Task process optimization method and device, equipment, medium and product

Abstract

The invention provides a task process optimization method and device, equipment, a medium and a product, and the method can be applied to a process engine, such as a process engine in a low-code platform. The method comprises the steps of presenting a first task flow in a flow configuration page; in response to an optimization operation for the first task process, generating a second task process; wherein the second task process and the first task process are used for executing the same business task, and the second task process and the first task process have at least one of the following differences: the number of process nodes, the type of the process nodes and the structural relationship between the process nodes. According to the method, the natural language processing capacity of the language model is utilized, the overall structure of the task process is automatically optimized, and the overall performance and maintainability of the task process are improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a method, apparatus, electronic device, computer-readable storage medium, and computer program product for optimizing task processes. Background Art

[0002] With the continuous development of computer technology, process engines have emerged. A process engine generally refers to a system used to define, execute, and manage task processes (also known as workflows). For example, a process engine can be deployed in a low-code platform and provided as a functional module in the low-code platform to offer services related to task processes. Users can arrange process nodes and the execution order between process nodes in the process engine. In this way, the process engine can process process nodes in sequence according to the execution order of the process nodes and advance the task process.

[0003] However, with the increase in the structural complexity of task processes, there are often process nodes in a task process that may become performance bottlenecks, or the maintainability of the task process is poor due to redundant process nodes or other situations. How to optimize the overall structure of the task process has become an urgent problem to be solved. Summary of the Invention

[0004] This application provides a method for optimizing task processes. This method reduces the workload of manual operations by users and realizes automatic optimization of the overall structure of task processes. This application also provides a corresponding apparatus, electronic device, computer-readable storage medium, and computer program product for the above method.

[0005] In a first aspect, this application provides a method for optimizing task processes, which is applied to a process engine. The method includes:

[0006] Present a first task process on a process configuration page;

[0007] In response to an optimization operation on the first task process, generate a second task process; wherein, the second task process and the first task process are used to execute the same business task, and there is at least one of the following differences between the second task process and the first task process: the number of process nodes, the type of process nodes, and the structural relationship between process nodes;

[0008] The second task process is generated through the following steps:

[0009] Generate a first prompt word; wherein, the first prompt word includes: the first task process described in a domain-specific language and prompt information for indicating optimization of the first task process from at least one dimension;

[0010] Send the first prompt word to the first language model, and receive the second task process described in the domain-specific language returned by the first language model;

[0011] Generate the second task process according to the second task process described in the domain-specific language.

[0012] In a second aspect, the present application provides a task process optimization device deployed in a process engine. The device includes:

[0013] A presentation module for presenting a first task process on a process configuration page;

[0014] A generation module for presenting a second task process in response to an optimization operation on the first task process; wherein, the second task process and the first task process are used to perform the same business task, and there is at least one of the following differences between the second task process and the first task process: the number of process nodes, the type of process nodes, and the structural relationship between process nodes;

[0015] The generation module is specifically configured to generate a first prompt word; wherein, the first prompt word includes: the first task process described in the domain-specific language and prompt information for indicating to optimize the first task process from at least one dimension; send the first prompt word to the first language model, and receive the second task process described in the domain-specific language returned by the first language model; generate the second task process according to the second task process described in the domain-specific language.

[0016] In a third aspect, the present application provides an electronic device, which includes a processor and a memory. The processor and the memory communicate with each other. The processor is configured to execute instructions stored in the memory so that the electronic device executes the task process optimization method as described in the first aspect or any implementation manner of the first aspect.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions are stored, and the instructions instruct an electronic device to execute the task process optimization method as described in the first aspect or any implementation manner of the first aspect.

[0018] In a fifth aspect, the present application provides a computer program product containing instructions, which, when running on an electronic device, causes the electronic device to execute the task process optimization method as described in the first aspect or any implementation manner of the first aspect.

[0019] Based on the implementation manners provided in the above aspects, the present application can be further combined to provide more implementation manners.

[0020] As can be seen from the above technical solutions, the present application has the following advantages:

[0021] The present application provides a method for optimizing a task process. This method is applied to a process engine. In a process configuration page, a first task process is presented. In response to an optimization operation on the first task process, a second task process is generated. Among them, the second task process and the first task process are used to execute the same business task, and there is at least one of the following differences between the second task process and the first task process: the number of process nodes, the type of process nodes, and the structural relationship between process nodes. The second task process is generated through the following steps: generating a first prompt word; where the first prompt word includes: the first task process described in a domain-specific language and prompt information for indicating optimization of the first task process from at least one dimension, sending the first prompt word to a first language model, receiving the second task process described in the domain-specific language returned by the first language model, and generating the second task process according to the second task process described in the domain-specific language.

[0022] In this method, in a process engine, such as the process engine in a low-code platform, for the user's optimization requirements for the original task process, the natural language processing ability of the language model is utilized to analyze and optimize the original task process, and the optimized task process is reconstructed, so that the optimized task process and the original task process can execute the same business task, but there are differences in the number, type, and structural relationship of process nodes, realizing the automatic optimization of the overall structure of the task process and improving the overall performance and maintainability of the task process. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical method of the embodiments of the present application, the drawings required for the embodiments will be briefly introduced below.

[0024] Figure 1 It is a flowchart of a method for optimizing a task process provided by an embodiment of the present application;

[0025] Figure 2A and Figure 2B It is a schematic diagram of a task process provided by an embodiment of the present application;

[0026] Figure 3A and Figure 3B It is a schematic diagram of a task process provided by an embodiment of the present application;

[0027] Figure 4A and Figure 4B It is a schematic diagram of a task process provided by an embodiment of the present application;

[0028] Figures 5A to 5D It is a schematic diagram of a process configuration page provided by an embodiment of the present application;

[0029] Figure 6 A structural schematic diagram of a task process optimization device provided by an embodiment of the present application;

[0030] Figure 7 A structural schematic diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0031] The terms "first" and "second" in the embodiments of the present application are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0032] First, some technical terms and application scenarios involved in the embodiments of the present application are introduced.

[0033] A process engine, which can also be called a process orchestration engine or a process orchestration tool, is usually used to define, execute, and manage task processes. The process engine usually supports visual operations. Users (such as process orchestration personnel) can drag, connect, etc. on the process orchestration page to orchestrate process nodes and generate task processes.

[0034] The process engine is usually deployed in an application platform as a service (aPaaS) platform and exists as a service component of the aPaaS platform. Among them, the aPaaS platform, which can also be called a low-code platform, is a cloud service platform that simplifies the deployment and management of application programs by providing extensible application infrastructure services. As a part of the aPaaS platform, the process engine enables the aPaaS platform to support complex business process management and automation.

[0035] A task process, which can also be called a workflow or a process template, can be understood as an execution sequence composed of a series of process nodes, and the dependency relationship between process nodes can represent the execution order of process nodes. Among them, a process node can be understood as a module used to execute a specific task, thereby implementing a specific function or providing a specific capability.

[0036] Task processes are usually used to execute business tasks. For example, task processes can be used to execute business tasks such as onboarding approval, store inspections, and product requirement status management. Usually, business tasks with more complex business logics correspond to task processes with higher structural complexities. For example, there may be process nodes that become performance bottlenecks in the task process, or there may be redundant process nodes in the task mileage, resulting in poor execution performance and maintainability of the task process.

[0037] In view of this, the present application provides a method for optimizing a task process. This method is applied to a process engine. In a process configuration page, a first task process is presented. In response to an optimization operation on the first task process, a second task process is generated. Here, the second task process and the first task process are used to execute the same business task, and there is at least one of the following differences between the second task process and the first task process: the number of process nodes, the type of process nodes, and the structural relationship between process nodes. The second task process is generated through the following steps: generating a first prompt; wherein, the first prompt includes: the first task process described in a domain-specific language and prompt information for indicating optimization of the first task process from at least one dimension, sending the first prompt to a first language model, receiving the second task process described in the domain-specific language returned by the first language model, and generating the second task process according to the second task process described in the domain-specific language.

[0038] In this method, in a process engine, such as the process engine in a low-code platform, in response to the user's optimization requirement for the original task process, the natural language processing ability of the language model is utilized to analyze and optimize the original task process, and the optimized task process is reconstructed. The optimized task process and the original task process can execute the same business task, but there are differences in the number, type, and structural relationship of process nodes, achieving automatic optimization of the overall structure of the task process and improving the overall performance and maintainability of the task process.

[0039] To facilitate understanding of the technical solution provided by the embodiments of the present application, the following will be described with reference to the accompanying drawings. Refer to Figure 1 The flowchart of a method for optimizing a task process shown, which is applied to a process engine. The method specifically includes the following steps:

[0040] S101: In the process configuration page, present the first task process.

[0041] The process configuration page, which can also be called the process configuration canvas, can be understood as a page provided by the process engine for configuring the task process. That is to say, the user (such as a process orchestrator) can arrange the process nodes and the execution order between process nodes in the task process in the process configuration page. In addition, the user can also configure node parameters for each process node in the process configuration page.

[0042] In the embodiments of the present application, the first task process can be understood as a task process with an optimization requirement. For example, the first task process can be any task process with a process execution logic.

[0043] Embodiments of the present application support determining a first task process with optimization requirements in different ways. In some embodiments, in response to a selection operation for the first task process on the process configuration page, the first task process is presented. Among them, the selection operation is used to select from the configured task processes.

[0044] That is to say, since the task processes that have been configured are usually stored in the process engine, a user (such as a process orchestrator) can select the task process that needs to be optimized from the configured task processes, and determine the first task process based on the selection operation triggered by the user.

[0045] In other embodiments, in response to a task process configuration operation triggered on the process configuration page, the first task process is presented. Among them, the task process configuration operation is used to configure the first task process.

[0046] That is to say, a user (such as a process orchestrator) can configure the task process on the process configuration page, such as arranging the process nodes and the execution order between the process nodes. Based on the task process configuration operation triggered by the user, the currently configured task process is determined as the first task process.

[0047] In still other embodiments, in response to a task process generation operation triggered on the process configuration page, the first task process is presented. Among them, the task process generation operation is associated with the natural language text used to describe the first task process, and the task process generation operation is used to trigger the first language model to generate the first task process based on the natural language text used to describe the first task process.

[0048] That is to say, a user (such as a process orchestrator) can describe the task process to be configured in the form of inputting natural language text on the process configuration page, such as inputting natural language text describing the business task to be achieved by the task process, etc. Based on the task process generation operation triggered by the user, the first language model is called, and the natural language processing ability of the first language model is used to automatically generate a task process that meets the user's needs, and the task process automatically generated by the first language model is determined as the first task process.

[0049] Among them, the first language model can be understood as a natural language processing model based on deep learning technology. The language model usually has the ability to understand, process, and generate natural language, and can handle different types of natural language tasks.

[0050] The embodiments of the present application do not limit the way for the user to input the natural language text for describing the first task process. For example, the user can directly input the natural language text for describing the first task process in the way of text input. Also, for example, the user can also input the speech for describing the first task process in the way of speech input, and through speech recognition and text conversion, obtain the natural language text for describing the first task process.

[0051] In some possible implementation manners, a digital assistant is deployed in the process engine, and the user inputs the natural language text by interacting with the digital assistant. Among them, the digital assistant can be understood as a module for providing human-computer dialogue services. That is to say, the user inputs the natural language text for describing the first task process through the digital assistant, and the digital assistant calls the first language model to enable the first language model to generate the first task process, realizing the automatic generation of the task process.

[0052] The embodiments of the present application do not limit the presentation manner of presenting the first task process. For example, in the process configuration page, the first task process is presented in the form of a topology diagram. In other words, the process nodes of the first task process form the respective nodes of the topology diagram, and the execution order between the process nodes of the first task process indicates the connection relationship between the respective nodes in the topology diagram.

[0053] S102: Generate a second task process in response to an optimization operation on the first task process.

[0054] Among them, the optimization operation on the first task process can be understood as an operation that triggers the optimization of the overall structure of the first task process. In other words, when the user has an optimization requirement for the first task process, by triggering the optimization operation on the first task process, the process of optimizing the first task process into the second task process is started.

[0055] The embodiments of the present application support the user to trigger the optimization operation on the first task process in different ways. In some embodiments, a second task process is generated in response to a trigger operation on an optimization control. Among them, the optimization control is used to trigger the optimization of the first task process.

[0056] That is to say, the process configuration page provides an optimization control. By the user triggering the optimization control, for example, clicking the optimization control, the process of optimizing the first task process into the second task process is started, realizing fast and convenient task process optimization.

[0057] In some other embodiments, a second task process is generated in response to an interaction operation with the digital assistant. Among them, the interaction operation with the digital assistant is associated with the natural language text for optimizing the first task process.

[0058] That is to say, the process engine deploys a digital assistant. The user inputs natural language text for optimizing the first task process by interacting with the digital assistant. For example, the user inputs "Please help me optimize this task process". In this way, through the dialogue between the user and the digital assistant, the process of optimizing the first task process into the second task process is automatically started.

[0059] In some possible implementation manners, in response to a triggering operation on the digital assistant, a digital assistant interaction interface is presented. In response to receiving natural language text for optimizing the first task process in the digital assistant interaction interface, a second task process is generated on the process configuration page.

[0060] Among them, the digital assistant interaction interface can be understood as an interface for human-computer dialogue. In other words, the user can interact with the digital assistant through the digital assistant interaction interface, and both the user's input text and the generated text of the digital assistant can be presented in the digital assistant interaction interface. The digital assistant interaction interface can have different display forms. For example, the digital assistant interaction interface can be a floating window of the digital assistant.

[0061] The triggering operation on the digital assistant can be understood as an operation for starting the interaction with the digital assistant. For example, the triggering operation on the digital assistant can be an operation for invoking the digital assistant interaction interface. Through the triggering operation on the digital assistant, the digital assistant interaction interface is presented so that the user can interact with the digital assistant.

[0062] The user can send natural language text for optimizing the first task process in the digital assistant interaction interface. Similarly, the embodiments of the present application do not limit the manner in which the user inputs natural language text for optimizing the first task process. For example, the user can directly input natural language text for optimizing the first task process in the digital assistant interaction interface by means of text input. Another example is that the user can also input the voice for optimizing the first task process in the digital assistant interaction interface by means of voice input, and through voice recognition and text conversion, obtain the natural language text for optimizing the first task process.

[0063] Through the digital assistant interaction interface provided by the digital assistant, during the user's use of the process engine, the user can describe the requirements related to the task process in the digital assistant interaction interface by inputting natural language content at any time, and use the digital assistant to assist the user in using the process engine conveniently and quickly.

[0064] In the embodiments of the present application, the second task process can be understood as the task process obtained by optimizing the first task process. The second task process and the first task process are used to execute the same business task, and there is at least one of the following differences between the second task process and the first task process: the number of process nodes, the type of process nodes, and the structural relationship between process nodes.

[0065] Among them, the difference in the number of process nodes can be understood as: the number of process nodes included in the first task process is different from the number of process nodes included in the second task process. For example, the number of process nodes included in the second task process is less than the number of process nodes included in the first task process. The difference in the types of process nodes can be understood as: there are process nodes in the first task process that perform the same function as the process nodes in the second task process, but the ways of performing this function are different. For example, there is a process node A in the first task process and a process node B in the second task process. Both process node A and process node B are used to perform function C, but process node A performs function C through method D, and process node B performs function C through method E. The difference in the structural relationship between process nodes can be understood as: the execution order between process nodes in the first task process is different from the execution order between process nodes in the second task process. For example, in the first task process, process node A is executed first, and then process node B is executed. In the second task process, process node A and process node B are executed in parallel.

[0066] That is to say, in the embodiment of the present application, the optimization of the first task process can be understood as optimizing the overall structure of the first task process. By optimizing the overall structure of the first task process, a second task process is obtained, so that the second task process can perform the same business task as the first task process, that is, the optimization process of the first task process does not affect the business logic originally executed by the first task process. At the same time, the optimization process of the first task process will change the overall structure of the first task process, optimize the process nodes that can be optimized in the first task process, and optimize the original scheduling defects of the first task process by changing the task process structure, thereby improving the execution efficiency and maintainability of the task process.

[0067] In the embodiment of the present application, a first language model is used to analyze the first task process, identify the process nodes that can be optimized in the first task process, and then generate a second task process. The first language model realizes the above analysis, identification, and optimization process of the first task process based on prompt engineering technology. Among them, a prompt can be used to guide the language model to perform a specific output in a generative task (such as a text generation task, a question-and-answer task, a dialogue task). By configuring the prompt, the language model can be helped to understand the background and requirements of the task, so that the language model can handle different types of natural language processing tasks without retraining the language model, increasing the scalability and flexibility of the language model.

[0068] In specific implementation, a first prompt is generated and sent to a first language model, and a second task process described in a domain-specific language (DSL) returned by the first language model is received. Then, a second task process is generated according to the second task process described in DSL.

[0069] Among them, the first prompt includes: a first task process described in DSL and prompt information for indicating optimization of the first task process from at least one dimension. For example, the prompt information for indicating optimization of the first task process from at least one dimension may be prompt information for indicating analysis of the first task process from at least one dimension, identifying process nodes in the first task process that need to be optimized, and optimizing the process nodes in the first task process that need to be optimized.

[0070] DSL is a computer programming language used to solve problems in specific domains. In the embodiments of the present application, by describing the task process in task process DSL, the syntax and semantics are closer to the concepts and requirements of the task process domain.

[0071] In some embodiments, in order to enable the first language model to have the ability to analyze the first task process described in DSL, the first prompt may further include the syntax knowledge of DSL. In this way, based on the prompting ability of the first prompt, the first language model understands the syntax of DSL, and then analyzes the first task process based on the syntax of DSL.

[0072] For example, the syntax knowledge of DSL may be partially as follows:

[0073] "Use DSL in yaml format to describe the workflow. In DSL, the nodes in the workflow are described through the nodes array, and the edge relationships between the nodes are described through the edges array. The id field of the node is used as the identifier of the node, the name field of the node is used as the name of the node, and the type field of the node indicates the type of the node. The definition field of the node contains the following fields: inputs, outputs, info, blocks, code field, language field, condition, data field. In each edge relationship, there must be sourceNodeID and targetNodeID, indicating the starting node and the pointing node of the edge. The definition.inputs parameter of the downstream node can reference the definition.outputs variable of the upstream node, and the reference relationship is defined through the data field"

[0074] The first task process described in DSL may be partially as follows:

[0075] "edges:

[0076] - sourceNodeID: start1

[0077] targetNodeID: llm1

[0078] - sourceNodeID: llm1

[0079] targetNodeID: end1

[0080] nodes:

[0081] - definition:

[0082] info:

[0083] description: Receive the text input by the user

[0084] outputs:

[0085] - name: query

[0086] required: true

[0087] type: string

[0088] id: start1

[0089] name: Start

[0090] type: start

[0091] - data:

[0092] modelType: "123456"

[0093] modleName: Tool call

[0094] prompt: ref(start1.outputs.query)

[0095] systemPrompt: xxxxxx

[0096] definition:

[0097] info:

[0098] description: Generate 5 relevant queries based on the text of the start node

[0099] inputs:

[0100] - description: User prompt for generating content

[0101] name: prompt

[0102] type: string

[0103] - description: System prompt for guiding the generation of content

[0104] name: systemPrompt

[0105] type: string

[0106] - description: Type id of the model used

[0107] name: modelType

[0108] outputs:

[0109] - name: output

[0110] type: string”

[0111] Thus, by configuring the above information in the first prompt, based on the prompting ability of the first prompt, the first language model can intuitively understand the first task process, accurately analyze the first task process, identify the process nodes in the first task process that need to be optimized, and generate a second task process described in DSL. Furthermore, according to the second task process described in DSL, task process orchestration is performed to generate an optimized second task process, realizing automatic optimization of the first task process.

[0112] As described above, the first prompt may include prompt information for indicating optimization of the first task process from at least one dimension. Herein, the dimension can be understood as an optimization direction or an optimization idea. For example, the dimension can be to improve the execution performance of the task process, improve the maintainability of the task process, etc. That is to say, in the embodiments of the present application, the first language model can perform different analyses on the first task process from different optimization directions and different optimization ideas to achieve comprehensive optimization.

[0113] Specifically, when the optimization operation for the first task process indicates optimization of the first task process from the first dimension, the prompt information in the first prompt for indicating optimization of the first task process from at least one dimension includes: prompt information for indicating optimization of the first task process from the first dimension.

[0114] When the optimization operation for the first task process does not indicate the dimension for optimizing the first task process, the hint information in the first hint word for indicating the optimization of the first task process from at least one dimension includes: hint information for indicating the optimization of the first task process from at least one preset dimension.

[0115] That is to say, the embodiments of the present application support different ways to determine the optimization dimension. When the user has a specific optimization requirement for a certain dimension, the first dimension can be indicated in the optimization operation for the first task process. For example, when the user triggers the optimization operation for the first task process through an interaction operation with the digital assistant, the natural language text input by the user for optimizing the first task process can indicate the optimization of the first task process from the first dimension. Thus, the hint information for optimizing the first task process from the first dimension is included in the first hint word. Furthermore, the first language model can analyze and optimize the first task process from the first dimension, realizing customized and targeted task process optimization.

[0116] When the user does not have a specific optimization requirement for a certain dimension, it can also not be indicated in the optimization operation for the first task process. Thus, by pre-configuring the preset dimension, the hint information for optimizing the first task process from the preset dimension is included in the first hint word. Furthermore, the first language model can analyze and optimize the first task process from the preset dimension, also providing optimization ideas and directions for the first language model and realizing comprehensive task process optimization.

[0117] In the process of the first language model analyzing the first task process based on the hint ability of the first hint word, the first language model can analyze with the help of auxiliary information related to the first task process. In some embodiments, the first hint word further includes the historical execution data of the first task process. The hint information in the first hint word for indicating the optimization of the first task process from at least one dimension may include hint information for indicating the execution of the following steps: according to the historical execution data of the first task process, determine the first data for measuring the execution performance of each process node in the first task process, and according to the first data, determine the process nodes to be optimized in the first task process, and optimize the process nodes to be optimized.

[0118] Among them, the historical execution data of the first task process can be understood as: the execution data of the first task process in the historical time period. The first data can be understood as the execution data with the process node as the granularity in the historical execution data of the first task process, and the first data can be used to measure the execution performance of each process node in the first task process. For example, the first data can be the execution time of the process node, the proportion of execution resources occupied by the process node, etc.

[0119] By configuring the above information in the first prompt, the first language model can combine the historical execution data of the first task process, identify the process nodes to be optimized with defective execution performance from the first task process, and then optimize the process nodes to be optimized. Combining the dynamic execution results of the first task process, the first task process is optimized from the dimension of optimizing execution performance.

[0120] In some other embodiments, the first prompt further includes the inspection result of the process inspector inspecting the first task process. The prompt information in the first prompt for indicating optimizing the first task process from at least one dimension may include the prompt information for indicating performing the following steps: determining the process nodes to be optimized in the first task process according to the inspection result, and optimizing the process nodes to be optimized.

[0121] Among them, the process inspector can be understood as a module provided by the process engine for inspecting the structure of the task process. For example, the process inspector can inspect whether there are redundant process nodes in the task process, the coupling degree of process nodes, the structural complexity of the task process, the dependency relationship between each process node, etc., and obtain the inspection result.

[0122] By configuring the above information in the first prompt, the first language model can combine the inspection result of the process inspector, identify the process nodes to be optimized with unreasonable structure from the first task process, and then optimize the process nodes to be optimized. Combining the static structure analysis result of the first task process, the first task process is optimized from the dimension of maintainability.

[0123] The idea of task process optimization and reconstruction will be described below in combination with specific first and second task processes.

[0124] The first case: changing the first process node and the second process node that are serially executed in the first task process to the first process node and the second process node that are executed in parallel in the second task process.

[0125] That is to say, through the optimization of the first task process, multiple process nodes that are serially executed in the first task process are optimized to multiple process nodes that are executed in parallel in the second task process. In this way, the execution speed of the task process is improved, and the first task process is optimized in terms of execution efficiency.

[0126] See Figure 2A and Figure 2B the schematic diagram of the task process shown, Figure 2AThe first task process before optimization. The first task process includes process nodes that are serially executed, such as a process node for inputting a product identity (ID), a process node for querying inventory based on the product ID, a process node for querying product details based on the product ID, a process node for querying product reviews based on the product ID, a process node for summarizing product information, and a process node for outputting product information. The first language model analyzes the first task process and finds that the input parameters of the process node for querying inventory based on the product ID, the process node for querying product details based on the product ID, and the process node for querying product reviews based on the product ID are all only the product ID, and there is no dependency relationship among the above three process nodes. Therefore, the first language model determines that the above three process nodes can be optimized to be executed in parallel. Figure 2B The second task process after optimization. In the second task process, the process node for querying inventory based on the product ID, the process node for querying product details based on the product ID, and the process node for querying product reviews based on the product ID are executed in parallel. And before the process node for querying inventory based on the product ID, the process node for querying product details based on the product ID, and the process node for querying product reviews based on the product ID, a process node for parallel execution is added. In this way, by optimizing the serially executed process nodes into parallel executed process nodes, the execution speed of the task process is accelerated.

[0127] The second case: Change the process node for obtaining external data in the first task process to a process node for pre-caching external data or a process node for pre-loading external data in the second task process.

[0128] That is to say, through the optimization of the first task process, using the process node based on the caching mechanism or the process node based on the pre-loaded data mechanism provided by the process engine to replace the original process node in the first task process, and obtaining external data in the way of pre-caching or pre-loading data. In this way, the execution performance of the task process is improved, and external data is obtained in a more efficient way.

[0129] The third case: Change the third process node and the fourth process node in the first task process to the first sub-process in the second task process, where the first sub-process includes the third process node and the fourth process node.

[0130] That is to say, through the optimization of the first task process, multiple process nodes in the first task process are optimized into sub-processes in the second task process. In this way, by changing the type of process nodes, the optimized second task process becomes more modular, reduces the business logic coupling degree of the process nodes in the task process, and improves the reusability and maintainability of the task process.

[0131] The fourth case: The fifth process node in the first task process is deleted in the second task process. Wherein, when the first task process does not include the fifth process node, the first task process is still used to execute the business task.

[0132] That is to say, through the optimization of the first task process, the redundant process nodes existing in the first task process are deleted, so that the optimized second task process does not include redundant process nodes. In this way, on the basis of not affecting the business tasks executed by the task process, the number of process nodes in the task process is reduced, and the duplication of process nodes in the task process is achieved.

[0133] See Figure 3A and Figure 3B the schematic diagram of the task process shown in Figure 3A For the first task process before optimization, the first task process includes process nodes for verifying orders, process nodes for checking inventory, process nodes for processing payments, process nodes for checking inventory, process nodes for allocating logistics, and process nodes for pushing notifications that are executed serially. The first language model analyzes the first task process and finds that the second process node for checking inventory in the first task process is a redundant process node. Moreover, the process node for verifying orders and the process node for checking inventory in the first task process can be combined into a first sub-process, and the process node for processing payments and the process node for allocating logistics can be combined into a second sub-process. Figure 3B For the second task process after optimization, the second task process includes a first sub-process, a second sub-process, and a process node for pushing notifications that are executed serially. In this way, by removing the redundant process nodes in the task process and encapsulating the task process into sub-processes, the reuse rate of the sub-processes is improved, the execution efficiency of the task process is enhanced, and the overall structure of the task process is made more concise.

[0134] The fifth case: The control flow node and the first code node in the first task process are changed to the second code node in the second task process. The control flow node is used to execute the first control logic, the code configured by the first code node is used to execute the first data processing logic, and the second code node is used to execute the first control logic and the first data processing logic.

[0135] Among them, a control flow node can be understood as a node provided by a process engine for implementing control logic. For example, a control flow node can be a loop node, a branch node, etc. A code node can be understood as a node provided by a process engine that allows users to configure data processing logic by themselves. In other words, the node parameters of a code node include the code configured by the user. For example, when a user has a need to perform data format conversion, since the process engine does not provide a process node for data format conversion, the user can add a code node and configure the code for data format conversion in the code node, so that the code node can execute the logic of data format conversion.

[0136] That is to say, by optimizing the first task process, the code logics of the control flow node and the code node existing in the first task process are merged and reconstructed into a single process node that can execute both control logic and data processing logic. In this way, the number of process nodes in the task process is reduced, the code logic is simplified, and the execution performance of the task process is improved.

[0137] See Figure 4A and Figure 4B the schematic diagram of the task process shown in Figure 4A For the first task process before optimization, the first task process includes a start node, a loop node, a first code node, and an end node that are executed serially. The first language model analyzes the first task process and finds that the code logics of the loop node and the first code node in the first task process can be merged into a second code node. Figure 4B For the second task process after optimization, the second task process includes a start node, a second code node, and an end node that are executed serially. In this way, by merging the process nodes of the task process, on the one hand, due to the reduction in the number of process nodes, the execution performance of the task process is improved. On the other hand, the code logic of a single code node is easier to maintain, improving the maintainability of the task process.

[0138] In some embodiments, confirmation can also be made to the user before generating the second task process. Specifically, the first prompt word further includes: prompt information for indicating an optimization plan for the first task process, and the first language model also returns the optimization plan for the first task process. In response to the optimization operation for the first task process, the optimization plan for the first task process is presented, and in response to the confirmation operation for the optimization plan for the first task process, the second task process is generated.

[0139] Among them, the optimization plan for the first task process includes at least one of the following described in natural language: the content to be optimized in the first task process and the optimization process of optimizing the first task process into the second task process.

[0140] For example, when a user triggers an optimization operation for a first task flow through an interaction operation with a digital assistant, an optimization solution for the first task flow can be presented in the digital assistant interaction interface, and a control for providing feedback on the optimization solution for the first task flow can be provided. The user can trigger a confirmation operation for the optimization solution for the first task flow by triggering the control.

[0141] That is to say, by configuring prompt information for instructing the generation of an optimization solution for the first task flow in the first prompt word, the first language model can generate an optimization solution that describes in natural language the optimization of the first task flow into a second task flow. In this way, by presenting the optimization solution, it is confirmed with the user whether to optimize the first task flow according to the optimization solution. After the user confirms the optimization solution, the first task flow is then optimized into the second task flow, avoiding the optimization of the first task flow not meeting the user's requirements.

[0142] Furthermore, considering the correctness and executability of the second task flow, after generating the second task flow, test cases for the second task flow can also be obtained, and the second task flow can be executed using the test cases to determine the test results of the second task flow. In response to the test results indicating that there are execution errors in the second task flow, the second task flow is updated.

[0143] The embodiments of the present application do not limit the manner of obtaining the test cases for the second task flow. For example, the test cases for the second task flow can be manually configured by the user, or the test cases for the second task flow can also be automatically generated by the first language model.

[0144] By testing the second task flow, it is judged whether the second task flow can be correctly executed. If there are execution errors in the second task flow, the second task flow is repaired and updated in a timely manner to ensure the correctness of the optimized second task flow and avoid execution failures caused by optimizing the task flow.

[0145] In this method, in a process engine, such as the process engine in a low-code platform, for the user's optimization requirements for the original task flow, the natural language processing ability of the language model is used to analyze and optimize the original task flow, and the optimized task flow is reconstructed, so that the optimized task flow can perform the same business tasks as the original task flow, but there are differences in the number, type, and structural relationship of the process nodes, realizing the automatic optimization of the overall structure of the task flow and improving the overall performance and maintainability of the task flow.

[0146] The above introduced the task flow optimization method provided by the present application. The following will be described in combination with specific page diagrams.

[0147] See Figures 5A to 5DA schematic diagram of a process configuration page is provided. In Figure 5A the process configuration page 50 presents a first task process 51. At the same time, the process configuration page 50 also presents a control 52 for triggering the digital assistant.

[0148] In Figure 5B response to a trigger operation on the control 52 for triggering the digital assistant, a digital assistant interaction interface 53 is presented. The digital assistant interaction interface 53 provides an input box where the user can enter natural language text for optimizing the first task process. After the user sends the natural language text for optimizing the first task process, the digital assistant interaction interface 53 presents the natural language text 531 for optimizing the first task process, such as "Optimize the task process".

[0149] In Figure 5C the digital assistant invokes a first language model to analyze and identify the first task process. The first language model returns an optimization plan for the first task process, and the optimization plan 532 of the first task process is presented in the digital assistant interaction interface 53, such as "The current task process is executed serially, and it is recommended to optimize it to parallel execution to improve execution performance". At the same time, a control 533 for providing feedback on the optimization plan for the first task process is also presented in the digital assistant interaction interface 53, such as an adoption control and a rejection control.

[0150] In Figure 5D response to a trigger operation on the adoption control in the control 533 for providing feedback on the optimization plan for the first task process, the first task process is optimized into a second task process, and the second task process 54 is presented in the process configuration page 50. In this way, the automatic optimization of the task process is achieved by interacting with the digital assistant.

[0151] The above combines Figure 1 to FIG. 5 to introduce the task process optimization method provided by the embodiments of the present application in detail. Next, the devices and equipment provided by the embodiments of the present application will be introduced with reference to the accompanying drawings.

[0152] Refer to Figure 6 the structural schematic diagram of the task process optimization device shown. Deployed in the process engine, the device 60 includes:

[0153] A presentation module 601, configured to present a first task process in a process configuration page;

[0154] A generation module 602, configured to generate a second task process in response to an optimization operation for the first task process; wherein, the second task process and the first task process are used to perform the same business task, and there is at least one of the following differences between the second task process and the first task process: the number of process nodes, the type of process nodes, and the structural relationship between process nodes.

[0155] Specifically, the generation module 602 is configured to generate a first prompt; wherein, the first prompt includes: the first task process described in a domain-specific language and prompt information for indicating optimization of the first task process from at least one dimension; send the first prompt to a first language model, and receive the second task process described in the domain-specific language returned by the first language model; generate the second task process according to the second task process described in the domain-specific language.

[0156] In some possible implementation manners, the presentation module 601 is specifically configured to:

[0157] In response to a selection operation for the first task process on a process configuration page, present the first task process, where the selection operation is used to select from the configured task processes; or,

[0158] In response to a task process configuration operation triggered on the process configuration page, present the first task process, where the task process configuration operation is used to configure the first task process; or,

[0159] In response to a task process generation operation triggered on the process configuration page, present the first task process, where the task process generation operation is associated with a natural language text for describing the first task process, and the task process generation operation is used to trigger the first language model to generate the first task process based on the natural language text for describing the first task process.

[0160] In some possible implementation manners, the generation module 602 is specifically configured to:

[0161] In response to a trigger operation for an optimization control, generate a second task process, where the optimization control is used to trigger optimization of the first task process; or,

[0162] In response to an interaction operation with a digital assistant, generate the second task process, where the interaction operation with the digital assistant is associated with a natural language text for optimizing the first task process.

[0163] In some possible implementation manners, the generation module 602 is specifically configured to:

[0164] In response to a trigger operation for a digital assistant, present a digital assistant interaction interface;

[0165] In response to receiving natural language text for optimizing the first task flow in the digital assistant interaction interface, generate the second task flow in the process configuration page.

[0166] In some possible implementation manners, the first prompt word further includes: prompt information for indicating to generate an optimization plan for the first task flow, and the first language model also returns the optimization plan for the first task flow; the generating module 602 is specifically configured to:

[0167] In response to an optimization operation for the first task flow, present the optimization plan for the first task flow; wherein, the optimization plan for the first task flow includes at least one of the following described in natural language: the content to be optimized in the first task flow and the optimization process of optimizing the first task flow into the second task flow;

[0168] In response to a confirmation operation for the optimization plan for the first task flow, generate the second task flow.

[0169] In some possible implementation manners, the apparatus 60 further includes a testing module, and the testing module is used for:

[0170] Obtain a test case for the second task flow;

[0171] Execute the second task flow by using the test case, and determine the test result of the second task flow;

[0172] In response to the test result indicating that there is an execution error in the second task flow, update the second task flow.

[0173] In some possible implementation manners, when the optimization operation for the first task flow indicates to optimize the first task flow from a first dimension, the prompt information in the first prompt word for indicating to optimize the first task flow from at least one dimension includes: prompt information for indicating to optimize the first task flow from the first dimension;

[0174] When the optimization operation for the first task flow does not indicate the dimension for optimizing the first task flow, the prompt information in the first prompt word for indicating to optimize the first task flow from at least one dimension includes: prompt information for indicating to optimize the first task flow from at least one preset dimension.

[0175] In some possible implementation manners, the first prompt word further includes historical execution data of the first task process, and the prompt information in the first prompt word for indicating to optimize the first task process from at least one dimension includes:

[0176] Prompt information for indicating to execute the following steps:

[0177] Determine first data for measuring the execution performance of each process node in the first task process according to the historical execution data of the first task process;

[0178] Determine the process nodes to be optimized in the first task process according to the first data;

[0179] Optimize the process nodes to be optimized.

[0180] In some possible implementation manners, the first prompt word further includes the inspection result of the process checker for inspecting the first task process, and the inspection result is used to measure the structural configuration of the first task process. The prompt information in the first prompt word for indicating to optimize the first task process from at least one dimension includes:

[0181] Prompt information for indicating to execute the following steps:

[0182] Determine the process nodes to be optimized in the first task process according to the inspection result;

[0183] Optimize the process nodes to be optimized.

[0184] In some possible implementation manners, the optimization operation includes at least one of the following:

[0185] Change the first process node and the second process node that are serially executed in the first task process to the first process node and the second process node that are executed in parallel in the second task process; and,

[0186] Change the process node for obtaining external data in the first task process to the process node for pre-caching the external data or the process node for pre-loading the external data in the second task process; and,

[0187] Change the third process node and the fourth process node in the first task process to the first sub-process in the second task process, where the first sub-process includes the third process node and the fourth process node; and,

[0188] Delete the fifth process node in the first task process in the second task process. Wherein, when the first task process does not include the fifth process node, the first task process is still used to execute the service task; and,

[0189] Change the control flow node and the first code node in the first task process into the second code node in the second task process, where the control flow node is used to execute the first control logic, the code configured by the first code node is used to execute the first data processing logic, and the second code node is used to execute the first control logic and the first data processing logic.

[0190] The task process optimization device 60 according to the embodiment of the present application can correspondingly execute the method described in the embodiment of the present application, and the above and other operations and / or functions of each module / unit of the task process optimization device 60 are respectively for implementing Figure 1 the corresponding processes of the respective methods in the illustrated embodiments. For the sake of brevity, they will not be described herein again.

[0191] The embodiment of the present application also provides an electronic device. This electronic device is specifically used to implement the functions of the task process optimization device 60 in the Figure 6 illustrated embodiment.

[0192] Figure 7 A schematic structural diagram of an electronic device 700 is provided. As Figure 7 shown, the electronic device 700 includes a bus 701, a processor 702, a communication interface 703, and a memory 704. The processor 702, the memory 704, and the communication interface 703 communicate with each other through the bus 701.

[0193] The bus 701 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 7 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0194] The processor 702 can be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP), etc.

[0195] The communication interface 703 is used for external communication. For example, the communication interface 703 can be used for communicating with a terminal.

[0196] The memory 704 may include a volatile memory, such as a random access memory (RAM). The memory 704 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0197] Executable code is stored in the memory 704, and the processor 702 executes the executable code to perform the foregoing task flow optimization method.

[0198] Specifically, in the case of implementing Figure 6 the illustrated embodiment, and Figure 6 when each module or unit of the task flow optimization device 60 described in the embodiment is implemented by software, the software or program code required to execute the functions of each module / unit in Figure 6 can be partially or fully stored in the memory 704. The processor 702 executes the program code corresponding to each unit stored in the memory 704 to perform the foregoing task flow optimization method.

[0199] An embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium may be any available medium that can be stored by a computing device or a data storage device such as a data center including one or more available media. The available medium may be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state drive), etc. The computer-readable storage medium includes instructions that direct the computing device to execute the foregoing task flow optimization method applied to the task flow optimization device 60.

[0200] An embodiment of the present application also provides a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the processes or functions described in the embodiments of the present application are fully or partially generated.

[0201] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer or data center to another website, computer or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0202] When the computer program product is executed by a computer, the computer executes any of the aforementioned task flow optimization methods. The computer program product may be a software installation package, and when any of the aforementioned task flow optimization methods is needed, the computer program product may be downloaded and executed on a computer.

[0203] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to each embodiment of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0204] The units involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the unit / module does not, in some cases, constitute a limitation on the unit itself.

[0205] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0206] In the context of the embodiments of the present application, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include electrical connections based on one or more wires, a portable computer disk, 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 of the foregoing.

[0207] It should be noted that the embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the systems or devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple. For the relevant parts, reference can be made to the descriptions in the method section.

[0208] It should be understood that in the present application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (one) of the following" or its similar expression refers to any combination of these items, including any combination of single items (ones) or plural items (ones). For example, at least one (one) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0209] It should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0210] The steps of the methods or algorithms described in connection with the embodiments disclosed herein may be implemented directly in hardware, in software modules executed by a processor, or in a combination thereof. The software modules may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0211] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A task process optimization method, characterized in that: Applied to a process engine, the method comprises: On the process configuration page, the first task process is presented; In response to the optimization operation on the first task flow, a second task flow is generated; wherein the second task flow and the first task flow are used to execute the same business task, and the second task flow and the first task flow have at least one difference in the following: the number of process nodes, the type of process nodes, and the structural relationship between process nodes; The second task flow is generated by the following steps: Generate a first prompt word; wherein the first prompt word includes: the first task flow described in a domain-specific language and prompt information for indicating that the first task flow is optimized from at least one dimension; Sending the first prompt word to a first language model, and receiving a second task flow described in a domain-specific language returned by the first language model; The second task flow is generated according to the second task flow described in the domain specific language.

2. The method according to claim 1, characterized in that In the process configuration page, the first task process is presented, including: In response to a selection operation on a first task flow in a flow configuration page, presenting the first task flow, wherein the selection operation is used to select a configured task flow; or, In response to a task flow configuration operation triggered in the flow configuration page, presenting the first task flow, wherein the task flow configuration operation is used to configure the first task flow; or, In response to a task process generation operation triggered in a process configuration page, the first task process is presented, the task process generation operation is associated with a natural language text used to describe the first task process, and the task process generation operation is used to trigger the first language model to generate the first task process based on the natural language text used to describe the first task process.

3. The method according to claim 1, characterized in that The generating a second task flow in response to the optimization operation on the first task flow comprises: generating a second task flow in response to a trigger operation on an optimization control, wherein the optimization control is used to trigger optimization of the first task flow; or The second task flow is generated in response to an interaction with a digital assistant, wherein the interaction with the digital assistant is associated with a natural language text for optimizing the first task flow.

4. The method according to claim 3, characterized in that The generating the second task process in response to the interactive operation with the digital assistant includes: In response to a trigger operation on the digital assistant, presenting a digital assistant interaction interface; In response to receiving natural language text for optimizing the first task process in the digital assistant interaction interface, the second task process is generated in the process configuration page.

5. The method according to claim 1, characterized in that The first prompt word further includes: prompt information for indicating the generation of an optimization solution for the first task flow, and the first language model further returns the optimization solution for the first task flow; The generating a second task flow in response to the optimization operation on the first task flow comprises: In response to the optimization operation for the first task flow, an optimization scheme for the first task flow is presented; wherein the optimization scheme for the first task flow includes at least one of the following items described in natural language: content to be optimized in the first task flow and an optimization process for optimizing the first task flow into the second task flow; In response to a confirmation operation on the optimization solution for the first task flow, the second task flow is generated.

6. The method according to claim 1, characterized in that After generating the second task flow according to the second task flow described in the domain specific language, the method further includes: Obtaining a test case for the second task process; Executing the second task flow using the test case to determine a test result of the second task flow; In response to the test result indicating that there is an execution error in the second task flow, the second task flow is updated.

7. The method according to claim 1, characterized in that When the optimization operation for the first task flow indicates to optimize the first task flow from a first dimension, the prompt information in the first prompt word for indicating to optimize the first task flow from at least one dimension includes: prompt information for indicating to optimize the first task flow from the first dimension; When the optimization operation for the first task flow does not indicate the dimension for optimizing the first task flow, the prompt information in the first prompt word for indicating optimizing the first task flow from at least one dimension includes: prompt information for indicating optimizing the first task flow from at least one preset dimension.

8. The method according to claim 1, characterized in that The first prompt word also includes historical execution data of the first task flow, and the prompt information in the first prompt word for indicating to optimize the first task flow from at least one dimension includes: Prompts for following the steps below: Determining first data for measuring execution performance of each process node in the first task process according to historical execution data of the first task process; Determine, according to the first data, a process node to be optimized of the first task process; Optimize the process node to be optimized.

9. The method according to claim 1, characterized in that: The first prompt word also includes an inspection result of the first task flow by the flow checker, and the inspection result is used to measure the structural configuration of the first task flow. The prompt information in the first prompt word for indicating to optimize the first task flow from at least one dimension includes: Prompts for following the steps below: Determine, according to the inspection result, a process node to be optimized of the first task process; Optimize the process node to be optimized.

10. The method according to any one of claims 1 to 9, characterized in that: The optimization operation includes at least one of the following: Changing the first process node and the second process node executed serially in the first task flow into the first process node and the second process node executed in parallel in the second task flow; or, Changing a process node for acquiring external data in the first task process to a process node for pre-caching the external data or a process node for pre-loading the external data in the second task process; or, Changing the third process node and the fourth process node in the first task process to the first sub-process in the second task process, wherein the first sub-process includes the third process node and the fourth process node; or, deleting the fifth process node in the first task process in the second task process, wherein when the first task process does not include the fifth process node, the first task process is still used to execute the business task; or The control flow node and the first code node in the first task flow are changed to the second code node in the second task flow, wherein the control flow node is used to execute the first control logic, the code configured in the first code node is used to execute the first data processing logic, and the second code node is used to execute the first control logic and the first data processing logic.

11. A task process optimization device, characterized in that: Deployed in the process engine, the device includes: A presentation module, used to present the first task process in the process configuration page; A generating module, configured to generate a second task flow in response to an optimization operation on the first task flow; wherein the second task flow and the first task flow are used to execute the same business task, and the second task flow and the first task flow differ in at least one of the following: the number of process nodes, the type of process nodes, and the structural relationship between process nodes; The generation module is specifically used to generate a first prompt word; wherein the first prompt word includes: the first task flow described in a domain-specific language and prompt information for indicating optimization of the first task flow from at least one dimension; send the first prompt word to a first language model, receive a second task flow described in a domain-specific language returned by the first language model; generate the second task flow according to the second task flow described in the domain-specific language.

12. An electronic device, characterized in that: The electronic device comprises a processor and a memory; The processor is configured to execute instructions stored in the memory, so that the electronic device performs the method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The method comprises instructions, wherein the instructions instruct an electronic device to execute the method according to any one of claims 1 to 10.

14. A computer program product, characterized in that The computer program product comprises computer readable instructions for implementing the method according to any one of claims 1 to 10.

Images