Workflow display method and apparatus, electronic device, and program product

Abstract

The present disclosure relates to a workflow display method and apparatus, an electronic device, and a program product. The method comprises: acquiring a first flowchart associated with a workflow, the first flowchart comprising multiple first components corresponding to multiple requirements of the workflow, and the first components comprising description information of the corresponding requirements. The method further comprises: displaying a second flowchart associated with the workflow, the second flowchart being generated by a target model on the basis of the first flowchart, the second flowchart comprising multiple second components corresponding to the multiple first components, and the second components being used to implement the requirements corresponding to the first components. According to embodiments of the present disclosure, the accuracy of user expressions of workflows can be improved on the basis of description information of functional requirements provided by outline nodes in an outline diagram and logical relationships between the outline nodes, thereby enabling a target model to accurately understand user intent on the basis of the outline diagram, and thus improving workflow accuracy and the success rate of workflow execution.

Description

Method, device, electronic device and program product for displaying a workflow TECHNICAL FIELD

[0001] The present disclosure relates to the field of computers, and more specifically to a method, device, electronic device and program product for displaying a workflow. BACKGROUND

[0002] Workflow refers to a method of representing a series of interlinked, automatically executed business activities in a model in a computer application environment to achieve business process automation. Workflow can be widely applied in enterprise management, office automation, application development and other fields. In the development of workflow, users can select the required task nodes and the logical relationship between the task nodes.

[0003] With the emergence of large language models (LLM), a workflow platform can provide a development method for users to develop a workflow assisted by a large language model. The core task of the large language model in the development process is to understand the user's natural language and determine the user's intention. In order to reduce the development difficulty and improve the development efficiency, how to use the large language model to assist the development of the workflow becomes an important task.

[0004] SUMMARY

[0005] In a first aspect of the present disclosure, a method for displaying a workflow is provided. The method includes obtaining a first flowchart related to the workflow, the first flowchart including a plurality of first components corresponding to a plurality of requirements of the workflow, the first component including description information of the corresponding requirement. The method further includes displaying a second flowchart related to the workflow, the second flowchart being generated by a target model based on the first flowchart, and the second flowchart including a plurality of second components corresponding to the plurality of first components, the second component being used to implement the requirement corresponding to the first component.

[0006] In a second aspect of the present disclosure, a method for displaying a workflow is provided. The method includes receiving a first flowchart related to the workflow from a client, the first flowchart including a plurality of first components corresponding to a plurality of requirements of the workflow, the first component including description information of the corresponding requirement. The method further includes generating a second flowchart related to the workflow based on the first flowchart by a target model, the second flowchart including a plurality of second components corresponding to the plurality of first components, the second component being used to implement the requirement corresponding to the first component. In addition, the method further sends the second flowchart to the client to make the client display the second flowchart.

[0007] In a third aspect of the disclosure, an apparatus for displaying a workflow is provided. The apparatus includes a first flowchart obtaining module configured to obtain a first flowchart related to the workflow, the first flowchart including a plurality of first components corresponding to a plurality of requirements of the workflow, the first component including description information of the corresponding requirement. The apparatus also includes a second flowchart displaying module configured to display a second flowchart related to the workflow, the second flowchart being generated by a target model based on the first flowchart, and the second flowchart including a plurality of second components corresponding to the plurality of first components, the second component being used to implement the requirement corresponding to the first component.

[0008] In a fourth aspect of the disclosure, an apparatus for displaying a workflow is provided. The apparatus includes a first flowchart receiving module configured to receive a first flowchart related to the workflow from a client, the first flowchart including a plurality of first components corresponding to a plurality of requirements of the workflow, the first component including description information of the corresponding requirement. The apparatus also includes a second flowchart generating module configured to generate a second flowchart related to the workflow by a target model based on the first flowchart, the second flowchart including a plurality of second components corresponding to the plurality of first components, the second component being used to implement the requirement corresponding to the first component. In addition, the apparatus also includes a second flowchart sending module configured to send the second flowchart to the client to enable the client to display the second flowchart.

[0009] In a fifth aspect of the disclosure, an electronic device is provided. The electronic device includes a processor; and a memory coupled with the processor, the memory having stored therein instructions that, when executed by the processor, cause the electronic device to perform the method according to any one of the first aspect or the second aspect of the disclosure.

[0010] In a sixth aspect of the disclosure, a computer program product is provided. The computer program product is tangibly stored on a non-transitory computer readable medium and includes machine executable instructions that, when executed, cause a machine to implement the method according to any one of the first aspect or the second aspect of the disclosure.

[0011] The summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. The summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. BRIEF DESCRIPTION OF DRAWINGS

[0012] FIG. 1 shows a schematic diagram of an example environment in which some embodiments of the disclosure can be implemented;

[0013] FIG. 2 shows a flowchart of a method for displaying a workflow according to some embodiments of the disclosure;

[0014] FIG. 3A illustrates a schematic diagram of a page for establishing a profile diagram, according to some embodiments of the present disclosure;

[0015] FIG. 3B illustrates a schematic diagram of a page for node selection, according to some embodiments of the present disclosure;

[0016] FIG. 3C illustrates a schematic diagram of another page for establishing a profile diagram, according to some embodiments of the present disclosure;

[0017] FIG. 3D illustrates a schematic diagram of yet another page for establishing a profile diagram, according to some embodiments of the present disclosure;

[0018] FIG. 3E illustrates a schematic diagram of a page for adjusting a profile diagram, according to some embodiments of the present disclosure;

[0019] FIG. 3F illustrates a schematic diagram of a page for executing a diagram, according to some embodiments of the present disclosure;

[0020] FIG. 4A illustrates a schematic diagram of a profile diagram of a workflow, according to some embodiments of the present disclosure;

[0021] FIG. 4B illustrates a schematic diagram of an execution diagram of a workflow, according to some embodiments of the present disclosure;

[0022] FIG. 5 illustrates a block diagram of an apparatus for displaying a workflow, according to some embodiments of the present disclosure; and

[0023] FIG. 6 illustrates a schematic block diagram of an electronic device, according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0024] It can be understood that all user-related data involved in the technical solution should be acquired and used after authorization by the user. This means that in the technical solution, if the user's personal information needs to be used, the user's explicit consent and authorization are required before the data is acquired, otherwise the relevant data collection and use will not be carried out. It should also be understood that in the implementation of the technical solution, relevant laws and regulations should be strictly followed in the process of data collection, use and storage, and necessary technical and measures should be taken to protect the security of the user's data and ensure the safe use of the data.

[0025] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein, but rather these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for exemplary purposes only and are not intended to limit the scope of protection of the present disclosure.

[0026] In the description of embodiments of the present disclosure, the term "includes" and its conjugations are to be understood to be open-ended, namely, "including but not limited to". The term "based on" is to be understood as "based at least in part on". The term "one embodiment" or "an embodiment" is to be understood as "at least one embodiment". The terms "a first", "a second", etc. can refer to different or same objects, unless explicitly stated otherwise. Other explicit or implicit definitions can also be included below.

[0027] As described above, how to utilize a large language model to assist workflow development is an important task of a workflow platform. In related manners, a complete natural language input by a user is taken as an input of a large language model, so as to output a complete workflow. Specifically, in related manners, a natural language description input by a user is first received and is given to a workflow background for processing. Then, the workflow background parses the natural language through a large language model to generate a workflow and returns the workflow to a front end. Finally, the front end draws the final workflow and displays the workflow on a page for the user.

[0028] In related manners, the generation of a workflow mainly depends on the understanding and conversion of a natural language by a large language model. Compared with manually developing a workflow completely, related manners can simplify the operation steps of a user. However, due to the randomness of the expression of a natural language, a user may not be able to accurately describe the process of a workflow. Moreover, due to errors, ambiguities in a natural language, and the performance of a large language model itself, a large language model may not be able to accurately plan nodes of a workflow and details in the nodes. Therefore, when planning the nodes of a workflow and the details thereof, a large language model in related manners is difficult to achieve a high accuracy, and there are problems such as node selection errors, node configuration errors, and parameter mapping errors, which result in a low success rate of the execution of a workflow.

[0029] To this end, in an embodiment of the present disclosure, a method for displaying a workflow is provided. First, a profile graph related to the workflow is established, and the profile graph includes a plurality of profile nodes, each of which corresponds to a functional requirement in the workflow and contains description information of the functional requirement. Then, an execution graph generated by a target model based on the profile graph is obtained and displayed, and a plurality of profile nodes in the execution graph are replaced by a plurality of execution nodes for implementing the functional requirement. In this way, the accuracy of a user expressing a workflow can be improved based on the description information of the functional requirement by the profile nodes and the logical relationship between the profile nodes in the profile graph, so that the target model can more accurately understand the user's intention based on the profile graph, thereby improving the accuracy of the workflow and the success rate of executing the workflow.

[0030] FIG. 1 illustrates a schematic diagram of an example environment 100 in which some embodiments of the present disclosure can be implemented. Referring to FIG. 1, the environment 100 includes a client 102 and a server 104. In some embodiments, the client 102 includes, but is not limited to, a user terminal, a mobile device, a computer, etc., and the server 104 includes, but is not limited to, a computing system, a single server, a distributed server, or a cloud-based server, etc. The client 102 and the server 104 are connected through a network for data transmission.

[0031] In some embodiments, a user can establish an outline diagram 106 (may be referred to as a first flowchart) of a workflow in the client 102. The outline diagram 106 includes a plurality of outline nodes (may be referred to as a plurality of first components), such as an outline node 106A, an outline node 106B, …, an outline node 106N. Here, N is an integer greater than 1. Each of the outline nodes includes corresponding description information for describing a functional requirement corresponding to the outline node, such as description information 106a, description information 106b, …, description information 106n, n is an integer greater than 1. It should be understood that each of the outline nodes contains its position information in the outline diagram 106 and the description information of the functional requirement, so that the user’s expression of the workflow can be split into a plurality of outline nodes.

[0032] In some embodiments, after the user establishes the outline diagram 106, the client 102 can send the outline diagram 106 to the server 104. After receiving the outline diagram 106, the server 104 invokes a language model 110 (may be referred to as a target model) to process the outline diagram 106, so as to select a corresponding execution node (may be referred to as a second component) for implementing a corresponding functional requirement according to the outline node in the outline diagram 106 and the description information of the outline node. Then, an execution diagram 108 (may be referred to as a second flowchart) of the workflow is generated according to the execution nodes and the logical relationship between the execution nodes (which is the same as the logical relationship between the outline nodes), and the execution diagram 108 is returned to the client 102. The client 102 can display the execution diagram 108 in the screen, including an execution node 108A, an execution node 108B, …, an execution node 108N.

[0033] It should be understood that the environment 100 of the present disclosure is only one example, i.e., the language model 110 is deployed in the server 104. Alternatively or additionally, the language model 110 can also be deployed locally, i.e., in the client 102, so that the client 102 can directly invoke the language model 110 to generate the execution diagram 108 of the workflow. In some embodiments, the language model 110 may, for example, be a large language model, which can be trained on large-scale text data through deep learning.

[0034] In embodiments of the present disclosure, first, the client 102 establishes a profile graph 106 related to the workflow, the profile graph 106 including a plurality of profile nodes, each of which corresponds to one of the functional requirements in the workflow and contains description information of the functional requirement. Then, the client 102 acquires and displays an execution graph 108 generated by the language model 110 of the server 104 based on the profile graph 106, in which the plurality of profile nodes are replaced by a plurality of execution nodes implementing the functional requirements. In this way, the accuracy of the user expressing the workflow can be improved based on the description information of the functional requirements by the profile nodes in the profile graph 106 and the logical relationship between the profile nodes, so that the language model 110 can more accurately understand the user's intention based on the profile graph, thereby improving the accuracy of the workflow and the success rate of executing the workflow.

[0035] It should be understood that the architecture and functions in the example environment 100 are described for illustrative purposes only, without implying any limitation on the scope of the present disclosure. Embodiments of the present disclosure can also be applied to other environments with different structures and / or functions.

[0036] The processes according to embodiments of the present disclosure will be described in detail below with reference to FIGS. 2-6. For ease of understanding, the specific data mentioned in the following description are all exemplary and do not serve to limit the protection scope of the present disclosure. It should be understood that the embodiments described below can also include additional actions not shown or can omit the actions shown, and the scope of the present disclosure is not limited in this respect.

[0037] FIG. 2 shows a flowchart of a method 200 for displaying a workflow according to some embodiments of the present disclosure. In some embodiments, the method 200 can be performed by the client 102 in the example environment 100 shown in FIG. 1. In some embodiments, the client 102 includes, but is not limited to, a user terminal, a mobile device, a computer, etc. It should be understood that although the following is described with the client 102 as the execution subject, the method 200 can also be performed by other devices. The method 200 can also include additional actions not shown or can omit the actions shown, and the scope of the present disclosure is not limited in this respect.

[0038] At block 202, a first flowchart related to the workflow is obtained. The first flowchart includes a plurality of first components corresponding to a plurality of requirements of the workflow, and each of the first components includes description information of a corresponding requirement. In some embodiments, a user can establish an outline diagram 106 (may be referred to as the first flowchart) of the workflow in the client 102. The outline diagram 106 includes a plurality of outline nodes (may be referred to as a plurality of first components). Each of the outline nodes includes corresponding description information for describing a functional requirement corresponding to the outline node. After the user establishes the outline diagram 106, the client 102 can obtain the outline diagram 106. It should be understood that each of the outline nodes includes position information of the outline node in the outline diagram 106 and description information of the functional requirement, so that the expression of the user for the workflow can be split into a plurality of outline nodes.

[0039] At block 204, a second flowchart related to the workflow is displayed. The second flowchart is generated by a target model based on the first flowchart, and the second flowchart includes a plurality of second components corresponding to the plurality of first components, and the second components are used to implement the requirements corresponding to the first components. In some embodiments, after the user establishes the outline diagram 106, the client 102 displays an execution diagram 108 (may be referred to as the second flowchart) corresponding to the outline diagram 106. The execution diagram 108 is generated by a language model 110 (may be referred to as the target model) based on the outline diagram 106, for example, the language model 110 can be called by the server 104 to generate the execution diagram 108 of the workflow. The execution nodes in the execution diagram 108 are selected based on the outline nodes in the outline diagram 106, so as to implement the corresponding functional requirements.

[0040] In embodiments of the present disclosure, an outline diagram related to the workflow is first established, and the outline diagram includes a plurality of outline nodes, each of which corresponds to one of the functional requirements in the workflow and includes description information of the functional requirement. Then, an execution diagram generated by a language model based on the outline diagram is obtained and displayed, and a plurality of execution nodes implementing the functional requirements are replaced in the execution diagram. In this way, the accuracy of the user expressing the workflow can be improved based on the description information of the functional requirements in the outline nodes and the logical relationship between the outline nodes in the outline diagram, so that the language model can more accurately understand the user's intention based on the outline diagram, thereby improving the accuracy of the workflow and the success rate of executing the workflow.

[0041] FIG. 3A, FIG. 3C, and FIG. 3D respectively show a schematic diagram of a page 300A, a page 300C, and a page 300D for establishing a contour graph according to some embodiments of the present disclosure, and FIG. 3B shows a schematic diagram of a page 300B for node selection according to some embodiments of the present disclosure. In some embodiments, the page 300A, the page 300B, the page 300C, and the page 300D are all pages of the client 102, and the page 300A, the page 300B, the page 300C, and the page 300D show the process of establishing a contour node by a user. In the page 300A, the contour graph 106 includes a start node 302, a contour node 306, and an end node 310. Among them, the start node 302 and the end node 310 are used to achieve the functional requirements of the start and end of the workflow, i.e., both are execution nodes; the contour node 306 includes description information 1. The contour graph 106 also includes an add node control 304 and an add node control 308.

[0042] In some embodiments, when the user clicks the add node control 308, the client 102 switches from the page 300A to the page 300B (or displays the page 300A and the page 300B at the same time), so as to show the user a node list 316 (which can be referred to as a component set), for example, including a class 1 node 3161, a class 2 node 3162, a class 3 node 3163, a class 4 node 3164, a class 5 node 3165, and a class 6 node 3166. When the user selects the class 3 node 3163 (corresponding to the contour node) in the node list 316, it can be determined that the user selects a contour node (which can be referred to as a user-selected first component), and then the client 102 switches to the page 300C.

[0043] In the page 300C, the contour node 312 is added at the position where the control 308 is located. The contour node 312 contains an information prompt box “Please enter the description information”, so as to guide the user to input the description information here. The user can input text content (which can be referred to as first content) in the information prompt box, and the client 102 determines the text content input by the user as the description information of the functional requirement of the contour node 312. When the user finishes inputting, the client 102 switches to the page 300D, and at this time, the contour node 312 can display the corresponding description information 2. The above is the process of establishing one of the contour nodes in the contour graph 106 by the user, i.e., the contour node 312. When the user establishes multiple contour nodes as needed, the final contour graph 106 can be formed.

[0044] In this way, the user can split the functional requirements of the workflow into multiple functional requirements, and establish a profile node in the profile graph 106 based on each work requirement, thereby refining the expression granularity of the functional requirements and improving the accuracy of the expression. Moreover, the interaction process for establishing the profile graph 106 in the present embodiment is simple and convenient, and the user can directly select the required profile node and input the description information, thereby improving the efficiency of establishing the profile graph 106.

[0045] In some embodiments, with reference to FIG. 3C, when the user inputs the text content in the profile node 312, the client 102 can send the text content input by the user to the server 104, and the server 104 can call the language model 110 to process the text content, thereby generating the description information 2 corresponding to the profile node 312. Then, the server 104 sends the description information 2 to the client 102, and the client 102 displays the description information 2 in the profile node 312 after receiving the description information 2. In this way, the text content input by the user can be preprocessed by the language model 110 before the execution graph 108 is generated, thereby understanding the intention of the user to generate the description information, improving the accuracy of the description information, and further improving the accuracy of the subsequent generation of the execution graph 108.

[0046] The above introduces the process of establishing profile nodes one by one to form the final profile graph 106, and the following will introduce a way of directly generating the profile graph 106 (such as directly generating the profile graph in the page 300D). In some embodiments, the client 102 can obtain the text content (which can be referred to as second content) described by the user for the overall functional requirements of the workflow, and determine the text content as the global description information corresponding to the overall functional requirements of the workflow. Then, the client 102 can send the description information to the server 104, and the server 104 receives the global description information, calls the language model 110 to process the global description information, thereby obtaining multiple profile nodes and corresponding multiple description information. Then, the server 104 generates the profile graph 106 based on the multiple profile nodes and the corresponding multiple description information, and returns the profile graph 106 to the client 102. The client 102 displays the profile graph 106 to the user in the screen after receiving the profile graph 106.

[0047] In some embodiments, during the process in which the server 104 invokes the language model 110 to generate the profile graph 106, the global description information can be first disassembled to determine a plurality of functional requirements under the overall functional requirement, and a corresponding profile node and corresponding description information are generated according to each functional requirement. Then, the server 104 generates the profile graph 106 according to the plurality of profile nodes and the corresponding plurality of description information. In this way, the language model 110 can first understand the global description information input by the user to disassemble a plurality of profile nodes and corresponding description information, without the user establishing profile nodes one by one, thereby improving the establishment efficiency of the profile graph 106 without affecting the accuracy of the description information.

[0048] FIG. 3E shows a schematic diagram of adjusting the page 300E of the profile graph, according to some embodiments of the present disclosure. Referring to FIG. 3D, in some embodiments, when the user moves the profile node 312, the client 102 can first determine the position to which the user wants to move the profile node 312 (for example, between the start node 302 and the profile node 306). Then, the client 102 adjusts the profile node 312 between the start node 302 and the profile node 306 to obtain the displayed page 300E. In this way, the user can conveniently adjust the profile graph 106, thereby improving the efficiency and convenience of establishing the profile graph 106.

[0049] In some embodiments, after establishing the profile graph 106, the client 102 can send the profile graph 106 to the server 104. After receiving the profile graph 106, the server 104 invokes the language model 110 to process the profile graph 106 to generate an execution graph 108 (which can be a second flowchart) of the workflow, and returns the execution graph 108 to the client 102. Among them, the plurality of execution nodes in the execution graph 108 respectively correspond to the plurality of profile nodes in the profile graph 106, for realizing the corresponding plurality of functional requirements. After receiving the execution graph 108, the client 102 can display the execution graph 108 in the screen.

[0050] FIG. 3F shows a schematic diagram of a page 300F of an execution graph in accordance with some embodiments of the present disclosure. In some embodiments, in the process of generating the execution graph 108 by the server 104, the corresponding execution nodes 318 and 320 can be selected according to the profile nodes 306 and the corresponding description information 1, and the profile nodes 312 and the corresponding description information 2 in the profile graph 106, for example, according to the similarity information between the description information and the execution nodes. Then, the server 104 generates the execution graph 108 according to the execution nodes 318, 320 and the logical relationship between the execution nodes (which is the same as the logical relationship between the profile nodes), as shown in the page 300F. For example, the server 104 can replace the profile nodes 306 and 312 in the profile graph 106 with the corresponding execution nodes 318 and 320, respectively, to generate the execution graph 108. In this way, the server 104 can quickly select the execution nodes based on the language model 110, thereby improving the efficiency of generating the execution graph 108.

[0051] In some embodiments, the execution nodes (which can be referred to as the third component) can also be included in the profile graph 106, such as the start node 302 and the end node 310 in the page 300E. The execution nodes of the profile graph 106 can be used to implement the functional requirements of the workflow, and thus the execution nodes and their positions can be retained in the execution graph 108 in the process of generating the execution graph 108 based on the profile graph 106.

[0052] In some embodiments, the user can select the execution nodes (i.e., the third component) according to the options in the node list 316 in the process of establishing the profile graph 106, and the client 102 determines the corresponding execution nodes after receiving the user's selection. At this time, the profile graph 106 displayed simultaneously includes the execution nodes (such as the start node 302 and the end node 310) and the profile nodes (such as the profile node 306). In the process of generating the execution graph 108 by the server 104 by calling the language model 110, the profile nodes are replaced with new execution nodes (such as the profile node 306 replaced with the execution node 318), i.e., the profile nodes and the new execution nodes are in the same position, and the new execution nodes and the original execution nodes together constitute the execution graph 108. In this way, flexibility can be improved in the process of establishing the profile graph 106, thereby improving the efficiency of generating the execution graph 108.

[0053] In some embodiments, the execution nodes further include configuration information, such as configuration information 1 and configuration information 2 in page 300F, which are parameters for the execution nodes to implement the corresponding functional requirements. In the process of calling the language model 110 to generate the execution nodes by the server 104, the server 104 can determine the configuration information required by the corresponding execution nodes according to the description information of the outline nodes, and generate the execution graph 108 according to the logical information of the outline graph 106, the selected multiple execution nodes and the corresponding multiple configuration information, and send it to the client 102. After the client 102 receives the execution graph 108 containing the configuration information, it can display the configuration information in the corresponding execution nodes in the execution graph 108, such as configuration information 1 in execution node 318 and configuration information 2 in execution node 320 in page 300F. In this way, the execution components can be quickly configured by the language model 110, thereby improving the accuracy of the workflow.

[0054] The above embodiments elaborate the details of the scheme in the present disclosure. For the convenience of further understanding the overall scheme, a more specific embodiment is provided below. In some embodiments, first, the user establishes the outline graph 106 in the client 102, and constructs the outline graph 106 by selecting and moving the outline nodes and execution nodes. It should be understood that only outline nodes can be used in the outline graph 106, or both outline nodes and execution nodes can be used. Then, the user can fill in the description information in the description of the outline node, so as to express the functional requirements of the outline node, such as "calling a search engine", "translating the text output by the upstream node into English", and "extracting the summary and link information in the search engine return result".

[0055] Further, the user sends the outline graph 106 with the outline nodes and the description information to the background server 104 through the client 102, and the server 104 calls the large language model to select the work, i.e. selects the execution node suitable for completing the corresponding functional requirement according to the description information of the outline node. For example, the description information is "calling a search engine", and the server 104 can select a search engine (as an execution node) to replace the current outline node. After completing the replacement of the outline node, the server 104 continues to call the large language model to complete the configuration of the execution node according to the configuration requirements of the functional requirements. For example, for the search engine node, the "query input" parameter can be referenced, for the code node, the code writing parameter can be configured, and for the large language model node, the prompt word can be configured.

[0056] To facilitate further understanding of the outline graph and the execution graph, more specific embodiments about the outline graph and the execution graph are provided below. FIG. 4A and FIG. 4B respectively show a schematic diagram of an outline graph 400A and an execution graph 400B of a workflow of some embodiments of the present disclosure. In some embodiments, the outline graph 400A includes 6 outline nodes, namely, an outline node 404A, an outline node 406A, an outline node 410A, an outline node 412A, an outline node 414A, and an outline node 416A, each of which contains corresponding description information (shown in the text input box) for representing the functional requirement of the outline node.

[0057] The outline graph 400A also includes 3 execution nodes, namely, a start node 402A, a loop node 408A, and an end node 418A. The start node 402A is used to start the workflow, including an “ask” control (for searching the content in the text input box), a text input box (a default value can be displayed when the user does not input text), and a “+ add” control (for adding an asking item). The loop node 408A includes an “initialize” item (the parameters of the initialization can be added by clicking the “+ add” control), a “condition” item (i.e., the loop condition), and a “step” item (i.e., the steps in the loop body). The end node 418A is used to end the workflow, and the “+ add” control can be clicked to add the final result.

[0058] When the outline graph 400A is processed by the language model 110, the execution graph 400B generated by the language model 110 includes 6 execution nodes, namely, an extract asking node 404B, an array node 406B, a search node 410B, an extract search result node 412B, an update loop output node 414B, and a generate report node 416B, which replace the outline node 404A, the outline node 406A, the outline node 410A, the outline node 412A, the outline node 414A, and the outline node 416A, respectively. The newly generated 6 execution nodes and the start node 402B, the loop node 408B, and the end node 418B together form the execution graph 400B of the workflow.

[0059] The configuration information in the execution nodes in the execution graph 400B can be configured by the language model 110. Specifically, the server 104 can invoke the language model 110 to configure the parameters according to the functional requirements of the execution nodes. For example, in the extraction query node 404B, a large language model needs to be invoked, and the language model 110 can configure the model type of the extraction query node 404B as “XXX4.2”, so that the XXX4.2 large language model can be invoked when the workflow executes the extraction query node 404B. In the loop node 408B, for example, the language model 110 can define “index = 0” as the initial parameter of the loop body. The configuration parameters can refer to more specific parameters in FIG. 4B, which will not be described one by one in this embodiment.

[0060] FIG. 5 shows a block diagram of an apparatus 500 for displaying a workflow according to some embodiments of the present disclosure. The apparatus 500 includes a first flowchart obtaining module 502 configured to obtain a first flowchart related to a workflow, the first flowchart including a plurality of first components corresponding to a plurality of requirements of the workflow, the first component including description information of the corresponding requirement. The apparatus 500 further includes a second flowchart displaying module 504 configured to display a second flowchart related to the workflow, the second flowchart being generated by a target model based on the first flowchart, and the second flowchart including a plurality of second components corresponding to the plurality of first components, the second component being used to implement the requirement corresponding to the first component.

[0061] In some embodiments, the apparatus 500 further includes a first component determining module configured to determine the first component selected by the user in response to detecting a selection operation of the user on the component set; a description information determining module configured to determine the description information of the requirement corresponding to the first component based on the first content related to the first component input by the user; and a first flowchart displaying module configured to display the first flowchart based on the plurality of first components and the corresponding plurality of description information.

[0062] In some embodiments, the description information determining module is further configured to: send the first content to the server to enable the server to invoke the target model to determine the description information of the requirement corresponding to the first component; and receive the description information of the requirement corresponding to the first component from the server.

[0063] In some embodiments, the apparatus 500 further includes: a global description information determining module configured to determine global description information of the plurality of requirements of the workflow based on the second content related to the workflow input by the user; a first flowchart obtaining module configured to obtain a first flowchart related to the global description information, the first flowchart being generated by the server invoking the target model, and a plurality of first components and a plurality of corresponding description information in the first flowchart being related to the global description information; and a first flowchart displaying module configured to display the first flowchart.

[0064] In some embodiments, the first flowchart displaying module is further configured to: in response to detecting a moving operation of the user on the first component, determine a position pointed by the moving operation; update the first flowchart, the first component being located at the position pointed by the moving operation in the updated first flowchart; and display the updated first flowchart.

[0065] In some embodiments, the second flowchart displaying module 504 is further configured to: send the first flowchart to the server to make the server invoke the target model to generate the second flowchart based on the first flowchart; receive the second flowchart from the server; and display the second flowchart.

[0066] In some embodiments, wherein the second component further includes configuration information for implementing the requirement, and the second flowchart displaying module 504 is further configured to: receive a plurality of configuration information of the plurality of second components from the server, the configuration information being generated by the server invoking the target model based on the description information; and display the plurality of corresponding configuration information in the plurality of second components of the second flowchart.

[0067] In some embodiments, wherein the first flowchart further includes a third component for implementing the requirement in the workflow, the apparatus 500 further includes: a third component determining module configured to determine the third component selected by the user in response to detecting a selection operation of the user on the component set; and a third component displaying module configured to display the third component in the first flowchart; and the second flowchart displaying module 504 is further configured to: display the third component in the second flowchart, the third component being located at the same position in the first flowchart as in the second flowchart.

[0068] It can be understood that the device 500 of the present disclosure can achieve at least one of the many advantages that the method or process as described above can achieve. For example, the device 500 establishes a profile diagram related to the workflow, which includes a plurality of profile nodes, each of which corresponds to one of the functional requirements in the workflow and contains description information of the functional requirement. Then, an execution diagram generated by the target model based on the profile diagram is obtained and displayed, in which a plurality of profile nodes are replaced by a plurality of execution nodes that implement the functional requirements. In this way, the accuracy of the user expressing the workflow can be improved based on the description information of the functional requirements in the profile nodes and the logical relationship between the profile nodes, so that the target model can more accurately understand the user's intention based on the profile diagram, thereby improving the accuracy of the workflow and the success rate of executing the workflow.

[0069] The present disclosure also provides another device for displaying a workflow. The device includes a first flowchart receiving module configured to receive a first flowchart related to a workflow from a client, the first flowchart including a plurality of first components corresponding to a plurality of requirements of the workflow, the first component including description information of the corresponding requirement. The device also includes a second flowchart generating module configured to generate, by a target model, a second flowchart related to the workflow based on the first flowchart, the second flowchart including a plurality of second components corresponding to the plurality of first components, the second component being used to implement the requirement corresponding to the first component. In addition, the device also includes a second flowchart sending module configured to send the second flowchart to the client to enable the client to display the second flowchart.

[0070] In some embodiments, the second flowchart generating module is further configured to: select, by the target model, the second component based on the description information in the first component; and generate the second flowchart based on the first flowchart and the selected plurality of second components.

[0071] In some embodiments, the second component further includes configuration information for implementing the requirement, and the second flowchart generating module is further configured to: determine, by the target model, the configuration information of the second component based on the description information of the first component; and generate the second flowchart based on the first flowchart, the plurality of second components and the corresponding plurality of configuration information.

[0072] In some embodiments, the device further includes a global description information receiving module configured to receive global description information of the plurality of requirements of the workflow from the client; a first component and description information generating module configured to generate, by the target model, the plurality of first components and the corresponding plurality of description information based on the global description information; a first flowchart generating module configured to generate the first flowchart based on the plurality of first components and the corresponding plurality of description information; and a first flowchart sending module configured to send the first flowchart to the client to enable the client to display the first flowchart.

[0073] FIG. 6 illustrates a schematic block diagram of an electronic device 600 according to some embodiments of the present disclosure. The electronic device 600 can be, for example, a processing unit of the client 102 or the server 104 as shown in FIG. 1. As shown in FIG. 6, the electronic device 600 includes a central processing unit (CPU) and / or a graphics processing unit (GPU) 601, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 602 or loaded into a random access memory (RAM) 603 from a storage unit 608. Various programs and data required by the electronic device 600 to operate can also be stored in the RAM 603. The CPU / GPU 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. Although not shown in FIG. 6, the electronic device 600 can also include a coprocessor.

[0074] Various components in the electronic device 600 are connected to the I / O interface 605, including an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, a speaker, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the electronic device 600 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0075] The various methods or processes described above can be performed by the CPU / GPU 601. For example, in some embodiments, the methods can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the CPU / GPU 601, one or more steps or actions in the methods or processes described above can be performed.

[0076] In some embodiments, the methods and processes described above can be implemented as a computer program product. The computer program product can include a computer readable storage medium having computer readable program instructions embodied therewith.

[0077] A computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: 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), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0078] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0079] Computer readable program instructions for carrying out operations of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including object oriented programming languages and conventional procedural programming languages. The computer readable program instructions 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). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate array (FPGA), or programmable logic array (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0080] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium that can be a computer readable storage medium having no data, programs, program modules, and / or computer program

[0081] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0082] The computer program product of the second aspect can include a computer readable storage medium. The computer readable storage medium can include instructions. The instructions can include one or both of: instructions for causing a computer to enable a user equipment device to receive a configuration message from a base station, the configuration message comprising an indication of a set of one or more parameters for a first type of hybrid automatic repeat request process, the first type of hybrid automatic repeat request process being associated with a first type of data; and instructions for causing a computer to enable a user equipment device to receive a configuration message from a base station, the configuration message comprising an indication of a set of one or more parameters for a first type of hybrid automatic repeat request process, the first type of hybrid automatic repeat request process being associated with a first type of data.

[0083] Embodiments of the present disclosure have been described above, with the understanding that these embodiments are exemplary only, and are not restrictive, and are not limited to the disclosed embodiments. Many modifications and changes to the described embodiments are possible, without departing from the scope and spirit of the described embodiments. The selection of terms to be used herein is intended to best explain the principles of the embodiments, practical application, or technical improvement over the technology in the market, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1. A method for displaying a workflow, comprising: obtaining a first flowchart associated with the workflow, the first flowchart comprising a plurality of first components corresponding to a plurality of requirements of the workflow, a first component comprising description information of a corresponding requirement; and displaying a second flowchart associated with the workflow, the second flowchart being generated by a target model based on the first flowchart, and the second flowchart comprising a plurality of second components corresponding to the plurality of first components, a second component being used to implement the requirement corresponding to the first component. 2.The method of claim 1, further comprising: in response to detecting a selection operation of a user on a component set, determining the first component selected by the user; based on first content input by the user in relation to the first component, determining the description information of the requirement corresponding to the first component; and based on the plurality of first components and the corresponding plurality of description information, displaying the first flowchart. 3.The method of claim 2, wherein based on the first content input by the user in relation to the first component, determining the description information of the requirement corresponding to the first component comprises: sending the first content to a server, so that the server invokes the target model to determine the description information of the requirement corresponding to the first component; and receiving the description information of the requirement corresponding to the first component from the server. 4.The method of claim 1, further comprising: based on second content input by a user in relation to the workflow, determining global description information of the plurality of requirements of the workflow; obtaining the first flowchart associated with the global description information, the first flowchart being generated by a server invoking the target model, and the plurality of first components and the corresponding plurality of description information in the first flowchart being related to the global description information; and displaying the first flowchart. 5.The method of any one of claims 2 to 4, wherein displaying the first flowchart comprises: in response to detecting a movement operation of a user on the first component, determining a position pointed to by the movement operation; updating the first flowchart, the first component being located at the position pointed to by the movement operation in the updated first flowchart; and displaying the updated first flowchart. 6.The method of claim 1, wherein displaying the second flowchart associated with the workflow comprises: sending the first flowchart to a server, so that the server invokes the target model to generate the second flowchart based on the first flowchart; receiving the second flowchart from the server; and displaying the second flowchart. 7.The method of claim 6, wherein the second component further comprises configuration information used to implement the requirement, and displaying the second flowchart further comprises: receiving a plurality of configuration information of the plurality of second components from the server, the configuration information being generated by the server invoking the target model based on the description information; and ​ ​ ​ ​ ​ displaying corresponding configuration information in the second components in the second flowchart. 8.The method of claim 1, wherein the first flowchart further comprises a third component for implementing a requirement in the workflow, and the method further comprises: in response to detecting a selection operation of a user on the component set, determining the third component selected by the user; displaying the third component in the first flowchart; and displaying a second flowchart related to the workflow comprises: displaying the third component in the second flowchart, the third component having a same position in the first flowchart as in the second flowchart. 9.A method for displaying a workflow, comprising: receiving a first flowchart related to the workflow from a client, the first flowchart comprising a plurality of first components corresponding to a plurality of requirements of the workflow, a first component comprising description information of a corresponding requirement; generating a second flowchart related to the workflow based on the first flowchart by a target model, the second flowchart comprising a plurality of second components corresponding to the plurality of first components, a second component for implementing the requirement corresponding to the first component; and sending the second flowchart to the client to make the client display the second flowchart. 10.The method of claim 9, wherein the generating a second flowchart related to the workflow based on the first flowchart by a target model comprises: selecting the second components based on the description information in the first components by the target model; and generating the second flowchart based on the first flowchart and the selected plurality of second components. 11.The method of claim 10, wherein the second component further comprises configuration information for implementing the requirement, and the generating the second flowchart based on the first flowchart and the selected plurality of second components comprises: determining the configuration information of the second component based on the description information of the first component by the target model; and generating the second flowchart based on the first flowchart, the plurality of second components and corresponding plurality of configuration information. 12.The method of claim 9, further comprising: receiving global description information of the plurality of requirements of the workflow from the client; generating the plurality of first components and corresponding plurality of description information based on the global description information by the target model; generating the first flowchart based on the plurality of first components and corresponding plurality of description information; and sending the first flowchart to the client to make the client display the first flowchart. 13.An apparatus for displaying a workflow, comprising: a first flowchart obtaining module configured to obtain a first flowchart related to the workflow, the first flowchart comprising a plurality of first components corresponding to a plurality of requirements of the workflow, a first component comprising description information of a corresponding requirement; and a second flowchart generating module configured to generate a second flowchart related to the workflow based on the first flowchart by a target model, the second flowchart comprising a plurality of second components corresponding to the plurality of first components, a second component for implementing the requirement corresponding to the first component. ​ ​ ​ The second flowchart display module is configured to display a second flowchart related to the workflow, the second flowchart being generated by a target model based on the first flowchart, and the second flowchart including a plurality of second components corresponding to the plurality of first components, the second components being used to implement the requirements corresponding to the first components.

14. An apparatus for displaying a workflow, comprising: a first flowchart receiving module configured to receive a first flowchart related to the workflow from a client, the first flowchart including a plurality of first components corresponding to a plurality of requirements of the workflow, the first components including description information of the corresponding requirements; a second flowchart generating module configured to generate a second flowchart related to the workflow by a target model based on the first flowchart, the second flowchart including a plurality of second components corresponding to the plurality of first components, the second components being used to implement the requirements corresponding to the first components; and a second flowchart sending module configured to send the second flowchart to the client to enable the client to display the second flowchart.

15. An electronic device, comprising: a processor; and a memory coupled with the processor, the memory having stored therein instructions which, when executed by the processor, cause the electronic device to perform the method according to any one of claims 1-8 or claims 9-12.

16. A computer program product tangibly stored in a non-transitory computer readable medium and comprising machine executable instructions that, when executed, cause a machine to perform the method according to any one of claims 1-8 or claims 9-12.

17. A computer program product tangibly stored in a non-transitory computer readable medium and comprising machine executable instructions that, when executed, cause a machine to perform the method according to any one of claims 1-8 or claims 9-12.

Images