Task execution method and apparatus, device, and storage medium
By identifying user intentions and combining functional blocks and data flows to automatically combine tasks to execute tasks, the existing application creation platform is solved, and the real-time and flexible execution of tasks is achieved, and the user experience is improved.
Patent Information
- Application Number
- PCT/CN2024/094316
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-24
- Filing Date
- 2024-05-20
- Publication Date
- 2024-11-28
AI Technical Summary
Existing application creation platforms are difficult to meet users' long-tail needs flexibly and conveniently, especially those who do not want to participate in the application creation process. They cannot provide applications that match the needs in a more flexible way or directly perform tasks that are intended by users.
By identifying user intentions, combining multiple functional blocks and associated data streams, a chain of calls is automatically formed, and tasks are performed using the functional blocks provided by the low-code platform, and applications are generated under preset conditions to meet user needs.
Realize the instant and flexible execution of tasks, which can better meet users' needs for expressing them through natural language, and improve application flexibility and user experience.
Smart Images

Figure CN2024094316_28112024_PF_FP_ABST
Abstract
Description
Method, apparatus, device and storage medium for performing tasks
[0001] This application claims priority to the Chinese invention patent application with application number 202310594243.1 filed on May 24, 2023, entitled “Methods, devices, equipment and storage media for performing tasks”, the entire contents of which are incorporated by reference into this application. Technical Field
[0002] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for performing tasks. Background Art
[0003] With the advancement of computer technology, various terminal devices can provide a variety of services for people in work and daily life. For example, terminal devices can be deployed with general applications that provide services. Terminal devices can also be deployed with application creation platforms. Such application creation platforms allow users to create applications that meet their needs. For example, users can build interfaces, establish databases, create corresponding processes, and perform operation and maintenance.
[0004] Summary of the Invention
[0005] In a first aspect of the present disclosure, a method for executing a task is provided. The method includes determining a task to be executed based on a user intent identified in response to user input. A group of function blocks is determined based on a plurality of function blocks and data flows associated with the task. The task is executed using the group of function blocks.
[0006] In a second aspect of the present disclosure, a device for executing a task is provided. The device includes: a task determination module configured to determine a task to be executed based on a user intent identified in response to a user input; a function block determination module configured to determine a set of function blocks based on a plurality of function blocks and a data flow associated with the task; and an execution module configured to execute the task using the combined set of function blocks.
[0007] In a third aspect of the present disclosure, a device for performing a task is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.
[0008] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.
[0009] In a fifth aspect of the present disclosure, a method for executing a task is provided. The method includes determining a task to be executed based on user intent identified in response to user input. The task is executed using a set of function blocks provided by a low-code platform. In response to a preset condition being met, an application for executing the task is generated based on the set of function blocks.
[0010] In a sixth aspect of the present disclosure, a device for executing a task is provided. The device includes: a task determination module configured to determine a task to be executed based on a user intent identified in response to a user input; an execution module configured to execute the task using a set of function blocks provided by a low-code platform; and a generation module configured to generate an application for executing the task based on the set of function blocks in response to a preset condition being met.
[0011] In a seventh aspect of the present disclosure, a device for processing a task is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the fifth aspect.
[0012] In an eighth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the fifth aspect.
[0013] It should be understood that the content described in this summary 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
[0014] 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:
[0015] FIG1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;
[0016] FIG2 shows a schematic diagram of an example architecture for performing tasks according to some embodiments of the present disclosure;
[0017] FIG3 shows a schematic diagram of an example for executing a ticket booking task according to some embodiments of the present disclosure;
[0018] FIG4 shows a flowchart of a method for performing a task according to some embodiments of the present disclosure;
[0019] FIG5 shows a block diagram of an apparatus for performing a task according to some embodiments of the present disclosure;
[0020] FIG6 shows a flowchart of a method for processing a task according to some embodiments of the present disclosure;
[0021] FIG7 shows a block diagram of an apparatus for processing tasks according to some embodiments of the present disclosure; and
[0022] FIG8 shows a block diagram of a device capable of implementing various embodiments of the present disclosure. DETAILED DESCRIPTION
[0023] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.
[0024] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below.
[0025] In this document, unless explicitly stated otherwise, "performing a step in response to A" does not necessarily mean executing the step immediately after "A," but rather may include one or more intermediate steps. It is understood 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 provisions.
[0026] It is understood that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scope of use, and usage scenarios of the information involved in the present disclosure should be informed to the relevant users and the authorization of the relevant users should be obtained in an appropriate manner in accordance with relevant laws and regulations, wherein the relevant users may include any type of right holders, such as individuals, enterprises, and groups. 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 autonomously choose whether to provide information to the application creation platform, application, server, or storage medium and other software or hardware that performs the operation of the technical solution of the present disclosure based on the prompt message.
[0027] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message may be sent to the relevant user in the form of a pop-up window, in which the prompt message may be presented in text form. Furthermore, the pop-up window may also include a selection control for the user to select "agree" or "disagree" to provide information to the application creation platform.
[0028] 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 comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.
[0029] As briefly mentioned above, developers can use application creation platforms to build, deploy, use, update, and manage applications based on their needs, thereby providing users with applications that meet their needs. However, due to the limitations of application creation platforms' capabilities, or in other words, such platforms can only create applications, for users who are only interested in the services they can provide and do not want to participate in application creation, such application creation platforms cannot meet users' long-tail needs in a more flexible and convenient way. In addition, sometimes users' specific needs may not be met by these existing applications. Therefore, providing users with applications that match their needs or directly performing the tasks indicated by the needs is a technical issue that needs to be explored.
[0030] Due to the more accurate semantic understanding and contextual reasoning capabilities brought by the model, users can express their intent (for example, using multimodal forms involving natural language) and interact with applications, while applications can interact with the model through natural language interfaces. In this case, it is expected that applications can make fuller use of natural language to make the application more flexible. It will be understood that in the context of this disclosure, a "model" can be a machine learning model.
[0031] To this end, embodiments of the present disclosure provide a solution for executing tasks. According to various embodiments of the present disclosure, a task to be executed is first determined based on user intent identified in response to user input. A set of function blocks is then determined based on multiple function blocks and data flows associated with the task. The task is then executed using this combined set of function blocks.
[0032] According to embodiments of the present disclosure, the function blocks required to meet user needs can be determined based on user intent identified from user input. Based on the functions of each function block and the underlying dependencies, a call chain is automatically formed, and these function blocks are combined to meet user needs. This allows for instant and flexible user needs to be met using a natural language interface.
[0033] Example embodiments of the present disclosure are described below with reference to the accompanying drawings.
[0034] Figure 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In the environment 100, an application creation platform 110 (e.g., a platform implemented based on low-code technology, also referred to as a low-code platform) can be used by users 140 who desire to create and maintain applications to create and maintain applications 150. In some embodiments, the application creation platform 110 can also be regarded as an application that provides application creation services. In some embodiments, the application creation platform 110 can be a platform based on application platform as a service (aPaas). The application creation platform 110 can understand the input of the user 140 through the model 120. In some embodiments, the application creation platform 110 can select appropriate functional blocks from the functional block library 130 and generate an application 150 based on part or all of the selected functional blocks.
[0035] In some embodiments, the application creation platform 110 can run a digital assistant 115. The digital assistant 115 can be integrated into the application creation platform 110 to be used to interact with the user 140. The digital assistant 115 can also run independently outside the application creation platform 110. The digital assistant 115 can be called or awakened by an appropriate method (for example, a shortcut key, a button, or voice), and then present an interaction window (for example, a conversation window) with the user 140. Such a conversation window can be presented in the client interface of the application creation platform 110. The conversation window can include interface elements for information interaction, such as an input box, a message list, a message bubble, and the like. As an intelligent assistant, the digital assistant 115 has intelligent dialogue and information processing capabilities. The digital assistant 115 can receive conversation messages entered by the user 140 in the conversation window and provide reply messages. In some embodiments, the digital assistant 115 can be acquired based on a model different from the model 120.
[0036] The application creation platform 110 may be run on an appropriate electronic device. In some embodiments, the function block library 130 may be stored as part of the application creation platform 110. In some embodiments, the model 120 and the application creation platform 110 may be run on different electronic devices.
[0037] The electronic device here can be any type of device with computing capabilities, including terminal devices or server devices. The terminal device can be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can, for example, include a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like.
[0038] In some embodiments, the electronic device may run a client of the application creation platform 110, which may support interaction with the application creation platform 110. When the application creation platform 110 runs on the user's terminal device, the user 140 may interact with the application creation platform 110 via the client. When the application creation platform 110 runs on a server device, the application creation platform 110 may provide services to the client running on the terminal device based on the communication connection between the server device and the terminal device.
[0039] 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.
[0040] FIG2 shows a schematic diagram of an example architecture 200 for performing tasks according to some embodiments of the present disclosure. The example architecture 200 can be implemented in the environment 100. The example architecture 200 is described below with reference to FIG1.
[0041] According to an exemplary implementation of the present disclosure, user input can describe user intent and can be multimodal. Multimodal input can include, for example, at least one of the following: text input describing the user intent in natural language, voice input, image input, or video input. For ease of description, the following description of the task execution process will only use text as an example of user input expressed in natural language.
[0042] In the example of FIG2 , the application creation platform 110 receives user input 210 in natural language from the user 140. In this way, the immediacy and flexibility of performing tasks can be improved. Such natural language can include text, voice, or a combination thereof. The application creation platform 110 can provide any suitable type of interface to receive the user input 210.
[0043] User input 210 may indicate a task 220 to be performed. Task 220 may be determined by parsing user input 210. In one example, application creation platform 110 receives user input 210 in text form, such as "Please order two cups of coffee for me." Application creation platform 110 parses the text and determines that the task to be performed is "order coffee." In another example, application creation platform 110 receives user input 210 in speech form, such as user 140 saying "book a flight to X." Application creation platform 110 parses the speech and determines that the task to be performed includes booking a flight.
[0044] The task parsing described herein can be performed by the application creation platform 110 itself, or by the application creation platform 110 utilizing the model 120. In some embodiments, the application creation platform 110 can determine the task to be performed using the model 120. The model 120 is, for example, a language model. The application creation platform 110 can send user input 210 to the model 120. It should be understood that any suitable language model can be utilized to determine the task to be performed based on the user input 210 represented in natural language, and this disclosure is not intended to limit the determination process.
[0045] The application creation platform 110 can determine a group of function blocks 240 based on the data flow associated with the task and multiple function blocks. The data flow associated with the task includes the various data and flow directions required to complete the task. As an example, the task is "help me generate a photo album and email it to me." In order to complete this task, the materials required to generate the photo album (for example, individual images), the requirements for the photo album, and other data need to be provided to the photo album generation module, and the user's email address needs to be provided to the email sending module. In addition, the generated photo album needs to be provided from the photo album generation module to the email sending module. For example, upstream function blocks, intermediate function blocks, downstream function blocks, etc. can be determined based on the data flow, and these function blocks can be used as a group of function blocks 240. Further, the application creation platform 110 can use the combined group of function blocks 240 to perform task 220. In this way, each function block can be flexibly combined to meet user needs based on its own functions and the dependencies behind them.
[0046] In some embodiments, the set of function blocks 240 may be determined from a function block library 130 comprising multiple function blocks 230. That is, these function blocks 230 are provided by the function block library 130. The multiple function blocks 230 may include applications and / or components within applications. Applications may include any type of application, including but not limited to office applications, utility applications, entertainment applications, shopping applications, social applications, and the like. Components may include but are not limited to audio and video conferencing components, email components, calendar components, schedule components, payment components, chat components, and the like. Application components may include, for example, a calendar component in an office application or a voiceprint recognition component in a utility application. Each of the multiple function blocks 230 may be either an application or a component within an application. Compared to applications, components within applications implement more refined functionality. Therefore, in these embodiments, these function blocks may be used to implement functionality with varying degrees of refinement (also known as granularity). This allows for greater flexibility in the selection and combination of function blocks, better meeting user needs expressed through natural language. Additionally or alternatively, the application creation platform 110 may store newly installed applications or components in the applications in the function block library 130 to perform more diverse tasks.
[0047] In some embodiments, the application creation platform 110 can determine a function block that matches the task 220 from the plurality of function blocks 230 based on the respective description information of the plurality of function blocks 230, and use it as at least part of a set of function blocks 240. The description information of each function block includes at least a semantic description of the function of the function block. Such a semantic description is in a form that is understandable to the model 120. The understandable form means that the language and format of the text meet the preset requirements of the model 125. The description information can also indicate the inputs and outputs of the function block, as well as the requirements for the inputs and outputs (e.g., format). In this way, the model 120 can select a function block that matches the task 220.
[0048] In some embodiments, the application creation platform 110 may send user input 210 and description information of multiple function blocks 230 to the model 120. The model 120 may determine the task 220 to be performed based on semantic analysis of the user input 210, and determine the function of each function block based on semantic analysis of the description information, thereby selecting a function block to perform the task.
[0049] In some embodiments, the application creation platform 110 can generate prompt word input based on the description information of each of the multiple functional blocks 230 and the user input 210. Such prompt word input is also called a prompt word, a guide word, etc. to the model. Furthermore, the application creation platform 110 provides the description information of each of the multiple functional blocks 230, the user input 210, and the prompt word input to the model 120. Based on the prompt word input, the model 120 can better understand the user input 210 and thus select a more appropriate functional block that matches the task 220. The application creation platform 110 obtains an indicator of the functional block that matches the task 220 from the model 120. In other words, the model 120 can indicate or notify the application creation platform 110 of the determined functional block so that the application creation platform 110 can subsequently combine it.
[0050] In some embodiments, the application creation platform 110 can receive user input 210 and interact with the user 140 through the digital assistant 115. The digital assistant 115 can be a model-based assistant. The digital assistant 115 has intelligent dialogue and information processing capabilities (e.g., processing text, voice, image, or video, etc.). For example, in a conversation window between the user 140 and the digital assistant 115, the user 140 can enter a conversation message, and the digital assistant 115 can provide a reply message or provide option information for the user 140 to select in response to the conversation message. In this way, a convenient interface can be provided for the user to express and clarify needs.
[0051] For example, for the "order coffee" task, digital assistant 115 receives a conversation message from user 140, "Please order two cups of coffee for me." To further clarify the user's request, digital assistant 115 asks user 140, "Which store / brand of coffee would you like to order?" After receiving user 140's response, application creation platform 110 can provide the entire conversation message or processed conversation message to model 120.
[0052] As another example, user 140 says "I want to borrow a book from the library." The application creation platform 110 analyzes the voice and determines that the user's need is "borrow a book." In order to further clarify the user's need, the digital assistant 115 can present a list of new books in the conversation window. After receiving the trigger operation of the user 140 (such as clicking on a book), the digital assistant 115 can present the cover, preface, trial reading chapters and other information of the book. The digital assistant 115 can also provide this information to the model 120 after receiving the confirmation operation of the user 140 (for example, the user 140 says "borrow this book for me").
[0053] Alternatively or additionally, the explicit or clarified requirements described above may also be implemented by the application creation platform 110 using the model 120 .
[0054] In some embodiments, the application creation platform 110 can interact with the user 140 (e.g., via the digital assistant 115) during the parsing or execution of the task 220. The interactive information can be in the form of text, images, audio, video, or any other appropriate format. For example, for the task of "booking a flight," the application creation platform 110 can query multiple matching flight information through a function block that supports flight booking. Furthermore, the application creation platform 110 can send this flight information to the user 140 in text format via the digital assistant 115 for the user 140 to make a selection.
[0055] In some embodiments, the application creation platform 110 can generate strategies or auxiliary information based on the user input 210 and provide it to the model 120. Such strategies or auxiliary information are used to at least guide the model 120 in understanding the user input 210 and selecting functional blocks. Considering that the model 120 may be a general model and may not be able to determine the information processing strategy in a specific domain or scenario, providing such strategies or auxiliary information to the model 120 can help the model 120 perform analysis and processing according to the preset strategy, so that the tasks to be executed and the functional blocks selected by the model 120 are more likely to meet expectations.
[0056] In some embodiments, the functional block matching task 220 may include multiple candidate modules for performing at least a portion of the task. These candidate modules at least partially implement the same or similar functions. For example, these candidate modules may all implement air ticket booking. In this case, the application creation platform 110 may provide an indication of these candidate modules to the user 140. The user may select a target candidate module from these candidate modules. Based on the user 140's selection of the target candidate module, the application creation platform 110 may remove other candidate modules other than the target candidate module. In this way, the task can be performed efficiently in a manner that better meets the user's expectations.
[0057] In some scenarios, when the application creation platform 110 analyzes user input through the model 120 and selects function blocks, the model 120 may split the task 220 into multiple subtasks. When selecting function blocks based on these subtasks and the descriptions of the multiple function blocks 230, the model 120 may provide feedback that no function blocks are available to perform one or more subtasks. In some embodiments, in response to such feedback, the application creation platform 110 may rewrite function blocks from the multiple function blocks 230 to create function blocks for performing such subtasks. Additionally or alternatively, the application creation platform 110 may create new function blocks. For example, it may split existing function blocks into smaller function blocks or create new function blocks from scratch. In this way, user requirements can be met to the greatest extent possible. The rewritten function blocks and / or newly created function blocks can be combined with function blocks selected from the function block library 130 to perform the task 220.
[0058] The following describes an example of combining a group of function blocks 240. In some embodiments, the application creation platform 110 may determine the execution order of the group of function blocks 240 based on the data flow associated with the task 220, and combine the group of function blocks 240 according to the execution order. Such data flow may include data transmitted between the individual function blocks. Based on the direction of data flow, the application creation platform 110 may combine the group of function blocks 240 in a sequential manner. Such sequential combination may be, for example, serial, parallel, or at least partially parallel.
[0059] In some embodiments, the application creation platform 110 may determine an endpoint function block in a set of function blocks 240 based on endpoint data in a data stream associated with the task 220. Such endpoint data may include input data, output data, or a combination of input data and output data in the data stream. Such an endpoint function block may include a start module, an end module, or both in a set of function blocks 240. The application creation platform 110 may determine the start module based on the input data and may also determine the end module based on the output data. Continuing with the example task of "booking a flight," the input data may include user information (e.g., information about "me") and the output data may include information about the flight booked. The application creation platform 110 may select a function block that identifies the user based on the input data (which is the start module in this example) and select a function block that supports flight booking based on the output data (which is the end module in this example).
[0060] As another example, for the task of "ordering coffee," the input data may include parameter information such as coffee type, cup size, hot or cold, and may also include information such as the delivery address and payment account number. The output data may include coffee order information. Based on such an endpoint data flow, the application creation platform 110 may determine, from multiple function blocks 230, a function block that supports coffee delivery, a function block that stores user preferences, and a function block that contains payment account information. In some scenarios, the application creation platform 110 determines multiple function blocks that support coffee delivery from multiple function blocks 230. The application creation platform 110 may use these function blocks as candidate modules and send options to the user 140. Based on the selections of the user 140, the application creation platform 110 determines a set of function blocks for performing the "order coffee" task.
[0061] The application creation platform 110 can perform semantic analysis on textual user input 210 using a model 120 (e.g., a language model). In some embodiments, the application creation platform 110 can select a natural language recognition module from a plurality of functional blocks 230 to parse the user input 210 to assist the model 120 in determining the task 220 to be performed. Such language recognition modules include, but are not limited to, voiceprint recognition modules, speech recognition modules, facial expression recognition (e.g., lip recognition, eye tracking) modules, gesture recognition modules, and the like.
[0062] In some embodiments, the application creation platform 110 determines, from a set of function blocks 240, adjacent function blocks adjacent to the endpoint function block based on the interface data of the endpoint function block. The endpoint function block and the adjacent function blocks can communicate via the interface data. Such adjacent function blocks may include a predecessor module and / or a successor module of the endpoint function block. The interface data may include input interface data and / or output interface data.
[0063] Continuing with the "book a flight" example task, the application creation platform 110 selects a function block that supports flight booking based on the output data. The input interface data of this endpoint function block may include user information, invoice information, and payment account information. Furthermore, based on this interface data, the application creation platform 110 selects predecessor modules, such as a function block that stores user information (e.g., name, ID number, etc.), a function block that stores invoice information, and a function block that stores payment account information. The output interface data of this endpoint function block may include outputting invoices, flights, etc. Based on this interface data, the application creation platform 110 selects subsequent modules, such as a function block that supports sending text messages to user 140, a function block that supports sending pictures to user 140, and so on.
[0064] Additionally or alternatively, the application creation platform 110 selects a feedback module from the plurality of functional blocks 230 to transmit an execution result 250 to the user 140. Feedback modules include, but are not limited to, calendar modules and schedule modules. For example, the application creation platform 110 can use the calendar module to add a flight itinerary as a task reminder. Additionally or alternatively, the application creation platform 110 can transmit the execution result 250 directly to the user 140. For example, the application creation platform 110 can announce the successful flight reservation and detailed reservation information in voice.
[0065] The application creation platform 110 can select a group of function blocks 240 from multiple function blocks 230. Such a group of function blocks 240 may include multiple adjacent function blocks, such as adjacent first and second function blocks. In some embodiments, the application creation platform 110 determines that the format of the output data of the first function block is consistent with the format of the input data of the second function block, and then the two function blocks can be combined. For example, in the example task of "booking a flight", the first function block is a voiceprint recognition module that can identify the identity of the user 140, thereby outputting the user's name in text format. The second function block is a function block that supports flight booking, which can receive the user's name in text format and select the added certificate information to output the booked flight information. Thus, the application creation platform 110 can directly combine the two matching function blocks.
[0066] In some embodiments, the combined first and second function blocks can be added to a cache of a function block library comprising a plurality of function blocks to form a third function block. Here, the input data of the third function block formed is the same as the input data of the first function block, and the output data of the third function block is the same as the input data of the second function block. In other words, a temporary function block generated using an existing function block can be stored in the cache, and the temporary function block can be used as the basis for subsequent combined functions. At this point, the temporary function module can implement more complex functions, and the temporary function block can be combined with other function blocks in the function block library. In some embodiments, the cache can be updated regularly, for example, when a temporary function block has not been used for a long time (for example, more than one month or other time period), the temporary function block is deleted. For another example, if a temporary function block is frequently used later, the temporary function block can be moved from the cache to the function block library.
[0067] In some scenarios, the first format of the output data of the first functional block is inconsistent with the second format of the input data of the second functional block. In some embodiments, the application creation platform 110 first uses the conversion module to convert the data in the first format into data in the second format, and then combines the first functional block, the conversion module, and the second functional block. For example, in the example task of "borrowing a book", the first functional block is a functional block that stores the library card of the user 140, and its output data is the library card in the image format. The second functional block is a functional block that supports book borrowing, and its input data is the document number in the text format. Therefore, the application creation platform 110 can use the format conversion module to convert the output data in the image format into the input data in the text format, thereby combining the two functional blocks through the format conversion module.
[0068] In some embodiments, the application creation platform 110 uses a customized function block based on the first format and the second format as a conversion module. Additionally or alternatively, the application creation platform 110 obtains a third-party function block based on the first format and the second format and uses it as a conversion module.
[0069] In some embodiments, the application creation platform 110 can add the conversion module to the plurality of function blocks 230. For example, the format conversion module is stored in the function block library 130 so that it can be directly selected and combined with other function blocks when needed.
[0070] In some embodiments, the combined set of function blocks 240 can be used to perform other tasks. For example, the application creation platform 110 can receive another user input expressed in natural language from a user (who may be another user different from user 140) and determine another task to be performed by parsing the other user input. Furthermore, in response to determining that the other task is of the same type as a previously performed task, the application creation platform 110 uses the combined set of function blocks 240 to continue performing the other task. In this way, the efficiency of executing tasks can be improved. For example, after the application creation platform 110 completes the task of "booking a flight" for user A using a set of function blocks 240, it receives the task of "booking a flight" from user B. The application creation platform 110 can continue to use the set of function blocks 240 to perform the task of "booking a flight" for user B without having to reselect function blocks from the multiple function blocks 230 and combine them.
[0071] In some embodiments, the application creation platform 110 generates an application using a combined set of function blocks 240 and stores the application, for example, by adding it to the function block library 130. In other words, such an application can be added to multiple function blocks 230 as a function block with greater granularity. Such an application can also directly provide services to users 140, just like other general-purpose applications. Additionally or alternatively, users 140 can update, manage, operate, and maintain the generated application through the application creation platform 110.
[0072] In some embodiments, the combined set of function blocks can be directly used to perform a task, in which case a new application is not generated. Alternatively and / or additionally, the combined set of function blocks can be used to generate a new application, and the new application can be added to the function block library so as to be treated as another function block. In this case, the number of function blocks in the function block library will change.
[0073] In some embodiments, whether to use the combined set of function blocks to generate an application can be determined based on whether a preset condition is met. The preset condition can include various aspects, such as the number of times a task is executed, the frequency of execution of the task, and whether a generation instruction has been received. For example, the application creation platform 110 accumulates the number of executions associated with a certain type of task 220. When it is determined that the number of executions of that type of task exceeds a threshold, the application creation platform 110 uses the combined set of function blocks 240 to generate an application for performing that type of task. Alternatively and / or additionally, the application creation platform 110 accumulates the frequency of execution associated with the certain type of task 220. When it is determined that the execution frequency exceeds a threshold frequency (e.g., three times per week, and / or another value), the application creation platform 110 uses the combined set of function blocks 240 to generate the application. Alternatively and / or additionally, the application can be generated using the combined set of function blocks 240 in response to receiving a generation instruction (e.g., a generation instruction input by a user, and / or a generation instruction set in the application creation platform 110). In this way, tasks that are executed frequently can be handled efficiently.
[0074] In summary, according to various embodiments of the present disclosure, the application creation platform 110 can utilize the model 120 to analyze user input 210 to determine a task 220, and can also determine a set of function blocks 240 that can execute the task 220 based on the description information of multiple function blocks 230. The application creation platform 110 can directly execute a temporary task by sequentially combining a set of function blocks 240, or it can generate an application that can be called upon at any time to execute the same type of task. Furthermore, the application creation platform 110 can improve the immediacy, flexibility, and comprehensiveness of task execution by adjusting function blocks, creating new function blocks, or adding generated applications to a function block library.
[0075] To more clearly understand the task execution scheme of the fundamentally disclosed embodiments, a specific example is described below with reference to FIG3 . FIG3 shows a schematic diagram of an example 300 for executing a ticket booking task according to some embodiments of the present disclosure. Example 300 represents an office scenario, where multiple users can share the application creation platform 110. Example 300 can be implemented in environment 100. Example 300 is described below with reference to FIG3 .
[0076] For example, user A says, "Book a flight to X." The application creation platform 110 receives user A's voice input and sends it, along with descriptions of each function block in the function block library 130, to the model 120. The model 120 or application creation platform 110 can perform semantic analysis on the voice input or convert the voice input into text and then perform semantic analysis to determine that the task to be performed is "book a flight." The data stream associated with this task may include user information, invoice information, payment account information, etc. Based on this data stream, the model 120 determines the function of each function block based on semantic analysis of the description information, thereby selecting the function block that performs the task. For example, if the model 120 analyzes the input data as the spoken word "I," it selects the voiceprint recognition module 301 (e.g., as the starting module) to determine user information, such as name and ID number. The model 120 analyzes the output data as "flight ticket" and selects the ticketing module 305 (e.g., as the ending module) to book the flight. After determining the starting and ending modules, the model 120 continues analyzing the data stream or description information to determine adjacent function blocks. For example, the ticketing module 305 requires data such as user name, ID number, destination, travel date, payment account, etc. Therefore, the model 120 selects the personnel module 302, the schedule module 303, and the finance module 304 as the predecessor modules, and selects the email module 306 as the successor module.
[0077] Furthermore, the application creation platform 110 receives the selection of the above-mentioned functional blocks from the model 120 and combines them in order to perform the "book a flight ticket" task. During the execution of the task, the voiceprint recognition module 301 processes the voice input to output the user's identification information (for example, name, employee number, etc.). The personnel module 302 receives the user's identification information and outputs the user's ID number and user name. The schedule module 303 receives the user's name and outputs the destination and travel date. The financial module 304 receives the user's name and outputs the payment account number, invoice information, etc. The ticketing module 305 receives the above information and outputs the electronic ticket. The email module 306 receives the electronic ticket and outputs an email containing flight information. In this way, the task of booking a flight ticket for user A is completed through the combination of a group of functional blocks.
[0078] Furthermore, the application creation platform 110 receives a task requesting to book an air ticket from another user B. The application creation platform 110 can use a combination of the above functional blocks or a stored application to execute the task of booking an air ticket for user B again.
[0079] In some scenarios, if the model 120 analyzes that the output data format of the ticketing module 305 is inconsistent with the input data format of the email module 306, the conversion module 320 may be selected for data format conversion. Thus, the application creation platform 110 can combine the above functional blocks through the conversion module 320.
[0080] 4 shows a flow chart of a method 400 for executing a task according to some embodiments of the present disclosure. The method 400 may be implemented at an electronic device running the application creation platform 110. The method 400 is described below with reference to FIG1.
[0081] At block 410, a task to be performed is determined based on the user intent identified with respect to the user input. At block 420, a set of function blocks is determined based on the plurality of function blocks and the data flows associated with the task. At block 430, the task is performed using the combined set of function blocks.
[0082] In some embodiments, based on the respective description information of the multiple functional blocks, a functional block matching the task can be determined from the multiple functional blocks as at least a part of a group of functional blocks, and the description information of each functional block includes at least a semantic description of the function of the functional block.
[0083] In some embodiments, a prompt word input may be generated based on the description information of each of the plurality of functional blocks and the user input; the prompt word input may be provided to the model; and an indicator of the functional block matching the task may be obtained from the model.
[0084] In some embodiments, method 400 also includes: in response to determining that the functional block matching the task includes multiple candidate modules for performing at least a portion of the task, providing a prompt of multiple candidate modules to the user; and based on the user's selection of a target candidate module among the multiple candidate modules, removing other candidate modules other than the target candidate module from the functional block matching the task.
[0085] In some embodiments, the method 400 further includes: determining an order of the set of functional blocks based on the data flow; and combining the set of functional blocks in the order.
[0086] In some embodiments, an endpoint function block in a set of function blocks can also be determined based on endpoint data in a data stream, where the endpoint data includes at least any one of the following items in the data stream: input data, output data, and the endpoint function block includes at least any one of the following items in a set of function blocks: a start module, an end module.
[0087] In some embodiments, based on the interface data of the endpoint functional block, an adjacent functional block adjacent to the endpoint functional block can be determined from a group of functional blocks. The endpoint functional block and the adjacent functional block communicate via the interface data. The adjacent functional block includes at least any one of the following items of the endpoint functional block: a predecessor module and a successor module.
[0088] In some embodiments, for a first functional block and a second functional block in a group of functional blocks, in response to determining that a first format of output data of the first functional block is consistent with a second format of input data of the second functional block, the first functional block and the second functional block can be combined, where the first functional block and the second functional block are adjacent functional blocks arranged in sequence.
[0089] In some embodiments, method 400 further includes: adding the combined first functional block and second functional block to a cache of a functional block library comprising a plurality of functional blocks to form a third functional block, the input data of the third functional block being the same as the input data of the first functional block, and the output data of the third functional block being the same as the input data of the second functional block.
[0090] In some embodiments, the method 400 further includes: in response to determining that the first format and the second format are inconsistent, converting the first format to the second format using a conversion module; and combining the first functional block, the conversion module, and the second functional block.
[0091] In some embodiments, the method 400 further includes adding the conversion module to a function block library comprising a plurality of function blocks.
[0092] In some embodiments, the conversion module is obtained based on at least any one of the following: a function block defined based on the first format and the second format; a third-party function block obtained based on the first format and the second format.
[0093] In some embodiments, method 400 also includes: in response to determining that multiple functional blocks cannot perform at least a portion of the tasks, creating a functional block for performing at least a portion of the tasks based on any of the following: rewriting a functional block in the multiple functional blocks; and creating a new functional block different from the multiple functional blocks.
[0094] In some embodiments, method 400 further includes: receiving another user input expressed in a natural language from the user; parsing the other user input to determine another task to be performed; and in response to determining that the task is of the same type as the other task, performing the other task using the combined set of functional blocks.
[0095] In some embodiments, the method 400 further includes: generating an application using the combined set of function blocks; and adding the application to a function module library including the plurality of function blocks.
[0096] In some embodiments, the application may also be generated in response to determining that a threshold condition is satisfied by the received user input associated with the type of task.
[0097] In some embodiments, method 400 further includes: determining that the user input satisfies a threshold condition in response to at least any one of the following: the number of user inputs exceeds a threshold number; the frequency of user inputs exceeds a threshold frequency.
[0098] In some embodiments, the plurality of function blocks are provided by a function block library and include at least any one of the following: an application, or a component in an application.
[0099] In some embodiments, the user input includes a multimodal form, and the multimodal form includes at least any one of the following: text input describing the user's intention in natural language, voice input, image input, and video input.
[0100] Figure 5 shows a schematic structural block diagram of an apparatus 500 for performing a task according to certain embodiments of the present disclosure. Apparatus 500 may be implemented as or included in an electronic device running application creation platform 110. Each module / component in apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.
[0101] As shown, apparatus 500 includes a task determination module 510 configured to determine a task to be executed based on a user intent identified in response to a user input. Apparatus 500 also includes a function block determination module 520 configured to determine a set of function blocks based on a plurality of function blocks and a data flow associated with the task. Apparatus 500 also includes an execution module 530 configured to execute the task using the combined set of function blocks.
[0102] In some embodiments, the function block determination module 510 is configured to determine a function block that matches the task from a plurality of function blocks as at least a part of a group of function blocks based on the respective description information of the plurality of function blocks, wherein the description information of each function block includes at least a semantic description of the function of the function block.
[0103] In some embodiments, the function block determination module 510 is further configured to generate a prompt word input based on description information of each of the plurality of function blocks and user input; provide the prompt word input to the model; and obtain an indicator of a function block matching the task from the model.
[0104] In some embodiments, the device 500 also includes a providing module, which is configured to provide a prompt of multiple candidate modules to the user in response to determining that the functional block matching the task includes multiple candidate modules for performing at least a portion of the task; and a removing module, which is configured to remove other candidate modules other than the target candidate module from the functional block matching the task based on the user's selection of the target candidate module among the multiple candidate modules.
[0105] In some embodiments, the apparatus 500 further includes a sequence determining module configured to determine a sequence of a group of functional blocks based on a data flow; and a combining module configured to combine the group of functional blocks in sequence.
[0106] In some embodiments, the sequence determination module is further configured to determine an endpoint function block in a set of function blocks based on endpoint data in the data stream, the endpoint data including at least any one of the following in the data stream: input data, output data, and the endpoint function block including at least any one of the following in a set of function blocks: a start module, an end module.
[0107] In some embodiments, the sequence determination module is further configured to determine an adjacent functional block adjacent to the endpoint functional block from a group of functional blocks based on the interface data of the endpoint functional block, the endpoint functional block and the adjacent functional block communicate via the interface data, and the adjacent functional block includes at least any one of the following of the endpoint functional block: a predecessor module and a successor module.
[0108] In some embodiments, the combination module is further configured to, for a first functional block and a second functional block in a group of functional blocks, combine the first functional block and the second functional block in response to determining that a first format of output data of the first functional block is consistent with a second format of input data of the second functional block, where the first functional block and the second functional block are adjacent functional blocks arranged in sequence.
[0109] In some embodiments, the device 500 also includes: an adding module, configured to add the combined first functional block and second functional block to a cache of a functional block library including multiple functional blocks to form a third functional block, the input data of the third functional block is the same as the input data of the first functional block, and the output data of the third functional block is the same as the input data of the second functional block.
[0110] In some embodiments, the apparatus 500 further includes a format conversion module configured to convert the first format into the second format using the conversion module in response to determining that the first format and the second format are inconsistent; and a second combination module configured to combine the first functional block, the conversion module, and the second functional block.
[0111] In some embodiments, the apparatus 500 further includes an adding module configured to add a conversion module to a function block library including a plurality of function blocks.
[0112] In some embodiments, the conversion module is obtained based on at least any one of the following: a function block defined based on the first format and the second format; a third-party function block obtained based on the first format and the second format.
[0113] In some embodiments, the device 500 also includes a creation module that is configured to create a functional block for performing at least a portion of the tasks based on any of the following in response to determining that multiple functional blocks cannot perform at least a portion of the tasks: rewriting a functional block in the multiple functional blocks; and creating a new functional block that is different from the multiple functional blocks.
[0114] In some embodiments, the device 500 also includes a second receiving module configured to receive another user input expressed in a natural language from the user; a parsing module configured to parse the other user input to determine another task to be performed; and a second execution module configured to execute the other task using a combined set of functional blocks in response to determining that the task is of the same type as the other task.
[0115] In some embodiments, the apparatus 500 further includes a generating module configured to generate an application using the combined set of function blocks; and a second adding module configured to add the application to a function block library including a plurality of function blocks.
[0116] In some embodiments, the generation module is further configured to generate the application in response to determining that the received user input associated with the type of task satisfies a threshold condition.
[0117] In some embodiments, the generation module is further configured to: determine that the user input satisfies the threshold condition in response to at least any one of the following: the number of user inputs exceeds a threshold number; the frequency of user inputs exceeds a threshold frequency.
[0118] In some embodiments, the plurality of function blocks are provided by a function block library and include at least any one of the following: an application, or a component in an application.
[0119] In some embodiments, the user input includes a multimodal form, and the multimodal form includes at least any one of the following: text input describing the user's intention in natural language, voice input, image input, and video input.
[0120] Figure 6 shows a flowchart of a method 600 for processing a task according to some embodiments of the present disclosure. At block 610, a task to be executed is determined based on the user intent identified in response to user input. At block 620, the task is executed using a set of function blocks provided by a low-code platform. At block 630, in response to a preset condition being met, an application for executing the task is generated based on the set of function blocks.
[0121] In some embodiments, the method 600 further includes determining that the preset condition is satisfied in response to at least any one of the following: the number of times the task is executed exceeds a threshold number; the frequency of executing the task exceeds a threshold frequency; an application generation instruction is received from a user input.
[0122] In some embodiments, the method 600 further includes adding the application to a function block library including a plurality of function blocks.
[0123] Figure 7 shows a block diagram of an apparatus 700 for processing a task according to some embodiments of the present disclosure. As shown in Figure 7, the apparatus 700 includes: a task determination module 710 configured to determine a task to be executed based on a user intent identified in response to a user input; an execution module 720 configured to execute the task using a set of function blocks provided by a low-code platform; and a generation module 730 configured to generate an application for executing the task based on the set of function blocks in response to a preset condition being met.
[0124] In some embodiments, the generation module 730 is further configured to: determine that the preset condition is met in response to at least any one of the following: the number of times the task is executed exceeds a threshold number; the frequency of executing the task exceeds a threshold frequency; an application generation instruction is received from the user.
[0125] In some embodiments, the apparatus 700 further includes: an adding module configured to add an application to a function block library including a plurality of function blocks.
[0126] FIG8 shows a block diagram of an electronic device 800 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 800 shown in FIG8 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 800 shown in FIG8 can be used to run the application creation platform 110 of FIG1 .
[0127] As shown in FIG8 , electronic device 800 is in the form of a general-purpose application creation platform. Components of electronic device 800 may include, but are not limited to, one or more processors or processing units 810, memory 820, storage device 830, one or more communication units 840, one or more input devices 850, and one or more output devices 860. Processing unit 810 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 820. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to increase the parallel processing capabilities of electronic device 800.
[0128] The electronic device 800 typically includes a plurality of computer storage media. Such media can be any accessible media that can be obtained by the electronic device 800, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 820 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 830 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 800.
[0129] The electronic device 800 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG8 , a disk drive for reading from or writing to a removable, non-volatile disk (e.g., a “floppy disk”) and an optical drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 820 may include a computer program product 825 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.
[0130] The communication unit 840 enables communication with other application creation platforms via a communication medium. Additionally, the functions of the components of the electronic device 800 can be implemented as a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 800 can operate in a networked environment using a logical connection to one or more other servers, a network personal computer (PC), or another network node.
[0131] The input device 850 may be one or more input devices, such as a mouse, keyboard, or trackball. The output device 860 may be one or more output devices, such as a display, a speaker, or a printer. The electronic device 800 may also communicate with one or more external devices (not shown) via the communication unit 840 as needed, such as a storage device, a display device, or the like, with one or more devices that allow a user to interact with the electronic device 800, or with any device that allows the electronic device 800 to communicate with one or more other application creation platforms (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).
[0132] 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.
[0133] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.
[0134] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.
[0135] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0136] The flow charts and block diagrams in the accompanying drawings have shown 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 box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the regulation. In some alternative implementations, the function marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be performed substantially in parallel, and they can sometimes be performed in the opposite order, depending on the function involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the regulation, or can be realized by a combination of special hardware and computer instructions.
[0137] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.
Claims
1. A method for performing a task, comprising: determining a task to be performed based on the user intent identified with respect to the user input; determining a set of functional blocks based on a plurality of functional blocks and a data flow associated with the task; as well as The task is performed using the combined set of functional blocks.
2. The method of claim 1 , wherein determining the set of functional blocks comprises: Based on the respective description information of the multiple function blocks, a function block matching the task is determined from the multiple function blocks as at least a part of the group of function blocks, and the description information of each function block at least includes a semantic description of the function of the function block.
3. The method according to claim 2, wherein determining a functional block matching the task comprises: Generate a prompt word input based on the description information of each of the plurality of function blocks and the user input; Providing the prompt word input to the model; as well as An indicator of the functional block matching the task is obtained from the model.
4. The method according to claim 3, further comprising: In response to determining that the function block matched to the task includes a plurality of candidate modules for performing at least a portion of the task, providing a prompt of the plurality of candidate modules to the user; as well as Based on the user's selection of a target candidate module among the plurality of candidate modules, other candidate modules except the target candidate module are removed from the functional blocks matching the task.
5. The method according to claim 1, further comprising: determining an order of the set of functional blocks based on the data flow; as well as The set of functional blocks are combined in the order.
6. The method of claim 5, wherein determining the order of the set of functional blocks comprises: Based on the endpoint data in the data stream, an endpoint function block in the set of function blocks is determined, wherein the endpoint data includes at least any one of the following in the data stream: input data, output data, and the endpoint function block includes at least any one of the following in the set of function blocks: a start module, an end module.
7. The method of claim 6, wherein determining the order of the set of functional blocks further comprises: Based on the interface data of the endpoint functional block, an adjacent functional block adjacent to the endpoint functional block is determined from the group of functional blocks, the endpoint functional block and the adjacent functional block communicate via the interface data, and the adjacent functional block includes at least any one of the following of the endpoint functional block: a predecessor module and a successor module.
8. The method of claim 5, wherein combining the set of functional blocks in the order comprises: For a first functional block and a second functional block in the group of functional blocks, in response to determining that a first format of output data of the first functional block is consistent with a second format of input data of the second functional block, the first functional block and the second functional block are combined, and the first functional block and the second functional block are adjacent functional blocks arranged in the order.
9. The method according to claim 8, further comprising: The combined first function block and the second function block are added to a cache of a function block library including the plurality of function blocks to form a third function block, the input data of the third function block being the same as the input data of the first function block, and the output data of the third function block being the same as the input data of the second function block.
10. The method according to claim 9, further comprising: In response to determining that the first format and the second format are inconsistent, Converting the first format into the second format using a conversion module; as well as The first functional block, the conversion module, and the second functional block are combined.
11. The method according to claim 8, further comprising: The conversion module is added to a function module library including the plurality of function blocks.
12. The method according to claim 8, wherein the conversion module is obtained based on at least any one of the following: a function block defined based on the first format and the second format; A third-party function block is obtained based on the first format and the second format.
13. The method according to claim 1, further comprising: In response to determining that the plurality of function blocks cannot perform at least a portion of the tasks, creating function blocks for performing the at least a portion of the tasks based on any one of the following: rewriting a functional block among the plurality of functional blocks; as well as A new function block different from the plurality of function blocks is created.
14. The method according to claim 1, further comprising: receiving another user input in natural language from the user; parsing the other user input to determine another task to be performed; as well as In response to determining that the task and the another task are of the same type, the another task is performed using the combined set of function blocks.
15. The method according to claim 1, further comprising: generating an application using the combined set of functional blocks; as well as The application is added to a function block library including the plurality of function blocks.
16. The method of claim 15, wherein generating the application comprises: In response to a preset condition being satisfied, the application is generated.
17. The method according to claim 16, further comprising determining that the preset condition is satisfied in response to at least any one of the following: the number of times the task is performed exceeds a threshold number; The frequency of performing the task exceeds a threshold frequency; The application generates an instruction received from the user.
18. The method according to claim 1, wherein the plurality of function blocks are provided by a function block library and include at least any one of the following: an application, a component in an application.
19. The method according to claim 1, wherein the user input comprises a multimodal form, and the multimodal form comprises at least any one of the following: text input, voice input, image input, video input that describes the user intention in a natural language.
20. An apparatus for performing a task, comprising: A task determination module is configured to, based on the user intention identified with respect to the user input, Identify the tasks to be performed; a function block determination module configured to determine a group of function blocks based on a plurality of function blocks and a data flow associated with the task; as well as The execution module is configured to execute the task by utilizing the group of combined functional blocks.
21. A device for performing a task, 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, when executed by the at least one processing unit, causing the device to perform the method according to any one of claims 1 to 19.
22. 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 19.
23. A method for processing a task, comprising: determining a task to be performed based on the user intent identified with respect to the user input; Utilize a set of functional blocks provided by the low-code platform to perform the tasks; as well as In response to a preset condition being satisfied, an application for executing the task is generated based on the set of functional blocks.
24. The method according to claim 23, further comprising determining that the preset condition is satisfied in response to at least any one of the following: the number of times the task is performed exceeds a threshold number; The frequency of performing the task exceeds a threshold frequency; The application generates an instruction received from the user.
25. The method of claim 23, further comprising: The application is added to a function block library including the plurality of function blocks.
26. An apparatus for processing a task, comprising: a task determination module configured to determine a task to be performed based on the user intent identified with respect to the user input; An execution module, configured to execute the task using a set of function blocks provided by the low-code platform; as well as The generating module is configured to generate an application for executing the task based on the set of function blocks in response to a preset condition being satisfied.
27. An apparatus for processing a task, 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 device to perform a method according to any one of claims 23 to 25 when executed by the at least one processing unit.
28. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 23 to 25.
Citation Information
Patent Citations
Method and device for providing information service based on usage scenario, and computer storage medium
CN112752238A
Data set construction and task type dialogue method, electronic equipment and storage medium
CN114255750A
Application integration with digital assistant
CN114968027A
Language based solution agent
US10013416B1
Cited By
Method, device and equipment based on cache processing task and storage medium
CN119759522A
