Workflow configuration method and device, medium, equipment and computer program product

Abstract

The invention discloses a workflow configuration method and device, a medium, equipment and a computer program product, and relates to the technical field of large language models.The method comprises the steps that in response to configuration of a target node in a workflow, candidate reference nodes corresponding to the target node are determined according to layout information of the workflow, the layout information comprises a plurality of nodes in the workflow and association relationships among the nodes; determining an input text of the agent based on the layout information, the description information of the target node, the cue word of the agent and the node information of the candidate reference node; and configuring the target node based on the input text and the intelligent agent to obtain configuration information of the target node. Therefore, the accuracy of the determined configuration information of the target node can be improved, and the problem that parameters referenced by node configuration are wrong due to the deviation of action scope understanding of the intelligent agent on the variables in the layout information is avoided.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of large language models and agent, in particular, to a workflow configuration method, device, medium, equipment and computer program product. BACKGROUND

[0002] With the application of large language models (LLM), the workflow configuration experience has changed from traditional manual mouse dragging operation to automatic configuration by LLM driven agent through natural language dialogue. In related technologies, the correct prompt words are usually generated for nodes to help the agent understand the syntax of the layout information of the workflow, so that the agent generates node configuration through reasoning, such as determining what problem the current workflow is to solve, what position the current node is in, and what configuration work the current node has. However, due to the bias of the agent's understanding of the scope of variables in the layout information, the parameters referenced by the node configuration may be incorrect, such as the current node referencing the internal parameters of another node, resulting in the workflow configuration failing to run successfully. SUMMARY

[0003] This summary is provided to introduce a selection of concepts, which are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used in limiting the scope of the claimed subject matter.

[0004] In a first aspect, the present disclosure provides a workflow configuration method, comprising: In response to configuring a target node in a workflow, determining a candidate reference node corresponding to the target node according to layout information of the workflow, wherein the layout information comprises a plurality of nodes in the workflow and an association relationship between the nodes, and the target node is any one of the plurality of nodes; determining input text of an agent based on the layout information, description information of the target node, prompt words of the agent, and node information of the candidate reference node; configuring the target node based on the input text and the agent, and obtaining configuration information of the target node.

[0005] In a second aspect, the present disclosure provides a workflow configuration device, comprising: The first determining module is configured to, in response to configuring a target node in a workflow, determine a candidate reference node corresponding to the target node according to layout information of the workflow, wherein the layout information contains a plurality of nodes in the workflow and an association relationship between the nodes, and the target node is any one of the plurality of nodes. The second determining module is configured to determine the input text of the agent based on the layout information, description information of the target node, a prompt word of the agent, and node information of the candidate reference node. The configuration module is configured to configure the target node based on the input text and the agent, and obtain configuration information of the target node.

[0006] In a third aspect, the present disclosure provides a computer readable medium having a computer program stored thereon, the computer program being executed by a processing device to implement the steps of the method of the first aspect.

[0007] In a fourth aspect, the present disclosure provides an electronic device, comprising: a storage device having a computer program stored thereon; a processing device configured to execute the computer program in the storage device to implement the steps of the method of the first aspect.

[0008] In a fifth aspect, the present disclosure provides a computer program product comprising a computer program, the computer program being executed by a processor to implement the steps of the method of the first aspect.

[0009] In the above technical solution, when a target node in a workflow is configured, a candidate reference node of the node can be determined based on layout information of the workflow, so as to obtain a visible node corresponding to the current node. Then, when an agent configures and reasons the node, the candidate reference node is given to the agent as a context, without the agent needing to understand and think about the layout information. This enables the agent to directly select from the candidate reference node, effectively reduces the reasoning data amount of the agent, improves the accuracy of the configuration information of the determined target node, avoids the problem of incorrect node configuration reference parameters caused by the agent's deviation in understanding the scope of variables in the layout information, improves the accuracy of the agent's configuration of the node, and ensures the effective operation of the obtained workflow after configuration.

[0010] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0011] The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings. The same or similar components have the same or similar reference labels. It should be understood that the drawings are not necessarily to scale, with emphasis instead being placed upon illustrating the principles of the embodiments of the present disclosure. In the drawings: Figure 1 is a flowchart of a workflow configuration method according to an embodiment of the present disclosure.

[0012] Figure 2 is a schematic diagram of a workflow according to an embodiment of the present disclosure.

[0013] Figure 3 is a schematic diagram of a workflow according to another embodiment of the present disclosure.

[0014] Figure 4 is a block diagram of a workflow configuration apparatus according to an embodiment of the present disclosure.

[0015] Figure 5 shows a structural schematic diagram of an electronic device suitable for implementing embodiments of the present disclosure. DETAILED DESCRIPTION

[0016] Embodiments of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings. While several embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and fully convey the scope of the present disclosure to those skilled in the art. It should be understood that the drawings and embodiments of the present disclosure are only for illustrative purposes and are not intended to limit the scope of protection of the present disclosure.

[0017] It should be understood that each step recited in the method embodiments of the present disclosure can be executed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the execution of the steps shown. The scope of the present disclosure is not limited in this respect.

[0018] As used herein, the term "includes" and its variants are to be read to be equivalent to "including but not limited to." The term "based on" is to be read as "based, at least in part, on." The term "one embodiment" means "at least one embodiment." The term "another embodiment" means "at least one additional embodiment." The term "some embodiments" means "at least some embodiments." Related terms have analogous meanings.

[0019] It should be noted that the terms "first", "second", and so on used in the present disclosure are merely used to distinguish different apparatuses, modules, or units, and are not intended to limit the order or interdependence of the functions performed by these apparatuses, modules, or units.

[0020] It should be noted that the modification of "one" and "multiple" mentioned in the present disclosure is illustrative but not restrictive, and those skilled in the art should understand that "one or more" should be understood unless otherwise explicitly indicated in the context.

[0021] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not used to limit the scope of the messages or information.

[0022] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type, use range, use scenario, etc. of the personal information involved in the present disclosure should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations.

[0023] For example, in response to receiving the active request of the user, prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using the personal information of the user. Thus, the user can voluntarily choose whether to provide the personal information to the software or hardware such as electronic device, application program, server or storage medium, etc. that performs the operation of the technical solutions of the present disclosure according to the prompt information.

[0024] As an optional but non-limiting implementation manner, in response to receiving the active request of the user, the manner of sending prompt information to the user may, for example, be a pop-up window manner, and the prompt information may be presented in the form of text in the pop-up window. In addition, the pop-up window may also carry selection controls for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0025] It can be understood that the above notification and user authorization process is only illustrative, and does not limit the implementation manner of the present disclosure, and other manners meeting the relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0026] At the same time, it can be understood that the data (including but not limited to the data itself, the acquisition or use of the data) involved in the present technical solutions should comply with the requirements of the relevant laws and regulations and relevant provisions.

[0027] Figure 1 As shown in FIG. 1, a flowchart of a workflow configuration method provided according to an embodiment of the present disclosure is shown, which can include the following steps. Figure 1 As shown in FIG. 1, a flowchart of a workflow configuration method provided according to an embodiment of the present disclosure is shown, which can include the following steps. In step 11, in response to configuring a target node in the workflow, a candidate reference node corresponding to the target node is determined according to layout information of the workflow, wherein the layout information contains a plurality of nodes in the workflow and the association relationship between the nodes, and the target node is any one of the plurality of nodes.

[0028] The candidate reference node of the target node can represent an accessible node of the target node in the workflow, and the target node can perform subsequent data processing based on data in the candidate reference node.

[0029] As an example, the layout information of the workflow can be written by a configuration user based on an actual application scenario, and the layout information can be represented based on a DSL (Domain-Specific Language). In the field of workflow, a workflow DSL can use a concise syntax to describe tasks, dependency relationships, branching logic, trigger conditions, and the like in a process, close to business process terminology, and avoid redundant structures of general programming languages. The following is an example of the representation of the layout information of the workflow: nodes: - start - functional node A1 - control flow node B1: block_0: # if blocks: # There can be multiple nodes in the block - functional node C1 block_1: # else blocks: - functional node D1 - functional node E1 - end The workflow can include a start node start, a functional node A1, a control flow node B1, a functional node C1, a functional node D1, a functional node E1, and an end node end, and the relationship between the nodes is as shown in Figure 2 The functional node C1 and the functional node D1 are internal nodes of the control flow node B1.

[0030] In this embodiment, if the functional node D1 needs to be configured, the corresponding candidate reference node is the start node start, the functional node A1, and the control flow node B1.

[0031] In step 12, the input text of the agent is determined based on the layout information, the description information of the target node, the prompt word of the agent, and the node information of the candidate reference node.

[0032] The prompt word of the intelligent agent can include a system prompt word to define the role and identity of the intelligent agent, so that the intelligent agent knows the role it needs to play, and the professional knowledge field in which the intelligent agent is located is used for data reasoning. The prompt word of the intelligent agent can also include a task target and a task rule. The task target is used to indicate the task that the intelligent agent needs to complete, and the task rule is used to indicate the rule that needs to be met in the process of completing the task by the intelligent agent. For example, in the workflow configuration scenario, the task target can be to generate a workflow described by a user, and the task rule can include rules that need to be met in the process of generating the workflow, such as type constraints of nodes, syntax constraints of expressions, naming principles, prohibition of referencing non-existent variables, and variables outside a block cannot access internally declared variables of nodes inside the block. The task rule is a rule that needs to be followed in the process of generating the workflow, and the present disclosure does not limit this.

[0033] In this step, the layout information, the description information of the target node, the node information of the candidate reference node, and the prompt word of the intelligent agent can be combined to obtain the input text, so that the node information of the candidate reference node is used as a context for the intelligent agent to configure.

[0034] In step 13, the target node is configured based on the input text and the intelligent agent, and configuration information of the target node is obtained.

[0035] If the input text is input into the intelligent agent, the intelligent agent can perform reasoning based on the input text to achieve configuration of the target node. In the related art, the syntax of the workflow DSL needs to be introduced to the intelligent agent, so that the intelligent agent further tries to understand the input workflow DSL after understanding the syntax, and then configures the node through the context to output the configuration information. Compared with the related art, in the embodiment, the intelligent agent can directly select the node and the parameter from the candidate reference node of the target node, which reduces the amount of data that needs to be reasoned by the intelligent agent.

[0036] In the above technical solution, when the target node in the workflow is configured, the candidate reference node of the node can be determined based on the layout information of the workflow, so that the visible node corresponding to the current node is obtained. Then, when the intelligent agent configures and reasons the node, the candidate reference node is given to the intelligent agent as a context, so that the intelligent agent does not need to understand and think about the layout information. The intelligent agent can directly select from the candidate reference node, which can effectively reduce the amount of data that needs to be reasoned by the intelligent agent, improve the accuracy of the configuration information of the determined target node, avoid the problem that the scope of the variable in the layout information is understood by the intelligent agent, and cause the node configuration to reference incorrect parameters, improve the accuracy of the configuration of the node by the intelligent agent, and ensure the effective operation of the obtained workflow after configuration.

[0037] In some possible embodiments, the method may further include: In response to the input of node description information in the configuration interface of the workflow, the node is identified as the target node, and the target node in the workflow is configured.

[0038] In some implementation scenarios, the layout information may only include the nodes in the workflow and the relationships between them, as shown in the workflow layout information above. Based on this layout information, the agent can determine the nodes that need to be generated through reasoning and construct edges based on the relationships between the nodes, thereby demonstrating the workflow process.

[0039] As an example, the workflow can be displayed in the workflow configuration interface, where users can configure individual nodes based on their actual application needs. For instance, functional node A1 can be selected as the target node. For example, the user selects functional node A1 in the configuration interface and uploads its description information. This description can include a node identifier, node name, and node definition. The node definition can include a title and description, such as calculating the sum of two numbers. Furthermore, the node definition can include definitions of input and output parameters, enabling the agent to write code to implement script logic based on this description information.

[0040] As another example, in response to determining that the layout information contains description information of a node, the node is identified as the target node, and the target node in the workflow is configured.

[0041] As an example, the layout information includes the various nodes in the workflow and the relationships between them, constraining the overall architecture of the workflow. Correspondingly, the layout information can also include node descriptions, making the descriptions part of the layout information. Furthermore, the nodes to be configured can be specified in the layout information, as shown in the following example: # Nodes that need to be configured id: script_0 # Configuration Commands It accepts input from the start node, calculates the sum of the two numbers, and outputs the result to the sum field.

[0042] Therefore, in this embodiment, when it is determined that the layout information includes node description information, it is considered that the nodes need to be configured synchronously. At this time, the node specified in the layout information that needs to be configured can be taken as the target node, and it is determined that the target node needs to be configured. In the example above, the node with id_script_0 is taken as the target node, and it is determined that this target node needs to be configured.

[0043] Thus, by the technical solution, the description information of the node can be contained in the layout information, so that the node configuration is synchronized when the workflow is generated, and the visual configuration of the workflow can be supported, so that the node input description information is selected in the configuration interface for separate configuration, the diversity of the node configuration in the workflow is improved, and the application range of the method is widened.

[0044] In some possible embodiments, the determining the candidate reference node corresponding to the target node according to the layout information of the workflow can include: If the layout information is fixed-canvas layout information, the node before the target node in the layout information and having a nesting level higher than or equal to the target node in the workflow is determined as the candidate reference node of the target node, wherein the edge relationship between the nodes in the fixed-canvas layout information is determined based on the order of the nodes in the layout information, and the nesting level of a node is higher than the nesting level of the internal node of the node.

[0045] In the fixed-canvas, the edge relationship of the node can be determined based on the order relationship and the nesting relationship of the node, for example, the layout information can contain the type of the node and the edge relationship. As described above, the example of the layout information is an example of the fixed-canvas, in which the preceding node in the adjacent nodes points to the following node in the fixed-canvas layout information, and the nesting relationship between different nodes is determined by the block. For example, the start and the function node A1 are adjacent nodes, in which the preceding node is the start and the following node is the function node A1, and the edge relationship in the layout information is that the start points to the function node A1.

[0046] For the following content in the layout information: Control flow node B1: block_0: # if blocks: # There can be multiple nodes in the blocks - Function node C1 block_1: # else blocks: - Function node D1 That is, the control flow node B1 is defined by the block to have two internal nodes, which are the functional node C1 of block_0 and the functional node D1 of block_1. Among them, the type of the node can include types such as loop, batch, condition, parallel, etc. For the above-mentioned types of nodes, internal nested nodes can be defined by the block, and the internal nested nodes still comply with the sequential decision. The variables outside the block cannot access the output parameters of the internal nodes of the block and the variables declared inside the block.

[0047] Therefore, in this embodiment, based on the block, the nesting relationship can be determined, the nesting level S1 can include the node start, the node A1, the node B1, the node E1 and the node end, the nesting level S2 can include the node C1 and the node D1, and the nesting level S1 is higher than the nesting level S2. For example, the target node determined is the node C1, the nodes before the target node C1 in the layout information are determined to be the node start, the node A1 and the node B1 after traversing the layout information, and the nesting level S1 of the node start, the node A1 and the node B1 in the workflow is higher than the nesting level S2 of the target node C1. Therefore, the node start, the node A1 and the node B1 can be determined as the candidate reference nodes of the target node C1. For another example, the target node determined is the node E1, the nodes before the target node E1 in the layout information are determined to be the node start, the node A1, the node B1, the node C1 and the node D1 after traversing the layout information, wherein the nesting level S1 of the node start, the node A1 and the node B1 in the workflow is equal to the nesting level S1 of the target node E1, and the nesting level S2 of the node C1 and the node D1 in the workflow is lower than the nesting level S1 of the target node E1. Therefore, the node start, the node A1 and the node B1 can be determined as the candidate reference nodes of the target node E1, so that the reference of the node E1 to the internal nodes C1 and D1 of the node B1 can be avoided.

[0048] Therefore, by the above technical solution, the candidate reference nodes that can be referenced by the current node can be determined based on the order relationship and the nesting relationship of the nodes in the layout information by traversing the layout information, which provides an effective candidate node range for the subsequent reasoning of the agent to configure the nodes, so as to improve the accuracy of the configuration information of the output nodes and ensure the effective operation of the workflow.

[0049] In some possible embodiments, the determining the candidate reference nodes corresponding to the target node according to the layout information of the workflow can include: If the layout information is layout information of a free canvas, based on the edge relationship in the layout information, a source node pointing to the target node is determined, wherein the layout information of the free canvas contains nodes and edge relationship between the nodes; The source node is taken as a new target node, and the determination of the source node pointing to the target node based on the edge relationship in the layout information is re-executed until the determined source node is a start node in the workflow; Each source node traversed is taken as the candidate reference node.

[0050] In the free canvas, a node array and an edge relationship array are usually needed to jointly describe the workflow, that is, which nodes exist and how the nodes are connected, and the sequence of the nodes in the node array is irrelevant to the edge relationship between the nodes, which is determined through the edge relationship array. As shown below, an example of the layout information of the free canvas is shown: nodes: - start - end - loop node A2 nodes: - function node B2 - function node C2 edges: - from: block_begin to: function node B2 - from: function node B2 to: function node C2 - from: function node C2 to: block_end - function node D2 edges: - from: start to: loop node A2 - from: loop node A2 to: function node D2 - from: function node D2 to: end The nodes are used to represent the nodes in the workflow, and the nesting between the nodes is realized through the nodes. The workflow corresponding to the above layout relationship is shown in Figure 3 , wherein the loop node A2 contains the function nodes B2 and C2, and the edge relationship between different nodes is defined through edges.

[0051] As an example, when the determined target node is node C2, the edge relationship in the layout information is traversed to determine that the node pointing to node C2 is node B2, and then the source node traversed is B2. Then B2 is taken as the target node to traverse the edge relationship in the layout information, and at this time the edge "from: block_begin to: function node B2" is traversed. For a node with a nested relationship, the source node is determined based on the edge relationship and the node, such as taking the node to which the nested body belongs as the source node. In this example, node A2 to which block_begin belongs can be taken as the source node. Then A2 is taken as the target node to traverse the edge relationship in the layout information, and it is determined that the node pointing to node A2 is node start, and the traversal ends.

[0052] The source nodes traversed in this process include node B2, node A2, and node start, and the candidate reference nodes of the target node C2 include node B2, node A2, and node start.

[0053] As another example, when the determined target node is node D2, the edge relationship in the layout information is traversed to determine that the node pointing to node D2 is node A2, and then the source node traversed is A2. Then A2 is taken as the target node to traverse the edge relationship in the layout information, and it is determined that the node pointing to node A2 is node start, and the traversal ends.

[0054] The source nodes traversed in this process include node A2 and node start, and the candidate reference nodes of the target node D2 include node A2 and node start.

[0055] Therefore, by the above technical solution, the candidate reference nodes that can be referenced by the current node can be determined based on the nodes and edge relationships in the layout information by traversing the layout information, which provides an effective candidate node range for the subsequent reasoning of the agent to configure the nodes, thereby improving the accuracy of the configuration information of the output nodes and ensuring the effective operation of the workflow.

[0056] In some possible embodiments, the prompt word contains node configuration example fields corresponding to multiple types, for example, the prompt word can contain a node configuration example sub-prompt word, and the sub-prompt word contains node configuration example fields of various types, as shown below: # Node configuration example

[0057] In the above information, the node configuration example fields of start, end, script, llm, callflow, connector, condition, forloop, batch, and parallel types are contained.

[0058] When the task of the agent is complex or requires a specific format, an example can be provided to help the agent understand the expected output. Accordingly, determining the input text of the agent based on the layout information, the description information of the target node, the prompt word of the agent, and the node information of the candidate reference node can include: Determining a target type of the target node. The target type of the target node can be determined based on the description information of the target node. For example, the target type is script.

[0059] Then, a node configuration example corresponding to the target type is obtained. The node configuration examples corresponding to different types can be pre-stored and configured. The node configuration example indicates the representation example of the node configuration under the corresponding type, and can provide an example reference for the output result of the agent. In this step, the node configuration example of script can be obtained from the storage location.

[0060] Then, the node configuration example is replaced with the node configuration example field of the target type in the prompt word, and the input text is obtained based on the updated prompt word, the layout information, the description information, and the node information.

[0061] As in the above example, the obtained node configuration example of script can replace the script field in the node configuration example prompt word, i.e., the script in the obtained node configuration example replaces the script in the node configuration example prompt word, so that the node configuration example required when the node is configured can be included in the node configuration example prompt word. Similarly, the updated prompt word, the layout information, the description information, and the node information can be combined to obtain the input text.

[0062] Therefore, by using the above technical solution, the node configuration example under the type of the target node can be added in the input text, so that the agent can more clearly understand how the node under the type should be configured, the node configuration example can be added on demand, the token occupation of the input text by invalid node configuration examples can be avoided, the understanding cost of the agent can be reduced, the accuracy of the reasoning result of the agent can be improved, and the node can be accurately configured.

[0063] In some possible embodiments, the configuring the target node based on the input text and the agent can include: The input text is input into the agent, so that the agent determines the node pointing to the target node from the candidate reference node based on the prompt word, the description information, and the node information, and determines the input parameter of the target node based on the output parameter of the candidate reference node.

[0064] The output parameter of a node is a parameter that can be referenced by a subsequent node, and a parameter declared internally in a node is usually only accessible within the node and cannot be accessed by other nodes. In this embodiment, the output parameter of a node can be determined based on the node information of the candidate reference node.

[0065] Accordingly, the input text is input into the agent in this step, and the agent can determine the node referenced by the target node as the candidate reference node based on the context in the input text when reasoning. Further, the agent can select the node pointing to the target node from the candidate reference nodes based on the prompt word of the agent, the description information of the current node, and the node information of the candidate reference nodes, and determine the input parameter of the target node in the output parameter of the node pointing to the target node.

[0066] For example, in the example in the above Figure 2 , the node start, the node A1, and the node B1 are the candidate reference nodes of the target node E1. When the node E1 is configured, the node pointing to the target node can be determined from the candidate reference nodes based on the prompt word, the description information of the node E1, and the node information of the node start, the node A1, and the node B1 respectively. When it is determined that the node pointing to the target node is the node A1, the input parameter of the node E1 can be determined from the output parameter of the node A1. When it is determined that the node pointing to the target node is the node B1, the input parameter of the node E1 can be determined from the output parameter of the node B1.

[0067] Therefore, by the above technical solution, the node information of the candidate reference node corresponding to the target node is added in the input text of the agent, which can effectively avoid the problem of referencing invisible nodes in the reasoning process of the agent for workflow configuration, effectively improve the accuracy and efficiency of node configuration, and to a certain extent, reduce the reasoning difficulty caused by complex edge relationships in the workflow, reduce the reasoning data amount of the agent, and further improve the configuration efficiency and accuracy of the agent for the nodes of the workflow.

[0068] Based on the same inventive concept, the disclosure also provides a workflow configuration device, as shown in Figure 4 The device 10 comprises: A first determination module 100 configured to determine candidate reference nodes corresponding to a target node in a workflow according to layout information of the workflow in response to configuration of the target node, wherein the layout information comprises a plurality of nodes in the workflow and an association relationship between the nodes, and the target node is any one of the plurality of nodes. A second determination module 200 configured to determine input text of an agent based on the layout information, description information of the target node, a prompt word of the agent, and node information of the candidate reference nodes. The configuration module 300 is configured to configure the target node based on the input text and the agent, and obtain configuration information of the target node.

[0069] Optionally, the first determination module comprises: A first determination sub-module is configured to, if the layout information is layout information of a fixed canvas, determine, as a candidate reference node of the target node, a node in the layout information that is before the target node and has a nesting level higher than or equal to the target node in the workflow, wherein an edge relationship between nodes in the layout information of the fixed canvas is determined based on an order of the nodes in the layout information, and a node has a nesting level higher than a nesting level of an internal node of the node.

[0070] Optionally, the first determination module comprises: A second determination sub-module is configured to, if the layout information is layout information of a free canvas, determine, based on an edge relationship in the layout information, a source node pointing to the target node, wherein the layout information of the free canvas comprises nodes and an edge relationship between the nodes. A third determination sub-module is configured to take the source node as a new target node, and trigger the second determination sub-module to perform the determination of the source node pointing to the target node based on the edge relationship in the layout information, until the determined source node is a start node in the workflow. A fourth determination sub-module is configured to take each of the traversed source nodes as the candidate reference node.

[0071] Optionally, the prompt word comprises a node configuration example field corresponding to a plurality of types. The second determination module comprises: A fifth determination sub-module is configured to determine a target type of the target node. An acquisition sub-module is configured to acquire a node configuration example corresponding to the target type. A sixth determination sub-module is configured to replace the node configuration example field of the target type in the prompt word with the node configuration example, and obtain the input text based on the updated prompt word, the layout information, the description information, and the node information.

[0072] Optionally, the configuration module is configured to: input the input text into the agent, so that the agent determines, based on the prompt word, the description information, and the node information, a node pointing to the target node from the candidate reference node, and determines an input parameter of the target node based on an output parameter of the candidate reference node.

[0073] Optionally, the apparatus further comprises: a third determining module, configured to determine a node as the target node and determine to configure the target node in the workflow in response to determining that the layout information contains description information of the node; or determine a node as the target node and determine to configure the target node in the workflow in response to inputting description information of the node in the configuration interface of the workflow.

[0074] Reference will now be made to the following description Figure 5 , which shows a structural diagram of an electronic device (e.g., a terminal device or a server) 600 suitable for use in implementing embodiments of the present disclosure. The terminal device in embodiments of the present disclosure can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet PCs), PMPs (Portable Multimedia Players), car terminals (e.g., car navigation terminals), and the like, as well as fixed terminals such as digital TVs, desktop computers, and the like. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functions and use range of embodiments of the present disclosure.

[0075] As shown in Figure 5 , the electronic device 600 can include a processing device (e.g., a central processing unit, a graphics processing unit, or the like) 601 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 602 or loaded from a storage device 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the electronic device 600 are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0076] In general, the following devices can be connected to the I / O interface 605: input devices 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, and the like; output devices 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, and the like; storage devices 608 including, for example, a magnetic tape, a hard disk, and the like; and communication devices 609. The communication devices 609 can allow the electronic device 600 to communicate wirelessly or via a wire with other devices to exchange data. Although Figure 5 The electronic device 600 is shown with various devices, but it should be understood that all of the shown devices are not required to be implemented or present. More or fewer devices can alternatively be implemented or present.

[0077] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program in accordance with embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program comprising program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

[0078] It should be noted that the computer-readable medium described above in the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination thereof. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program used by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium can include a data signal propagated in baseband or propagated as a carrier wave in a propagated data signal, in which the computer-readable program code is carried. Such a propagated data signal can take a variety of forms, including but not limited to, an electromagnetic signal, an optical signal, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium that can be used to carry or store a program for use by or in connection with an instruction execution system, apparatus, or device, other than the computer-readable storage medium. The program code contained in the computer-readable medium can be transmitted by any suitable medium, including but not limited to, wire, cable, RF (radio frequency), or the like, or any suitable combination thereof.

[0079] In some embodiments, the client, server, or other computing machines utilized by the system can communicate over any known or later developed network protocol, such as the Hypertext Transfer Protocol (HTTP), and can be interconnected with any form or medium of digital data communication (for example, a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet, and peer-to-peer networks (for example, ad hoc peer-to-peer networks), as well as any then-current or later developed networks.

[0080] The computer-readable medium described above can be included in the electronic device described above; alternatively, it can exist separately from the electronic device and be loaded into the electronic device at a later time.

[0081] The computer-readable medium described above carries one or more programs that, when executed by the electronic device, cause the electronic device to: in response to configuration of a target node in a workflow, determine a candidate reference node corresponding to the target node according to layout information of the workflow, wherein the layout information contains a plurality of nodes in the workflow and an association relationship between the nodes, and the target node is any one of the plurality of nodes; determine input text of an agent based on the layout information, description information of the target node, a prompt word of the agent, and node information of the candidate reference node; and obtain configuration information of the target node based on the input text and the configuration of the target node by the agent.

[0082] Computer program code for carrying out operations of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network ("LAN") or a wide area network ("WAN"), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0083] The diagrams of the accompanying drawings and the accompanying text herein illustrate possible architectural, functional, and operational architectures, features, and advantages of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams can represent a module, a segment, or a portion of code that comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0084] The modules involved in the embodiments of the present disclosure can be implemented in the form of software or in the form of hardware. Among them, the name of the module does not constitute a limitation to the module itself in some cases. For example, the first determining module can also be described as "a module that determines the candidate reference node corresponding to the target node in the workflow according to the layout information of the workflow in response to the configuration of the target node in the workflow".

[0085] The functions described above herein can be performed at least in part by one or more hardware logic components. For example, non-limiting example 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), system-on-a-chip (SOCs), complex programmable logic devices (CPLDs), etc.

[0086] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0087] According to one or more embodiments of the present disclosure, example 1 provides a workflow configuration method, the method comprising: In response to configuration of a target node in a workflow, determining a candidate reference node corresponding to the target node according to layout information of the workflow, wherein the layout information contains a plurality of nodes in the workflow and an association relationship between the nodes, and the target node is any one of the plurality of nodes; Determining an input text of an agent based on the layout information, description information of the target node, a prompt word of the agent, and node information of the candidate reference node; Obtaining configuration information of the target node based on the input text and the configuration of the target node by the agent.

[0088] According to one or more embodiments of the present disclosure, example 2 provides the method of example 1, wherein the determining the candidate reference node corresponding to the target node according to the layout information of the workflow comprises: If the layout information is layout information of a fixed canvas, nodes in the layout information that are before the target node and have a nesting level higher than or equal to the target node in the workflow are determined as the candidate reference node of the target node, wherein the edge relationship between the nodes in the layout information of the fixed canvas is determined based on the order of the nodes in the layout information, and the nesting level of a node is higher than the nesting level of an internal node of the node.

[0089] According to one or more embodiments of the present disclosure, example 3 provides the method of example 1, wherein the determining the candidate reference node corresponding to the target node according to the layout information of the workflow comprises: If the layout information is layout information of a free canvas, determining a source node pointing to the target node based on the edge relationship in the layout information, wherein the layout information of the free canvas contains nodes and an edge relationship between the nodes; Taking the source node as a new target node and re-executing the determining the source node pointing to the target node based on the edge relationship in the layout information until the determined source node is a start node in the workflow; Taking each of the traversed source nodes as the candidate reference node.

[0090] According to one or more embodiments of the present disclosure, example 4 provides the method of example 1, wherein the prompt word contains a node configuration example field corresponding to a plurality of types; The determining the input text of the agent based on the layout information, the description information of the target node, the prompt word of the agent, and the node information of the candidate reference node comprises: determine a target type of the target node; obtain a node configuration example corresponding to the target type; replace a node configuration example field of the target type in the prompt word with the node configuration example, and obtain the input text based on the updated prompt word, the layout information, the description information, and the node information.

[0091] According to one or more embodiments of the present disclosure, example 5 provides the method of example 1, wherein the configuring the target node based on the input text and the agent comprises: inputting the input text into the agent to determine a node pointing to the target node from the candidate reference nodes based on the prompt word, the description information, and the node information by the agent, and determining an input parameter of the target node based on an output parameter of the candidate reference node.

[0092] According to one or more embodiments of the present disclosure, example 6 provides the method of example 1, wherein the method further comprises: in response to determining that the layout information contains the description information of the node, determining the node as the target node and determining to configure the target node in the workflow; or in response to inputting the description information of the node in the configuration interface of the workflow, determining the node as the target node and determining to configure the target node in the workflow.

[0093] According to one or more embodiments of the present disclosure, example 7 provides a workflow configuration apparatus, the apparatus comprising: a first determination module configured to, in response to configuring a target node in a workflow, determine a candidate reference node corresponding to the target node according to layout information of the workflow, wherein the layout information contains a plurality of nodes in the workflow and an association relationship between the nodes, and the target node is any one of the plurality of nodes; a second determination module configured to determine an input text of an agent based on the layout information, description information of the target node, a prompt word of the agent, and node information of the candidate reference node; a configuration module configured to configure the target node based on the input text and the agent to obtain configuration information of the target node.

[0094] According to one or more embodiments of the present disclosure, example 8 provides a computer readable medium having stored thereon a computer program, which, when executed by a processing apparatus, implements the steps of the method of any one of examples 1-6.

[0095] According to one or more embodiments of the present disclosure, example 9 provides an electronic device comprising: a storage device having stored thereon a computer program; a processing device for executing the computer program in the storage device to implement the steps of the method of any one of examples 1-6.

[0096] According to one or more embodiments of the present disclosure, example 10 provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of any one of examples 1-6.

[0097] The above description merely provides preferred embodiments of the present disclosure and a principle of applied technology. It should be understood by those skilled in the art that the disclosed scope of the present disclosure is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by the combinations of the above technical features or equivalent features thereof without departing from the above disclosed concept. For example, the technical solutions formed by the mutual replacement of the above features and the technical features disclosed in the present disclosure (but not limited to) having similar functions.

[0098] In addition, although each operation is depicted in a particular order, this should not be understood as requiring the operations to be performed in the particular order shown or in a sequential order. In certain circumstances, multitasking and parallel processing can be advantageous. Similarly, although several implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments can also be combined in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented separately or in any suitable sub-combination.

[0099] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims. With respect to the devices in the above-described embodiments, the specific manner in which the various modules perform operations has been described in detail in the embodiments related to the method, and will not be described here in detail.

Claims

1. A workflow configuration method, characterized in that, The method includes: In response to configuring a target node in the workflow, a candidate reference node corresponding to the target node is determined based on the layout information of the workflow. The layout information includes multiple nodes in the workflow and the relationships between the nodes, and the target node is any one of the multiple nodes. Based on the layout information, the description information of the target node, the prompt words of the agent, and the node information of the candidate reference nodes, the input text of the agent is determined; Based on the input text and the intelligent agent, the target node is configured to obtain the configuration information of the target node.

2. The method according to claim 1, characterized in that, The step of determining the candidate reference node corresponding to the target node based on the workflow layout information includes: If the layout information is the layout information of a fixed canvas, then the nodes in the layout information that are before the target node and whose nesting level in the workflow is higher than or equal to that of the target node are determined as candidate reference nodes of the target node. The edge relationship between nodes in the layout information of the fixed canvas is determined based on the order of the nodes in the layout information, and the nesting level of the node is higher than the nesting level of the internal nodes of the node.

3. The method according to claim 1, characterized in that, The step of determining the candidate reference node corresponding to the target node based on the workflow layout information includes: If the layout information is the layout information of a free canvas, the source node pointing to the target node is determined based on the edge relationships in the layout information, wherein the layout information of the free canvas includes nodes and the edge relationships between nodes; The source node is used as the new target node, and the process of determining the source node pointing to the target node based on the edge relationship in the layout information is repeated until the determined source node is the start node in the workflow. Each of the source nodes encountered during the traversal is used as a candidate reference node.

4. The method according to claim 1, characterized in that, The prompt words contain multiple types of node configuration sample fields; The step of determining the input text of the agent based on the layout information, the description information of the target node, the agent's prompt words, and the node information of the candidate reference nodes includes: Determine the target type of the target node; Obtain the node configuration example corresponding to the target type; Replace the node configuration sample field of the target type in the prompt with the node configuration sample, and obtain the input text based on the updated prompt, the layout information, the description information and the node information.

5. The method according to claim 1, characterized in that, The configuration of the target node based on the input text and the intelligent agent includes: The input text is input into the agent so that the agent can determine the node pointing to the target node from the candidate reference nodes based on the prompt word, the description information and the node information, and determine the input parameters of the target node based on the output parameters of the candidate reference nodes.

6. The method according to claim 1, characterized in that, The method further includes: In response to determining that the layout information includes node description information, the node is identified as the target node, and the target node in the workflow is configured accordingly; or In response to the input of node description information in the configuration interface of the workflow, the node is identified as the target node, and the target node in the workflow is configured.

7. A workflow configuration device, characterized in that, The device includes: The first determining module is configured to, in response to the configuration of a target node in the workflow, determine a candidate reference node corresponding to the target node based on the layout information of the workflow, wherein the layout information includes multiple nodes in the workflow and the relationships between the nodes, and the target node is any one of the multiple nodes; The second determining module is used to determine the input text of the intelligent agent based on the layout information, the description information of the target node, the prompt words of the intelligent agent, and the node information of the candidate reference nodes; The configuration module is used to configure the target node based on the input text and the intelligent agent, and obtain the configuration information of the target node.

8. A computer-readable medium having a computer program stored thereon, characterized in that, When executed by a processing device, the computer program performs the steps of the method according to any one of claims 1-6.

9. An electronic device, characterized in that, include: A storage device on which computer programs are stored; A processing device for executing the computer program in the storage device to implement the steps of the method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-6.

Images