identify the logical architecture information, and determine the target function block in the target application for executing the target function based on the identification result. In some embodiments, the application creation platform 110 may use a model 125 to identify the logical architecture information, and directly obtain the target function block from the model 125.
[0040] Regarding the method of obtaining the logical architecture information, in some embodiments, the application creation platform 110 can use the model 125 to extract the logical architecture information from the target application. Specifically, the application creation platform 110 can obtain the code of the target application and / or other descriptive information about the target application, and provide the code of the target application and / or other descriptive information to the model 125. In some embodiments, the application creation platform 110 can generate prompt word input for the model 125 based on the code and / or other descriptive information of the target application. The application creation platform 110 can achieve the generation of prompt word input through prompt word engineering. The generated prompt word input is provided to the model 125, so that the model 125 can determine the logical architecture information of the target application from the code and / or other descriptive information of the target application, and feed it back to the application creation platform 110.
[0041] In some embodiments, the application creation platform 110 may also extract logical architecture information from annotation information associated with the target application. The annotation information may at least describe the functions of one or more functional blocks in the target application. In some embodiments, the annotation information may be associated with the code of the target application, for example, the annotation information may be included in the code of the target application.
[0042] Regarding annotation information, in some embodiments, when the target application is an application previously generated by the application creation platform 110, if each functional block of the target application already contains annotation information, the application creation platform 110 can directly obtain the annotation information associated with the target application. If each functional block of the target application does not contain annotation information, the application creation platform 110 can also use the model 125 to determine the function of each functional block, and then perform an annotation information adding operation on each functional block of the target application to obtain the annotation information.
[0043] In some embodiments, part or all of the annotation information may also be predefined by the developer of the target application. For example, the developer may add annotation information to one or more functional blocks in the target application during its development, and the application creation platform 110 may obtain the annotation information of the target application when obtaining the target application.
[0044] In some embodiments, if the annotation information clearly indicates the division of each functional block in the target application and the functions it implements, the application creation platform 110 can understand the logical architecture of the target application based on the annotation information and identify which part of the target application corresponds to the functional block of the target function.
[0045] In some embodiments, if the comprehensibility of the annotation information is low, the application creation platform 110 can provide the annotation information to the model 125 and instruct the model 125 to help extract the logical architecture information of the target application and / or identify the functional blocks in the target application. In some embodiments, the application creation platform 110 can generate a prompt word input for the model 125 based on the annotation information and other auxiliary information, and provide the prompt word input to the model 125. The model 125 can extract the logical architecture information of the target application from the annotation information and send it to the application creation platform 110. The model 125 can also directly provide the application creation platform 110 with the division results of the functional blocks in the target application. Alternatively or additionally, the application creation platform 110 can also extract the logical architecture information from the annotation information through other means.
[0046] Further, after identifying the target function block from the target application, the application creation platform 110 can extract multiple atomic components defined for the target function block from the target application. For example, if the target application is a library application and the target function is a book management function, the application creation platform 110 can identify a book management function block that can execute the book management function from the library application. The application creation platform 110 can then extract the book management page, book management-related data forms, APIs, etc. defined for the book management function block in the library application.
[0047] In some embodiments, as described above, the application creation platform 110 can obtain the interaction information between the user 140 and the digital assistant 120 during the interaction process for the task, and determine the multiple atomic components required for the target function in the task based on the interaction information. The digital assistant 120 here is associated with the application creation platform 110, and the interaction information includes at least the description information of each of the multiple atomic components. The description information of each of the multiple atomic components may include a semantic description of the function of the atomic component. For example, the application creation platform 110 can receive a user request to request the execution of a specific task (regardless of whether the application that performs the task already exists). The application creation platform 110 can allow the user to interact with the digital assistant 120 to clarify the various functions in the task during the interaction process, and the atomic components described by each function. The description information for the atomic components can be provided in part or in whole by the user 140, and in part or in whole by the application creation platform 110 (for example, after being determined by the model 125) and confirmed by the user 140.
[0048] In some embodiments, the application creation platform 110 may determine multiple atomic components based on at least a portion of the interactive information (e.g., session information from the user 140). Exemplarily, the application creation platform 110 may receive a session message from the user 140 in the session window between the user 140 and the digital assistant 120, and determine multiple atomic components required by the user 140 based on the session message. For example, the application creation platform 110 may determine that a ticket booking task is to be performed in response to receiving a session message "Book me a ticket from city A to city B", and the ticket booking task at least involves a ticket query function. The application creation platform 110 may present information in the session window to guide the user 140 to further clarify specific tasks, functions in the tasks, and other user needs. The application creation platform 110 may determine the multiple atomic components required to implement each function through such human-computer interaction.
[0049] In some embodiments, the application creation platform 110 can also determine multiple atomic components based on the interactive information with the help of the model 125. Specifically, the application creation platform 110 can generate prompt word input for the model based on at least a portion of the interactive information and the set of atomic components provided by the application creation platform 110. For example, the prompt word input can describe the user needs indicated by the conversation message and the set of atomic components provided by the platform. The set of atomic components provided by the application creation platform 110 can depend on the specific capabilities of the platform and can change as the platform is developed and updated. In some embodiments, the prompt word input can indicate all the atomic components that the application creation platform 110 can provide, or it can be a plurality of candidate atomic components that the application creation platform 110 selects from all the atomic components based on the interactive information and can be used to implement the target function. The application creation platform 110 can generate prompt word input for the model 125 based on at least a portion of the interactive information and the set of atomic components provided by the application creation platform 110 through prompt word engineering.
[0050] Further, the application creation platform 110 may provide the prompt word input to the model 125, and obtain the plurality of atomic components from the model 125. The application creation platform 110 may further determine the plurality of atomic components for implementing the target function based on the plurality of atomic components.
[0051] In block 220, the application creation platform 110 determines description information for the target function block, the description information at least including a semantic description of the target function. The semantic description here can be in a form that can be understood by the machine learning model, which helps to conveniently and quickly call the target function block in the subsequent natural language interface. For example, in a scenario where the application creation platform 110 uses a model to select, process tasks, create and modify application calls for function blocks, the semantic description of the target function can enable the model to accurately understand the functions that the module can achieve and decide whether to call the function block.
[0052] In some embodiments, in addition to the semantic description of the target function, the description information of the target function block may also include, but is not limited to, the function identifier of the target function block (e.g., the general name of the function block), the input parameters of the target function block, the output parameters of the target function block, and the description information of each of the multiple atomic components of the target function block. Such supplementary information helps to more clearly describe the target function block and helps to accurately understand the target function block in the subsequent call of the natural language interface.
[0053] In some embodiments, when the annotation information of the target application includes a semantic description of the target function that can be executed by the target function block, the application creation platform 110 can directly determine the annotation information as the description information for the target function block. In some embodiments, when the annotation information of the target application does not include a semantic description of the target function that can be executed by the target function block, the application creation platform 110 can also generate description information for the target function block based on the description information of each of the multiple atomic components of the target function block.
[0054] In some embodiments, the application creation platform 110 can generate description information for the target functional block based on the description information of each of the multiple atomic components of the target functional block by means of the model 125. In some embodiments, the application creation platform 110 can directly provide the description information of each of the multiple atomic components to the model 125, and obtain the description information for the target functional block output by the model 125.
[0055] In some embodiments, the application creation platform 110 can generate a prompt word input for the model based on the description information of each of the multiple atomic components of the target functional block. Similarly, the application creation platform 110 can fill the description information of each of the multiple atomic components into the input template of the model 125 through the prompt word project to obtain the prompt word input that conforms to the input form of the model 125. The application creation platform 110 then provides the prompt word input to the model 125 and obtains the description information for the target functional block from the model 125.
[0056] In some embodiments, during the output process of the description information, the user can also determine whether the generated description information is accurate and meets expectations through human-computer interaction. Specifically, the application creation platform 110 can generate candidate description information for the target function block (for example, it can be automatically generated or generated with the help of the model 125). The application creation platform 110 can provide the candidate description information to the user 140. Based on the modification or confirmation of the candidate description information received by the user 140, the application creation platform 110 can determine the candidate description information or the modified description information as the description information of the target function block. Specifically, the application creation platform 110 can provide the candidate description information to the user 140 by presenting the candidate description information in the conversation window between the user 140 and the digital assistant 120. The application creation platform 110 can determine that the modification of the candidate description information by the user 140 is received in response to receiving a conversation message from the user 140 indicating the modification of the candidate description information in the conversation window. Exemplarily, the application creation platform 110 can determine that the modification of the candidate description information by the user is received in response to receiving the conversation message "Modify the description information of the function block A to XX".
[0057] In some embodiments, the application creation platform 110 may further provide the session message to the model 125, and obtain a modification method for the candidate description information from the model 125. The application creation platform 110 may modify the candidate description information based on the modification method. In some embodiments, the application creation platform 110 may also directly provide the candidate description information and the session message to the model 125, and obtain the modified description information from the model 125. Alternatively or additionally, the application creation platform 110 may also directly determine the modification method corresponding to the session message based on a pre-set identification rule, and then modify the candidate description information based on the modification method to determine the description information of the target functional block.
[0058] In some embodiments, the application creation platform 110 may also determine that a user modification to the candidate description information is received in response to receiving an instruction to modify the candidate description information. Exemplarily, the application creation platform 110 may determine that a user modification to the candidate description information is received in response to receiving a voice instruction from the user 140, "Modify the description information of the function block A to XX". In some embodiments, the application creation platform 110 may also determine that a user modification to the candidate description information is received in response to receiving a selection operation of the candidate description information by the user 140 in the conversation window. The selection operation includes, but is not limited to, a click operation, a long press operation, a sliding operation, and the like on the candidate description information.
[0059] In this way, after determining the candidate description information, the application creation platform 110 can adjust the candidate description information based on the user's modification to determine the description information of the target functional block.
[0060] like Figure 3 As shown, the application creation platform 110 may determine a plurality of atomic components 310 for implementing the target function, including atomic components 310-1, 310-2, ..., 310-M, where M is a positive integer greater than 1. The application creation platform 110 may be configured to: Figure 2 In blocks 210 and 220 of process 200, atomic components for implementing the target function are determined, and description information 332 is determined accordingly.
[0061] Return to reference Figure 2 In block 230 , the application creation platform 110 encapsulates the multiple atomic components and description information into a target function block for the application creation platform 110 to call to execute the target function.
[0062] In some embodiments, after the application creation platform 110 determines the description information for the target function block, it can encapsulate the description information and multiple atomic components together, and the encapsulation result is the target function block. The application creation platform 110 can store the target function block in a database for subsequent calls to execute the target function. Figure 3 As shown, the application creation platform 110 can encapsulate the description information 332 and multiple atomic components 310 (including atomic components 310-1, 310-2, ..., 310-M) into a target function block 330. The application creation platform 110 can store the target function block 330 in the database 130 for subsequent calling.
[0063] Figure 4 A schematic diagram of a target functional block 400 according to some embodiments of the present disclosure is shown. Figure 4 The target functional block 400 in may correspond to Figure 3 The target functional block 330 in the target functional block 400. The package of the target functional block 400 includes the description information of the target functional block and multiple atomic components. In some embodiments, the package of the target functional block 400 may also include the code of the functional block.
[0064] The target function block 400 may be, for example, a book borrowing function block. The description information of the target function block 400 includes a function identifier 411 of the target function block "book borrowing function", a semantic description 412 of the target function block "helping users borrow books", an input parameter 413 of the target function block "input is an ISBN number", and description information 414 of each of the multiple atomic components of the target function block, including description information 414-1 "description: contains information about the book", 414-2 "description: contains information about the book borrowed by the user", and 414-3 "description: performs a book borrowing operation". In some embodiments, the description information of the target function block 400 may also include output parameters of the target function block, and the output parameters may be, for example, "the borrowing status identifier of the book corresponding to the ISBN number output by the borrowing function" or "a reminder that the book cannot be borrowed".
[0065] The multiple atomic components encapsulated in the target functional block 400 may include, for example: Figure 4 The atomic components shown include API 415 - 1 , data tables 415 - 2 and 415 - 3 , and data flow 415 - 4 .
[0066] In some embodiments, the application creation platform 110 can call the target function block stored in the database to perform the target function. Specifically, the application creation platform 110 can receive user input, which can indicate the target task to be performed. The application creation platform 110 can receive user input from the conversation window between the user and the digital assistant. The application creation platform 110 can also receive user input in other appropriate ways. In some embodiments, the user input can include multimodal input, such as text input (e.g., input in the form of natural language), voice input, image input, video input, and the like.
[0067] The application creation platform 110 can determine whether the target task includes at least the target function, and in the case of determining that the target task includes at least the target function, at least trigger the call to the target function block to perform the target task. Regarding the determination method of the target function, in some embodiments, the application creation platform 110 can determine whether the target task includes at least the target function with the help of the model 125. Specifically, the application creation platform 110 can generate a prompt word input for the model 125 based at least on the description information of the target function block and the user input. The application creation platform 110 can fill the description information of the target function block and the user input into the input template of the model 125 through the prompt word project to generate the prompt word input for the model. The application creation platform 110 can provide the prompt word input to the model 125 to obtain an indication of whether the target task includes the target function. Alternatively or additionally, in some embodiments, the application creation platform 110 can also determine whether the target task includes at least the target function based on a pre-set identification rule.
[0068] In some embodiments, the application creation platform 110 may call at least a target function block from the database 130 to perform a target task. For example, if the application creation platform 110 receives a user input "help me build a library management system", the application creation platform 110 may determine that the target task indicated by the user input is a task of creating a library management system. The application creation platform 110 calls at least a target function block that can perform a target function matching the task of creating a library management system from the database 130 to perform the task of creating a library management system.
[0069] According to the scheme, multiple atomic components for realizing the target function are determined, and the multiple atomic components are used together to execute the target function in the task. Descriptive information for the target function block is determined and the multiple atomic components and the description information are encapsulated into a target function block for the application creation platform to call to execute the target function. In this way, multiple atomic components that can realize specific functions can be automatically encapsulated into a target function block that can be called as a whole during the use of the application creation platform. This can expand the task processing capability of the application creation platform, improve the efficiency of subsequent processing, and meet the diversified needs of users.
[0070] Figure 5 A schematic structural block diagram of an apparatus 500 for application processing according to some embodiments of the present disclosure is shown. The apparatus 500 may be implemented in or included in the application creation platform 110, for example. Each module / component in the apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.
[0071] As shown in the figure, the device 500 includes a composition determination module 510, which is configured to determine multiple atomic components for implementing the target function, and the multiple atomic components are provided by the application creation platform. The device 500 also includes a description determination module 520, which is configured to determine description information for the target function block, and the description information at least includes a semantic description of the target function. The device 500 also includes an encapsulation module 530, which is configured to encapsulate the multiple atomic components and the description information into a target function block, so that the application creation platform can call to execute the target function.
[0072] In some embodiments, the description information of the target function block also includes at least one of the following: a function identifier of the target function block, an input parameter of the target function block, an output parameter of the target function block, and description information of each of the multiple atomic components.
[0073] In some embodiments, the composition determination module 510 includes: an identification module configured to identify a target function block for executing a target function from a target application; and an extraction module configured to extract multiple atomic components defined for the target function block in the target application.
[0074] In some embodiments, the identification module is further configured to identify a target functional block from the target application based on the logical architecture information of the target application.
[0075] In some embodiments, the logical architecture information is at least partially extracted by the model from the code of the target application.
[0076] In some embodiments, the logical architecture information is extracted at least in part from annotation information associated with the target application.
[0077] In some embodiments, the composition determination module 510 includes: an interaction information acquisition module, configured to obtain interaction information between a user and a digital assistant during an interaction process for a target function, the digital assistant being associated with an application creation platform, the interaction information including at least description information of each of a plurality of atomic components; and a first determination module, configured to determine a plurality of atomic components required to perform the target function based on the interaction information.
[0078] In some embodiments, the first determination module includes: a first input generation module, configured to generate a prompt word input for the model based on at least a portion of the interaction information and a set of atomic components provided by the application creation platform; a first input module, configured to provide the prompt word input to the model; and an indication acquisition module, configured to obtain indications of multiple atomic components from the model.
[0079] In some embodiments, the description determination module 520 includes: a second input generation module, configured to generate a prompt word input for the model based on the description information of each of the multiple atomic components of the target functional block; a second input module, configured to provide the prompt word input to the model; and an information acquisition module, configured to obtain description information for the target functional block from the model.
[0080] In some embodiments, the description determination module 520 includes: a candidate description information generation module, configured to generate candidate description information for a target functional block; a candidate description information providing module, configured to provide candidate description information to a user; and a description information determination module, configured to determine the description information of the target functional block based on the received user modification or confirmation of the candidate description information.
[0081] In some embodiments, the device 500 also includes: a user input receiving module, configured to receive user input, the user input indicating a target task to be executed; a target function determination module, configured to determine whether the target task includes at least the target function; and a task execution module, configured to at least trigger a call to a target function block to execute the target task if it is determined that the target task includes at least the target function.
[0082] In some embodiments, the target function determination module includes: a third input generation module, configured to generate a prompt word input for the model based at least on the description information of the target function block and user input; and a third input module, configured to provide the prompt word input to the model to obtain an indication of whether the target task includes the target function.
[0083] The modules included in the device 500 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more 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 modules in the device 500 can be implemented at least in part by one or more hardware logic components. As an 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 the like.
[0084] Figure 6 1 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 Figure 6 The electronic device 600 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 6 The electronic device 600 shown may be used to implement or partially implement Figure 1 The application creation platform 110 is provided.
[0085] like Figure 6 As shown, the electronic device 600 is in the form of a general electronic device. The components of the electronic device 600 may include, but are not limited to, one or more processors or processing units 610, a memory 620, a storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. The processing unit 610 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 620. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 600.
[0086] The electronic device 600 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 620 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 630 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 600.
[0087] The electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 6 As shown in , 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 the 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 that are configured to perform various methods or actions of various embodiments of the present disclosure.
[0088] The communication unit 640 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 600 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, 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.
[0089] The input device 650 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 660 may be one or more output devices, such as a display, a speaker, a printer, etc. 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, etc., communicate with one or more devices that allow a user to interact with the electronic device 600, or communicate 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).
[0090] 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.
[0091] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.
[0092] 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, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0093] 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, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0094] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be 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.
[0095] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.
Claims
1. An application processing method, comprising: Determine a plurality of atomic components for realizing a target function, wherein the plurality of atomic components are provided by an application creation platform; Determining description information for the target function block, the description information at least including a semantic description of the target function; as well as The multiple atomic components and the description information are encapsulated into the target function block, so that the application creation platform can call it to execute the target function.
2. The method according to claim 1, wherein the description information of the target functional block further includes at least one of the following: The function identifier of the target function block, The input parameters of the target function block, the output parameters of the target function block, and The description information of each of the multiple atomic components.
3. The method of claim 1 , wherein determining the plurality of atomic components comprises: identifying the target function block for performing the target function from a target application; as well as A plurality of atomic components defined for the target functional block in the target application are extracted.
4. The method of claim 3, wherein identifying the target functional block from the target application comprises: The target functional block is identified from the target application based on the logical architecture information of the target application. 5 . The method of claim 4 , wherein the logical architecture information is at least partially extracted by a model from code of the target application. 6 . The method of claim 4 , wherein the logical architecture information is extracted at least in part from annotation information associated with the target application.
7. The method of claim 1 , wherein determining the plurality of atomic components comprises: Obtaining interaction information between a user and a digital assistant during an interaction process for the target function, wherein the digital assistant is associated with the application creation platform, and the interaction information at least includes description information of each of the multiple atomic components; as well as A plurality of atomic components required for executing the target function is determined based on the interaction information.
8. The method of claim 7, wherein determining the plurality of atomic components based on the interaction information comprises: Generate a prompt word input for a model based on at least a portion of the interactive information and a set of atomic components provided by the application creation platform; providing the cue word input to the model; and An indication of the plurality of atomic components is obtained from the model.
9. The method according to claim 1, wherein determining the description information of the target functional block comprises: Generating prompt word input for a model based on the description information of each of the plurality of atomic components of the target functional block; providing the cue word input to the model; and The description information for the target functional block is obtained from the model.
10. The method according to claim 1, wherein determining the description information of the target functional block comprises: Generating candidate description information for the target functional block; Providing the candidate description information to the user; as well as Based on the modification or confirmation of the candidate description information received from the user, the description information of the target functional block is determined.
11. The method according to claim 1, further comprising: receiving user input, the user input indicating a target task to be performed; determining whether the target task at least includes the target function; as well as If it is determined that the target task at least includes the target function, at least a call to the target function block is triggered to execute the target task.
12. The method according to claim 11, wherein determining whether the target task includes at least the target function comprises: generating a prompt word input for a model based at least on the description information of the target functional block and the user input; as well as The cue word input is provided to the model to obtain an indication of whether the target task includes the target function.
13. An apparatus for application processing, comprising: A composition determination module, configured to determine a plurality of atomic components for realizing a target function, wherein the plurality of atomic components are provided by an application creation platform; A description determination module, configured to determine description information for the target function block, wherein the description information at least includes a semantic description of the target function; as well as The encapsulation module is configured to encapsulate the multiple atomic components and the description information into the target function block, so that the application creation platform can call it to execute the target function.
14. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 12 when executed by the at least one processing unit.
15. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 12.
Citation Information
Cited By
Vehicle function development method and device, electronic equipment and storage medium
CN121255145A
