Workflow creation method and device based on model, equipment, medium and product

Abstract

According to the embodiment of the invention, the invention provides a workflow creation method and device based on a model, equipment, a storage medium and a program product. The method comprises the following steps: in response to a received workflow editing request sent in a data object, determining a workflow framework corresponding to a workflow by utilizing at least one machine learning model based on the workflow editing request, a current draft of the workflow and information of the data object, the workflow framework indicates corresponding node types of a plurality of nodes included in the workflow and a topological structure of the plurality of nodes, and the current draft comprises a structured representation of a current state of the workflow; determining corresponding configuration information of the plurality of nodes according to the workflow framework; and determining the workflow based on the workflow framework and the corresponding configuration information of the plurality of nodes. The workflow creation process can be implemented using a large model. For example, a large model may be utilized to create a workflow for a database table.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to a model-based workflow creation method, apparatus, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] With the rapid development of machine learning and data analysis technologies, more and more office and management systems are integrating intelligent assistants to simplify the creation and execution of task processes for data objects. In scenarios such as task management, form processing, and approval processes, users often need to define operational processes in a structured manner, such as sequentially configuring trigger conditions, judgment logic, and processing actions. Especially when process logic is complex and data volumes are large, accurately generating clearly structured and fully configured operational processes becomes a significant concern. Summary of the Invention

[0003] In a first aspect of the present disclosure, a model-based workflow creation method is provided. The method includes: in response to receiving a workflow edit request issued in a data object, based on the workflow edit request, a current draft of the workflow, and information about the data object, determining a workflow framework corresponding to the workflow using at least one machine learning model, wherein the workflow framework indicates corresponding node types of multiple nodes included in the workflow and a topological structure of the multiple nodes, and the current draft includes a structured representation of a current state of the workflow; determining corresponding configuration information of the multiple nodes according to the workflow framework; and determining the workflow based on the workflow framework and the corresponding configuration information of the multiple nodes.

[0004] In a second aspect of the present disclosure, a device for model-based workflow creation is provided. The device includes: a workflow framework determination module, configured to, in response to receiving a workflow edit request issued in a data object, determine a workflow framework corresponding to the workflow based on the workflow edit request, a current draft of the workflow, and information about the data object using at least one machine learning model, wherein the workflow framework indicates corresponding node types of multiple nodes included in the workflow and a topological structure of the multiple nodes, and the current draft includes a structured representation of the current state of the workflow; a configuration information determination module, configured to determine corresponding configuration information of multiple nodes according to the workflow framework; and a workflow determination module, configured to determine the workflow based on the workflow framework and the corresponding configuration information of the multiple nodes.

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

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein computer instructions are stored on the medium, and when the computer instructions are executed by a processor, the method of the first aspect is implemented.

[0007] In a fifth aspect of the present disclosure, a computer program product is provided, which includes a computer program, wherein when the computer program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.

[0008] 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

[0009] 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: Figure 1 A schematic diagram illustrating an example environment in which embodiments of the present disclosure can be implemented; Figure 2 A schematic diagram illustrating an example process of workflow creation according to some embodiments of the present disclosure; Figure 3A A schematic diagram showing an example interface for generating a workflow framework according to some embodiments of the present disclosure; Figure 3B A schematic diagram illustrating an example interface for determining configuration information according to some embodiments of the present disclosure is shown; Figure 3C A schematic diagram illustrating an example interface of an update workflow framework according to some embodiments of the present disclosure; Figure 4 A flowchart illustrating a method for model-based workflow creation according to some embodiments of the present disclosure is shown; Figure 5 A schematic structural block diagram of an apparatus for creating a model-based workflow according to some embodiments of the present disclosure is shown; and Figure 6 A block diagram of an electronic device is shown in which one or more embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION

[0010] 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.

[0011] 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.

[0012] Herein, unless explicitly stated otherwise, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0013] 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.

[0014] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the type, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and authorization should be obtained from relevant users in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.

[0015] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to the software or hardware such as the electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0016] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message may be sent to the relevant user in the form of a pop-up window, in which the prompt message may be presented in text form. Furthermore, the pop-up window may also include a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0017] 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.

[0018] As used herein, the term "model" can learn the association between corresponding inputs and outputs from training data, so that after training is completed, corresponding outputs can be generated for given inputs. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as a "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably herein. In some embodiments described below, the machine learning model may be a large language model or have an architecture based on a large language model. The machine learning model may also be a multimodal model capable of processing multimodal inputs (e.g., text input and visual input).

[0019] Figure 1 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In this example environment 100, a digital assistant 120 and a service component 125 are installed in a terminal device 110. A user 140 can interact with the digital assistant 120 and the service component 125 via the terminal device 110 and / or a device attached to the terminal device 110.

[0020] In some embodiments, the digital assistant 120 and the service component 125 can be downloaded and installed on the terminal device 110. In some embodiments, the digital assistant 120 and the service component 125 can also be accessed through other means, such as through a web page. Figure 1 In the environment 100 , in response to the business component 125 being started, the terminal device 110 can present the interface 150 of the digital assistant 120 and the business component 125 .

[0021] The business component 125 includes but is not limited to one or more of the following: chat business component (also known as instant messaging business IM component), document business component, audio and video conference business component, email business component, task business component, calendar business component, objectives and key results (OKR) business component, etc. It is understandable that although Figure 1A single business component is shown in the figure, but in fact, multiple business components can be installed on the terminal device 110. Business components can be integrated on a multifunctional collaboration platform. In the case where multiple business components are installed in the terminal device 110, these multiple business components can be integrated on one or more multifunctional collaboration platforms. In the multifunctional collaboration platform, people can start different business components as needed to complete corresponding information processing, sharing, communication, etc. Business component 125 can provide content entity 126. Content entity 126 can be a content instance created by user 140 or other users on business component 125. For example, depending on the type of business component 125, content entity 126 can be a document (for example, a word document, a PDF document, a presentation, a spreadsheet document, etc.), an email, a message (for example, a conversation message on an instant messaging business component), a calendar, a schedule, a task, audio, video, an image, etc.

[0022] In some embodiments, the digital assistant 120 may be provided by a separate business component, or may be integrated into a business component 125 that can provide a content entity. The business component for providing the client interface of the digital assistant may correspond to a single-function business component or a multi-function collaboration platform, such as an office suite or other collaboration platform that can integrate multiple components. It is understood that similar to the business component, although Figure 1 A single digital assistant is shown in the figure, but there can actually be multiple digital assistants.

[0023] In some embodiments, the digital assistant 120 supports the use of plug-ins. Each plug-in can provide one or more functions of a business component. Such plug-ins include, but are not limited to, one or more of the following: a search plug-in, a contact plug-in, a message plug-in, a document plug-in, a spreadsheet plug-in, an email plug-in, a calendar plug-in, a schedule plug-in, a task plug-in, and the like.

[0024] The digital assistant 120 can be an intelligent assistant for the user, having intelligent dialogue and information processing capabilities. In an embodiment of the present disclosure, the digital assistant 120 is used to interact with the user 140 to assist the user 140 in using a terminal device or a service component. An interaction window with the digital assistant 120 can be presented in the client interface. In the interaction window, the user 140 can communicate with the digital assistant 120 by inputting natural language, pictures, audio files, video files, web page files, etc., to instruct the digital assistant to assist in completing various tasks, including operations on the content entity 126.

[0025] The digital assistant 120 can be called or awakened by an appropriate means (e.g., a shortcut key, button, or voice) to present an interaction window with the user 140. By selecting the digital assistant 120, the interaction window with the digital assistant 120 can be opened. The interaction window may include interface elements for information interaction, such as an input box, a message list, a message bubble, and the like. In other embodiments, the digital assistant 120 can be awakened through an entry control or menu provided in a page, or by inputting a preset command.

[0026] In some embodiments, the terminal device 110 communicates with the server 130 to provide services for the digital assistant 120 and the business component 125. The terminal device 110 can be any type of mobile, fixed, or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a television receiver, a radio receiver, an e-book device, a gaming device, or any combination thereof, including accessories and peripherals for these devices or any combination thereof. In some embodiments, the terminal device 110 can also support any type of user interface (such as "wearable" circuitry, etc.). The server 130 can be any type of computing system / server capable of providing computing capabilities, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, and the like.

[0027] It should be understood that the structure and function of the various elements in the environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of the present disclosure.

[0028] As briefly mentioned above, with the advancement of data analytics and machine learning technologies, more and more workflow processing systems are exploring smarter, more accessible approaches to assist users in creating automated task processes. In some business scenarios, users need to set specific processing logic based on data records, such as triggering notifications, conditional branching, and data aggregation. To this end, some platforms have begun providing low-code or graphical workflow editing tools, allowing users to configure automated processes by dragging nodes and entering parameters.

[0029] However, traditional workflow configuration methods still have limitations in many aspects. First, for users unfamiliar with automation logic or not adept at abstract modeling, the learning curve is high, requiring them to understand complex information such as process structure, node logic, and parameter dependencies. Second, traditional workflow processes are typically static and lack contextual awareness. This approach cannot proactively perceive and guide users in configuring the process based on their current data environment (such as the business table they are currently working on).

[0030] In view of this, according to an embodiment of the present disclosure, an improved solution for workflow creation is provided. According to this solution, in response to receiving a workflow edit request issued in a data object, a workflow framework corresponding to the workflow is determined based on the workflow edit request, the current draft of the workflow, and information about the data object using at least one machine learning model. The workflow framework indicates the corresponding node types of multiple nodes included in the workflow and the topological structure of the multiple nodes. The current draft includes a structured representation of the current state of the workflow. Further, according to the workflow framework, the corresponding configuration information of the multiple nodes is determined. Still further, based on the workflow framework and the corresponding configuration information of the multiple nodes, the workflow is determined.

[0031] This allows users to issue workflow edit requests for various data objects (e.g., structured data objects, database tables). Based on the workflow edit request, workflow draft, and data object information, a workflow framework that matches the target requirements can be automatically constructed. By further determining the configuration information for each node, a complete and executable target workflow is ultimately formed. This approach effectively improves the automation level of workflow creation and modification, lowering the barrier to user understanding and operation. This intelligent workflow creation method, which supports specific business data within a data environment, can improve workflow creation efficiency, data adaptability, and structural interpretability. For example, large models can be used to implement workflow creation.

[0032] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings. Figure 2A schematic diagram illustrates an example process 200 for creating a workflow according to some embodiments of the present disclosure. Part or all of process 200 can be implemented by the terminal device 110 or by other devices, such as other remote devices with computing capabilities (either in the terminal device or a server). For ease of discussion, the example embodiments will be primarily described with respect to the terminal device 110. It should be understood that the actions described with respect to the terminal device 110 can be performed at least in part by other entities, such as the digital assistant 120, or by the terminal device 110 alone, by the server 130 alone, or both in concert. For example, computationally intensive tasks or algorithm-related processing can be performed by the server 130. In the following description, different nodes or stages of creating or editing a workflow can utilize a machine learning model. The machine learning models utilized in different nodes or stages can be the same or different. The utilized machine learning model can be a large model. The large model can be a large language model. Alternatively or additionally, the large model can be a multimodal model capable of processing multiple modal inputs (e.g., textual input, visual input).

[0033] like Figure 2 As shown, the terminal device 110 can receive a workflow editing request 201 issued in a data object. A data object refers to a data entity in various forms used to carry business information. Data objects can include structured data objects (e.g., data tables, database tables, etc.) and unstructured data objects. Data objects can be presented in the interface 150 in the form of tables, forms, or charts. For example, a data object can include one or more multidimensional data tables with associated structural information. Each data object can contain a field structure and data records. The field structure includes the number of fields, field names, field types, etc., and the data records correspond to actual data rows in the table.

[0034] In some embodiments, a data object may be associated with multiple functional components, such as a form for data entry, a dashboard for data analysis, etc. The dashboard may include statistical analysis results of the data table contents, and may be displayed in various chart formats, such as bar charts, line charts, pie charts, funnel charts, etc. When operating these data objects, such as viewing a table, editing a form, or analyzing a chart, user 140 may initiate a request to create or modify a workflow based on the data content.

[0035] A workflow is a logical execution chain consisting of multiple functional nodes. These nodes are organized according to a specific topology and are used to process business logic associated with data objects. The design, configuration, and triggering of a workflow can all rely on information from one or more data objects. The core function of a workflow is to implement data-driven automated operations.

[0036] In some embodiments, data objects can provide contextual information and data sources for workflow creation and configuration. The workflow's structural design and node configuration can be based on the field structure, field value type, and historical records within the data object. For example, if a user wishes to set up a process to "notify the responsible person when the project status is delayed," the terminal device 110 can identify the "Project Status" field contained in the data object and generate corresponding judgment nodes and notification node configurations accordingly.

[0037] Alternatively or additionally, workflow execution can target data records within a data object. For example, a decision node might iterate over every record in a table, triggering subsequent actions for rows that meet a condition. The execution results might also be written back to the original data object or update its associated state.

[0038] In some embodiments, a data object can be mapped to multiple workflow instances. Different workflows can act on different fields, record sets, or business views of the data object, thereby supporting multi-dimensional automated processing capabilities.

[0039] In some embodiments, in response to receiving a workflow edit request 201 issued in a data object, the terminal device 110 can determine a workflow framework corresponding to the workflow based on the workflow edit request, the current draft of the workflow, and information about the data object. The workflow framework can be determined using a machine learning model, such as a large language model or a multimodal large model. The workflow framework indicates the corresponding node types of the multiple nodes included in the workflow and the topological structure of the multiple nodes. The current draft includes a structured representation of the current state of the workflow. The workflow edit request 201 can be triggered by the user 140 while viewing a data object (such as a multidimensional table, form, or dashboard) by clicking a corresponding button, inputting natural language, or the like.

[0040] The current draft of a workflow refers to a structured intermediate state of the current workflow, which is used to record existing nodes, configurations, or previous user editing behaviors in the workflow. The current draft of a workflow can be organized in the form of a graphical structure, for example, presented as a drawing board in interface 150. The current draft of a workflow can include node types, connection relationships, and some generated or retained configuration fields. Based on this, the terminal device 110 can determine the workflow framework corresponding to the current editing request. The workflow framework is used to describe the overall structure of the workflow. The workflow framework (or the shell protocol of the workflow) can indicate the node types of multiple nodes (such as trigger nodes, judgment nodes, data processing nodes, etc.) and the connection relationships between multiple nodes (i.e., the topological structure). The workflow framework can clarify the execution logic structure of the current workflow, providing a basis for subsequent node-by-node configuration generation.

[0041] As an example, see Figure 2 At block 210 , terminal device 110 may perform requirement identification based on workflow edit request 201 . For example, workflow edit request 201 may indicate that user 140 wishes to create a new workflow, or to restructure or modify an existing workflow. If workflow edit request 201 indicates the creation of a new workflow based on the current data object, terminal device 110 may proceed to block 230 .

[0042] At block 220, the terminal device 110 may generate a workflow framework. For example, the terminal device 110 may determine a blank structured representation of the workflow as the current draft. This means that before specific nodes or logical configurations are specified, a basic draft can be initialized to serve as a container for subsequent workflow construction. The current draft can be used to inherit the workflow framework and configuration content that will be generated subsequently. Furthermore, the terminal device 110 may utilize at least one machine learning model to generate the workflow framework based on the workflow edit request, the current draft of the workflow, and information about data objects.

[0043] In some embodiments, terminal device 110 can extract structural information (such as field names, field types, and inter-table relationships) and sample data from data objects (e.g., multidimensional tables) as important contextual information when generating a workflow framework. This structural information can help determine the node types to include in the model inference process. For example, identifying a field as a time field can generate a trigger node, or identifying a field as a classification state can generate a decision node.

[0044] In some embodiments, terminal device 110 may determine intermediate protocol information corresponding to the current draft. The intermediate protocol information is used to describe a structured representation using a language suitable for at least one machine learning model. Terminal device 110 may first perform an intermediate protocol conversion on the current draft of the workflow, converting the structural information already in the draft into an intermediate representation suitable for processing by a language model.

[0045] In some examples, intermediate protocol information can include natural language-like information that is highly readable and expressive. This intermediate protocol information can be organized in a structured format, with field values ​​expressed in natural language and accompanied by explanatory text to indicate the meaning of each field or the business objective of the node. This intermediate protocol information helps improve the model's understanding of structural semantics.

[0046] Alternatively or additionally, to avoid information loss due to structural compression, the intermediate protocol information can include structure-preserving intermediate protocol information. This intermediate protocol information can maintain a basic consistency with the structural hierarchy of the workflow draft, with only some fields (e.g., identifiers, table names, field names) optimized for readability or semantic replacement. This intermediate protocol information does not compress or retranslate the original structure, preserving the connection relationships between nodes, nested structures, and complete configuration fields to the greatest extent possible. Therefore, this intermediate protocol information is suitable for workflow generation tasks with longer processes or complex structures.

[0047] In some embodiments, the terminal device 110 can utilize at least one machine learning model to generate a workflow framework based on intermediate protocol information, data object information, and workflow edit requests. For example, when user 140 initiates an edit request to "create an automatic reminder process" in a multidimensional table, the terminal device 110 can convert the current draft state into intermediate protocol information. Alternatively or additionally, the terminal device 110 can extract the field structure and sample values ​​in the current multidimensional table that are most relevant to the edit request semantics, such as the field name, field type, and sample values ​​of fields such as "amount," "person in charge," and "project status," and provide them to the model along with the intermediate protocol information. Furthermore, the terminal device 110 can utilize a machine learning model to combine fields in the current table related to business logic (such as "person in charge," "status," and "deadline") to generate a process structure including trigger nodes, judgment nodes, and notification nodes, thereby achieving automated task modeling for data objects.

[0048] In some embodiments, the terminal device 110 can update the current workflow draft based on the generated workflow framework. For example, the terminal device 110 can translate the structural information of multiple nodes described in the workflow framework, the node type, and the connection relationship between the nodes back into a structured representation that conforms to the workflow draft format, thereby forming an updated workflow draft. Furthermore, the terminal device 110 can present the updated current draft. For example, after the draft update is completed, the terminal device 110 can present the updated workflow draft in the drawing board area (or other user-visible editing interface). The drawing board can graphically display the type, connection direction, and initial description information of each node in the workflow. Based on the workflow draft, the user can intuitively view the framework generation results and make further edits, supplements, or adjustments based on business needs.

[0049] In some embodiments, for the sake of simplicity and reuse, the terminal device 110 can encapsulate the complete process of generating a workflow framework from a workflow editing request 201 into a functional block. This functional block can be exposed to the outside as an atomic capability, called "shell protocol generation capability" or "workflow architecture generation capability". This functional block integrates the conversion of the current draft to intermediate protocol information, context parameter preparation, calling and architecture generation of the machine learning model, and the complete process of converting the generated results back to the current draft. By utilizing functional blocks that encapsulate atomic capabilities, the terminal device 110 can concisely complete the complex workflow framework planning process, improve calling efficiency and support cross-scenario reuse.

[0050] As an example, Figure 3A FIG. 3 is a schematic diagram showing an example interface 300A for generating a workflow framework according to some embodiments of the present disclosure. Figure 3A As shown, the terminal device 110 can receive a workflow edit request 201 via an input box 301. The input box 301 can support natural language input. The user 140 can describe the desired automation logic through text, voice, images, etc. The received workflow edit request 201 can be presented in the user interface in the form of a speech bubble 302, allowing the user to view the historical input content.

[0051] Terminal device 110 can identify the natural language request and parse it based on the data objects associated with the current interface (e.g., multidimensional tables), thereby generating a workflow framework. For example, if the user input is "Generate a workflow that automatically sends notifications, specifically notifying customers that the order is a large one if the transaction amount reaches 10,000 yuan," terminal device 110 can parse the natural language request into a structured intent and initiate the workflow framework generation process based on the corresponding fields (e.g., "amount field" in the "order table") and data records in the multidimensional table.

[0052] Continue to refer Figure 3ABased on the received workflow edit request 201, the terminal device 110 can call the function block that encapsulates the framework generation capability to automatically execute and generate the workflow framework. During execution, the terminal device 110 can provide the user with current status feedback via the execution information area 304. The execution information area 304 can display information about the execution process, such as "Creating process file" or "Starting to create process nodes." Furthermore, to enhance user comprehensibility and process traceability, the terminal device 110 can present a node list 305 of the generated workflow framework in the conversation. Furthermore, the terminal device 110 can display the names and numbers of the nodes included in the current workflow in the node list 305, such as "1. Triggered when a new order arrives," "2. Determine if it is a large order," "3. Send a large order reminder message," etc., to help the user understand the workflow structure and execution sequence.

[0053] During the generation of the workflow framework, the terminal device 110 can initialize a current draft object and present it on the interface 300A in the form of a draft canvas 303. The draft canvas 303 is used to display the structured state of the workflow draft, where each node is presented in the form of a module, and its topological relationship in the overall process is represented by a connecting line. For example, the draft canvas 303 shows that the generated workflow framework includes a "trigger when there is a new order" node numbered 1 (trigger node), a "determine whether it is a large order" node numbered 2 (conditional judgment node), and two parallel subsequent processing nodes 3 and 4 (corresponding to message reminder actions when the conditions are met and not met, respectively). These nodes constitute a basic process structure with conditional branches.

[0054] Alternatively or additionally, the draft canvas 303 allows users to adjust or select node structures through interactive methods such as dragging and clicking, thereby triggering subsequent node configuration generation processes or manual modifications. Based on the draft, users can further edit node content, supplement configuration items, or add new operation instructions. The terminal device 110 can automatically reconstruct the draft or further improve the process structure based on the canvas state and user input, supporting interactive iterative generation and adjustment.

[0055] Return Reference Figure 2 After generating the workflow framework, the terminal device 110 may execute block 225. In block 225, the terminal device 110 may determine corresponding configuration information for multiple nodes in the framework based on the workflow framework. In some embodiments, the workflow framework further indicates corresponding configuration fields and corresponding description information for the multiple nodes, where the description information indicates at least one operation of the corresponding node. The configuration field indicates parameters for the at least one operation.

[0056] Descriptive information is used to explain the operational logic that the corresponding node should execute in natural language, helping to understand the process corresponding to each node in the workflow framework. Configuration fields are used to indicate the parameters or execution conditions required for the node and are key structures for implementing specific actions. For example, the description information for judgment node 2 could be "Judge whether the order amount in the order table is greater than 10,000 yuan." The corresponding configuration fields can include a reference field (such as "order amount"), a judgment condition (such as "greater than"), and a threshold (such as "10,000").

[0057] In some embodiments, the configuration field can be associated with a specific field or data type in the data object. For example, if the "amount" field in the data object is a numeric field, the terminal device 110 can select this field as the source of the judgment condition and infer the available comparison operators and their applicable scopes.

[0058] In some embodiments, for a node among the multiple nodes, the terminal device 110 may determine a parameter value for at least one operation corresponding to the node based at least on the description information of the node. Furthermore, the terminal device 110 may add the parameter value to the configuration field of the node as part of the configuration information of the node. The terminal device 110 may sequentially complete the configuration fields of each node based on the node description information, the configuration field structure, and the available fields in the data object, thereby gradually filling in blank nodes to form a complete process.

[0059] As an example, Figure 3B FIG. 3 is a schematic diagram showing an example interface 300B for determining configuration information according to some embodiments of the present disclosure. Figure 3B As shown, the terminal device 110 can present a configuration control 311 for a node. The terminal device 110 can configure the control 311 to utilize user input for receiving configuration information for the node. The configuration control 311 is used to display the description information and fields to be configured of the node, and allows the user to enter the required parameter values ​​through a drop-down menu, text input, or field selection. Based on the description information of the node and the user input, the terminal device 110 can determine the parameter value. For example, the terminal device 110 can parse and determine the value of the corresponding configuration field based on the description information of the node and the user input, and write it into the data field corresponding to the node. Alternatively or additionally, the terminal device 110 can provide a combination operation of node logical conditions through the control 312, such as "AND", "OR", etc., thereby supporting the construction of multi-condition judgment logic.

[0060] Continue to refer Figure 3BInterface 300B includes a smart fill control 313. In response to triggering smart fill control 313, terminal device 110 can utilize a machine learning model to determine parameter values ​​based on the node's description, the current workflow draft, and data object information. For example, the machine learning model can be used to determine parameter values ​​simultaneously based on the description, current draft, and data object information. Terminal device 110 can utilize the machine learning model to automatically identify the configuration requirements for the current node based on the node's description, the workflow draft status, and data object information (e.g., the current data table structure and field meanings), and infer and generate reasonable parameter values. For example, for a node described as "Determine whether an order is a large order," terminal device 110 can automatically identify the "Order Amount" field, set the judgment relation to "greater than," and enter a threshold of "10,000." For another example, the parameter value determination process can be further broken down. A machine learning model can be used to determine the configuration requirements for the node. Furthermore, parameter values ​​can be determined based on the configuration requirements. Alternatively or additionally, the terminal device 110 may present the inference result as a recommended configuration for the user to confirm, adjust, or directly adopt, thereby achieving efficient automation of node configuration.

[0061] In some embodiments, determining the parameter value can be performed by calling a function block that encapsulates the node configuration capability. For example, calling the corresponding function block automatically executes the process of converting the current draft into intermediate protocol information, preparing context parameters, determining the parameter value of the node using a machine learning model, and converting the parameter value generated back to the current draft.

[0062] Continue to refer Figure 3B , the interface 300B includes an add control 314. In response to the triggering of the add control 314, the terminal device 110 can add a new node in the current workflow framework. For example, the user can choose to add functional nodes of the type "send notification", "call robot" or "data update". While adding the node, the terminal device 110 can automatically initialize the node type and connection relationship according to the context information (such as the selected insertion position, the preceding node type), and guide the user to complete the parameter configuration of the new node or call the smart fill function. By adding the control 314, incremental expansion can be performed based on the generated workflow framework, so as to flexibly adjust the workflow logic to adapt to diverse business needs. In some embodiments, adding a new node in the current workflow framework can be executed by calling a function block that encapsulates the node configuration capability.

[0063] In some embodiments, terminal device 110 can determine the configuration order of multiple nodes based on a depth-first search (DFS) strategy. This depth-first search ensures that when configuring a node, its predecessor nodes (i.e., the input sources that may affect the current node) have already been configured, thereby avoiding references to undefined parameters or incomplete structures. In some examples, terminal device 110 can analyze the dependencies between fields and nodes in data objects in real time and recommend related fields when adding or modifying nodes, thereby improving interaction efficiency and field configuration accuracy.

[0064] Furthermore, the terminal device 110 can determine the configuration information of each of the multiple nodes by sequentially calling the function blocks for node configuration generation in the configuration order. For example, the function blocks for node configuration generation can be encapsulated as an atomic capability, called "configuration information determination capability" or "node configuration capability." This atomic capability may include converting the current draft into intermediate protocol information, preparing context parameters, using large language model reasoning or template rules to determine the parameter values ​​of the node (such as field name, judgment condition, execution action, etc.), converting the configuration generation result back to the current draft, and writing the generation result into the configuration field of the node, thereby forming a complete execution process for the complete node configuration information. The terminal device 110 can execute this process node by node in the DFS order until all nodes in the entire workflow have completed the filling of configuration parameter values.

[0065] Return Reference Figure 2 If the workflow edit request includes a workflow modification request, process 200 proceeds to block 230. At block 230, terminal device 110 may utilize a first machine learning model to determine a modification plan for the workflow based on the workflow modification request and the current draft of the workflow. The first machine learning model may be a pre-defined planning module or other machine learning model (e.g., a large language model). The modification plan is used to determine and plan modifications to the current workflow at the structural and configuration levels.

[0066] In some examples, the modification plan can indicate whether the current draft requires structural adjustments, that is, whether the workflow framework needs to be modified. For example, if the user requests to "replace the second-step judgment node with a data aggregation node," the modification plan may include operations such as deleting the original judgment node, inserting a new aggregation node, and reconnecting upstream and downstream nodes. Alternatively or additionally, the modification plan can include local modification instructions that do not affect the framework structure, such as modifying only the configuration parameters of a specific node.

[0067] In box 231, the terminal device 110 can determine whether the modification plan indicates a modification to the workflow framework, that is, whether the modification plan indicates a structural modification to the current workflow framework. If the modification plan indicates a modification to the workflow framework, the process 200 can proceed to box 232. In box 232, the terminal device 110 can use a second machine learning model to update the workflow framework corresponding to the workflow based on the workflow editing request, the current draft of the workflow, and the information of the data object. The second machine learning model can be the same as or different from the first machine learning model used to determine the modification plan. The embodiments of the present disclosure are not limited in this respect. For example, the process of updating the workflow framework can be to call a function block that encapsulates the workflow framework generation capability to convert the current draft into intermediate protocol information, prepare context parameters, generate the framework of the workflow using the second machine learning model, and convert the framework generation result back to the current draft.

[0068] Based on the updated workflow framework, terminal device 110 can further determine the configuration information of each node to complete the parameter configuration of the newly added node or update the context dependencies of the affected nodes. This ensures the consistency of the workflow's logical structure and execution parameters. The determination of the configuration information of each node can be performed by calling the aforementioned function block that encapsulates the node configuration capabilities.

[0069] In some embodiments, if the modification plan only indicates adjustments to the configuration information of one or more nodes (e.g., the first node among multiple nodes) without involving structural changes, process 200 may proceed to block 235. At block 235, terminal device 110 may update the configuration information of the first node based on the workflow framework. The process of updating the configuration information of the first node may be executed by calling the aforementioned function block that encapsulates node configuration capabilities.

[0070] As an example, Figure 3C FIG. 3 is a schematic diagram showing an example interface 300C of an update workflow framework according to some embodiments of the present disclosure. Figure 3C As shown, the terminal device 110 can receive a workflow edit request 201 via an input box 301. The workflow edit request 201 can include the user 140's intention to modify the current workflow structure or configuration, for example, "change the judgment value to 15000" or "change the execution operation of a certain node." The terminal device 110 can identify the requirements of the workflow edit request 201. In response to the workflow edit request 201 indicating the modification of the current workflow (e.g., workflow A), the terminal device 110 can parse the data objects associated with the current interface (e.g., multidimensional tables) to update the framework structure of the workflow.

[0071] Continue to refer Figure 3CDuring workflow framework modifications, terminal device 110 can provide user feedback on the current status via execution progress area 321. This area can display the progress of the current structural update, such as the affected nodes, the changed content, and the expected results. This improves system transparency and user controllability, enabling users to clearly understand the impact of edit requests on the overall workflow structure and effectively supporting multiple rounds of adjustments and verification for complex processes.

[0072] Continue to refer Figure 3C Interface 300C may include a control 322 for confirming or canceling the update operation. For example, control 322 may include an "Accept" button and a "Cancel" button, respectively used to confirm and apply the current changes or cancel the current round of changes. When user 140 clicks the "Accept" button, terminal device 110 may write the updated workflow framework and its configuration information to the current draft and refresh the display area to make the new structure effective. If user 140 selects "Cancel", terminal device 110 may cancel the current round of changes, leaving the current draft of the workflow unchanged.

[0073] In some embodiments, the terminal device 110 can highlight the nodes that have been configured, or prompt the parts that have not been configured yet, in the draft drawing board 303 to guide the user to make supplements. The user 140 can further proofread, modify or save the workflow based on this.

[0074] Return Reference Figure 2 After determining the configuration information for each node in the workflow framework, terminal device 110 can determine workflow 202 based on the workflow framework and the corresponding configuration information of the multiple nodes. For example, terminal device 110 can combine the types and connections of each node in the framework structure with their corresponding configuration fields to construct a complete process definition with execution semantics. This process definition can include trigger conditions, judgment logic, data processing methods, message notification content, and other content, and is stored as an executable process entity in a structured data format.

[0075] In some embodiments, the terminal device 110 can fully present the completed workflow in the draft canvas 303, including the type, number, connection direction, and configured core parameters of all nodes. The terminal device 110 can support exporting the completed workflow to a standard format or submitting it to a workflow engine to support subsequent automated operation.

[0076] In some embodiments, after generating a complete workflow, the terminal device 110 can automatically generate workflow summary information based on the workflow framework corresponding to the workflow, the corresponding configuration information of the multiple nodes included in the workflow, and the user's historical input context. The summary information is used to summarize the business objectives and execution logic of the current workflow, and may include information such as trigger conditions, key judgment nodes, and core processing steps.

[0077] In some embodiments, the terminal device 110 can determine the title of the workflow based on the summary information. The title is used to briefly identify the core function or scenario of the workflow. The terminal device 110 can extract keywords from the summary information to construct it, or automatically generate it in combination with user input. Furthermore, the terminal device 110 can synchronously present the generated summary information and title in the interface of the data object. For example, the title can be displayed in the upper area of ​​the multidimensional table interface as the workflow identification name. The summary information can be presented in the dialogue area or the workflow list to assist users in quickly understanding the functions and applicable scenarios of the current process. Through the generation and display of titles and summaries, not only the readability and interpretability of the workflow display are enhanced, but also convenience is provided for the user's subsequent process management and retrieval.

[0078] In some embodiments, the terminal device 110 may detect that the workflow associated with the current interface is inconsistent with the input workflow editing request 201. In other words, the user may propose a modification or creation requirement for workflow B in the editing interface of workflow A. For example, the terminal device 110 can determine whether the request can be directly configured on the workflow corresponding to the current draft based on the target statement in the editing request. If it cannot be determined or it is judged to be a mismatch, the terminal device 110 can further confirm the intention of the user 140. For example, the interface prompts "Do you want to apply this configuration to workflow B?" or guides the user 140 to select the target workflow among multiple workflow candidates.

[0079] Alternatively or additionally, terminal device 110 may determine whether to switch to the current workflow based on information such as at least one other workflow recently operated on by the user (e.g., the last workflow file opened), the content of the edit request currently entered by the user, and the characteristics of the workflow it points to (e.g., name, process type, etc.). Ultimately, terminal device 110 can determine a clear current workflow and use this information as input for subsequent "Create Workflow" or "Modify Workflow" processes. This ensures that subsequent structure generation or parameter configuration operations are targeted at the correct workflow file, thus avoiding accidental modifications or semantic conflicts.

[0080] In summary, according to the embodiments of the present disclosure, by automatically generating clearly structured and fully configured workflows based on the structural information and content data associated with data objects, the efficient transformation from business data to automated processes is achieved. Furthermore, by dividing workflow generation into two phases: framework generation and configuration completion, and introducing an intermediate protocol to bridge natural language and structured logic, the large model's ability to understand data object context and its generation accuracy are improved.

[0081] Figure 4 A flowchart of a method 400 for creating a model-based workflow according to some embodiments of the present disclosure is shown. The method 400 can be implemented on any device. For example, the method 400 can be implemented on the terminal device 110 or the server 130, or can be coordinated by the terminal device 110 and the server 130. Figure 1 Method 400 is described.

[0082] In box 410, the terminal device 110, in response to receiving a workflow editing request issued in a data object, uses at least one machine learning model to determine a workflow framework corresponding to the workflow based on the workflow editing request, the current draft of the workflow and information of the data object, where the workflow framework indicates corresponding node types of multiple nodes included in the workflow and a topological structure of the multiple nodes, and the current draft includes a structured representation of the current state of the workflow.

[0083] In block 420 , the terminal device 110 determines corresponding configuration information of the plurality of nodes according to the workflow framework.

[0084] In block 430 , the terminal device 110 determines a workflow based on the workflow framework and corresponding configuration information of the plurality of nodes.

[0085] In some embodiments, the method 400 further includes: in response to determining that the workflow editing request includes a workflow creation request, determining the workflow structured representation in a blank state as a current draft.

[0086] In some embodiments, determining a workflow framework corresponding to a workflow includes: determining intermediate protocol information corresponding to a current draft, the intermediate protocol information being used to describe a structured representation using a language adapted for at least one machine learning model; and generating a workflow framework using at least one machine learning model based on the intermediate protocol information, information about the data object, and a workflow editing request.

[0087] In some embodiments, the method 400 further includes: updating the current draft of the workflow based on the workflow framework; and presenting the updated current draft of the workflow.

[0088] In some embodiments, the workflow framework also indicates corresponding configuration fields and corresponding descriptive information of multiple nodes, the descriptive information indicates at least one operation of the corresponding node, the configuration field indicates a parameter of at least one operation, and determining the corresponding configuration information of multiple nodes includes: for a node among the multiple nodes, determining the parameter value of at least one operation corresponding to the node based at least on the descriptive information of the node; and adding the parameter value to the configuration field of the node as part of the configuration information of the node.

[0089] In some embodiments, determining a parameter value of at least one operation corresponding to the node includes: receiving user input of configuration information for the node; and determining the parameter value based on description information of the node and the user input.

[0090] In some embodiments, determining a parameter value of at least one operation corresponding to the node includes: utilizing a machine learning model to determine the parameter value based on description information of the node, a current draft of the workflow, and information of the data object.

[0091] In some embodiments, determining the corresponding configuration information of multiple nodes includes: determining the configuration order of the multiple nodes based on a depth-first traversal strategy; and determining the configuration information of each node in the multiple nodes by calling the function blocks for node configuration generation in sequence according to the configuration order.

[0092] In some embodiments, determining a workflow framework corresponding to a workflow includes: in response to determining that a workflow editing request includes a workflow modification request, determining a modification plan for the workflow based on the workflow modification request and a current draft of the workflow using a first machine learning model; and in response to the modification plan indicating a modification to the workflow framework, updating the workflow framework corresponding to the workflow based on the workflow editing request, the current draft of the workflow, and information of the data object using a second machine learning model.

[0093] In some embodiments, determining a workflow framework corresponding to the workflow further comprises: in response to a modification plan indicating a modification to configuration information of a first node among the plurality of nodes, updating configuration information of the first node based on the workflow framework.

[0094] In some embodiments, method 400 also includes: determining summary information of the workflow based on a workflow framework corresponding to the workflow, corresponding configuration information of multiple nodes included in the workflow, and historical input context; determining a title of the workflow based on the summary information; and presenting the summary information and title in the interface of the data object.

[0095] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 5A schematic structural block diagram of an apparatus 500 for creating a model-based workflow according to some embodiments of the present disclosure is shown. Apparatus 500 may be implemented or included in, for example, a terminal device 110, or a server 130, or partially implemented in the terminal device 110 and partially implemented in the server 130. Each module / component in apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0096] like Figure 5 As shown, the device 500 includes a workflow framework determination module 510, which is configured to determine, in response to receiving a workflow editing request issued in a data object, a workflow framework corresponding to the workflow based on the workflow editing request, the current draft of the workflow and information of the data object using at least one machine learning model, wherein the workflow framework indicates corresponding node types of multiple nodes included in the workflow and a topological structure of the multiple nodes, and the current draft includes a structured representation of the current state of the workflow; a configuration information determination module 520, which is configured to determine corresponding configuration information of multiple nodes according to the workflow framework; and a workflow determination module 530, which is configured to determine the workflow based on the workflow framework and the corresponding configuration information of the multiple nodes.

[0097] In some embodiments, the apparatus 500 further includes a current draft determining module configured to: in response to determining that the workflow editing request includes a workflow creation request, determine the workflow structured representation in a blank state as the current draft.

[0098] In some embodiments, the workflow framework determination module 510 is further configured to: determine intermediate protocol information corresponding to the current draft, the intermediate protocol information being used to describe a structured representation using a language adapted to at least one machine learning model; and generate a workflow framework using at least one machine learning model based on the intermediate protocol information, information of the data object, and a workflow editing request.

[0099] In some embodiments, the current draft determination module is further configured to: update the current draft of the workflow based on the workflow framework; and present the updated current draft of the workflow.

[0100] In some embodiments, the workflow framework also indicates corresponding configuration fields and corresponding descriptive information of multiple nodes, the descriptive information indicates at least one operation of the corresponding node, the configuration field indicates a parameter of at least one operation, and the configuration information determination module 520 is further configured to: for a node among the multiple nodes, determine the parameter value of at least one operation corresponding to the node based at least on the descriptive information of the node; and add the parameter value to the configuration field of the node as part of the configuration information of the node.

[0101] In some embodiments, the configuration information determination module 520 is further configured to: receive user input of configuration information for the node; and determine parameter values ​​based on the description information of the node and the user input.

[0102] In some embodiments, the configuration information determination module 520 is further configured to: utilize a machine learning model to determine parameter values ​​based on the description information of the node, the current draft of the workflow, and the information of the data object.

[0103] In some embodiments, the configuration information determination module 520 is further configured to: determine the configuration order of multiple nodes based on a depth-first traversal strategy; and determine the configuration information of each node in the multiple nodes by calling the function blocks for node configuration generation in sequence according to the configuration order.

[0104] In some embodiments, the workflow framework determination module 510 is further configured to: in response to determining that the workflow editing request includes a workflow modification request, determine a modification plan for the workflow based on the workflow modification request and the current draft of the workflow using a first machine learning model; and in response to the modification plan indicating a modification to the workflow framework, update the workflow framework corresponding to the workflow based on the workflow editing request, the current draft of the workflow, and information of the data object using a second machine learning model.

[0105] In some embodiments, the workflow framework determination module 510 is further configured to: in response to the modification plan indicating modification of configuration information of a first node among the plurality of nodes, update the configuration information of the first node based on the workflow framework.

[0106] In some embodiments, the device 500 also includes an information determination module, which is configured to: determine summary information of the workflow based on the workflow framework corresponding to the workflow, corresponding configuration information of multiple nodes included in the workflow, and historical input context; determine the title of the workflow based on the summary information; and present the summary information and title in the interface of the data object.

[0107] The units and / or 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 units and / or modules can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units and / or modules in the device 500 can be implemented at least in part by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0108] Figure 6 1 is a block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented. The electronic device 600 may be used to implement, for example, Figure 1 The terminal device 110 shown. It should be understood that Figure 6 The illustrated electronic device 600 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein.

[0109] refer to Figure 6 , electronic device 600 is in the form of a general electronic device. Components of electronic device 600 may include, but are not limited to, one or more processors or processors 610, memory 620, storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processor 610 may be a real or virtual processor and is capable of performing various processes according to a program stored in memory 620. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to increase the parallel processing capabilities of electronic device 600.

[0110] The electronic device 600 typically includes a plurality of computer storage media. Such media can be any available media accessible to the electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 620 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 630 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 600.

[0111] The electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 6 As shown in FIG, a magnetic disk drive for reading from or writing to a removable, non-volatile magnetic disk (e.g., a "floppy disk") and an optical disk 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. Memory 620 may include a computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0112] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 600 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 600 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0113] The input device 650 may be one or more input devices, such as a mouse, keyboard, or trackball. The output device 660 may be one or more output devices, such as a display, a speaker, or a printer. The electronic device 600 may also communicate with one or more external devices (not shown) through the communication unit 640 as needed, such as a storage device, a display device, or the like, with one or more devices that allow a user to interact with the electronic device 600, or with any device that allows the electronic device 600 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0114] 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.

[0115] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, devices, equipment, 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.

[0116] 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.

[0117] 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.

[0118] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0119] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, non-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 intended 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 model-based workflow creation method, comprising: In response to receiving a workflow edit request issued in a data object, determining, using at least one machine learning model, a workflow framework corresponding to the workflow based on the workflow edit request, a current draft of the workflow, and information about the data object, the workflow framework indicating corresponding node types of a plurality of nodes included in the workflow and a topological structure of the plurality of nodes, the current draft including a structured representation of a current state of the workflow; as well as Determining corresponding configuration information of the plurality of nodes according to the workflow framework; as well as The workflow is determined based on the workflow framework and corresponding configuration information of the plurality of nodes.

2. The method according to claim 1, further comprising: In response to determining that the workflow editing request includes a workflow creation request, a workflow structured representation in a blank state is determined as the current draft.

3. The method according to claim 1, wherein determining a workflow framework corresponding to the workflow comprises: determining intermediate protocol information corresponding to the current draft, the intermediate protocol information being used to describe the structured representation using a language adapted for the at least one machine learning model; as well as The workflow framework is generated using the at least one machine learning model based on the intermediate protocol information, the information of the data object, and the workflow editing request.

4. The method according to claim 1, further comprising: Based on the workflow framework, updating the current draft of the workflow; as well as An updated current draft of the workflow is presented.

5. The method according to claim 1 , wherein the workflow framework further indicates corresponding configuration fields and corresponding description information of the plurality of nodes, the description information indicates at least one operation of the corresponding node, the configuration field indicates a parameter of the at least one operation, and determining the corresponding configuration information of the plurality of nodes comprises: For a node among the plurality of nodes, Determining a parameter value of at least one operation corresponding to the node based at least on the description information of the node; as well as The parameter value is added to the configuration field of the node as part of the configuration information of the node.

6. The method according to claim 5, wherein determining a parameter value of at least one operation corresponding to the node comprises: receiving user input of the configuration information for the node; as well as The parameter value is determined based on the description information of the node and the user input.

7. The method according to claim 5, wherein determining a parameter value of at least one operation corresponding to the node comprises: The parameter value is determined by using a machine learning model based on the description information of the node, the current draft of the workflow, and the information of the data object.

8. The method of claim 1 , wherein determining corresponding configuration information of the plurality of nodes comprises: Determining the configuration order of the multiple nodes based on a depth-first traversal strategy; as well as The configuration information of each of the plurality of nodes is determined respectively by sequentially calling the function blocks for node configuration generation according to the configuration order.

9. The method according to claim 1, wherein determining a workflow framework corresponding to the workflow comprises: In response to determining that the workflow edit request includes a workflow modification request, determining a modification plan for the workflow using a first machine learning model based on the workflow modification request and a current draft of the workflow; as well as In response to the modification plan indicating a modification to the workflow framework, the workflow framework corresponding to the workflow is updated using a second machine learning model based on the workflow edit request, the current draft of the workflow, and the information of the data object.

10. The method according to claim 9, further comprising: In response to the modification plan indicating modification of configuration information of a first node among the plurality of nodes, the configuration information of the first node is updated based on the workflow framework.

11. The method according to claim 1 , further comprising: Determining summary information of the workflow based on a workflow framework corresponding to the workflow, corresponding configuration information of a plurality of nodes included in the workflow, and historical input context; determining a title of the workflow based on the summary information; as well as The summary information and the title are presented in an interface of the data object.

12. An apparatus for creating a model-based workflow, comprising: a workflow framework determination module configured to, in response to receiving a workflow edit request issued in a data object, determine a workflow framework corresponding to the workflow based on the workflow edit request, a current draft of the workflow, and information about the data object using at least one machine learning model, wherein the workflow framework indicates corresponding node types of a plurality of nodes included in the workflow and a topological structure of the plurality of nodes, and the current draft includes a structured representation of a current state of the workflow; A configuration information determination module is configured to determine corresponding configuration information of the plurality of nodes according to the workflow framework; as well as The workflow determination module is configured to determine the workflow based on the workflow framework and corresponding configuration information of the multiple nodes.

13. An electronic device comprising: at least one processor; as well as At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 11 when executed by the at least one processor.

14. A computer-readable storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions can be executed by a processor to implement the method according to any one of claims 1 to 11.

15. A computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 11.

Images