Method, device, storage medium and program product for task processing

Abstract

A method, device, storage medium and program product for task processing are provided. According to the proposed method, a first input can be received, the first input being for selecting a first task to create an execution process, execution of the first task having been completed; presenting the execution process, the execution process comprising a plurality of steps, one step comprising at least one action for executing the first task; and in response to a confirmation of the execution process, executing a second task based on the execution process, the second task being of a same type as the first task. In this way, the accuracy and controllability of task execution can be improved.

Description

Technical Field

[0001] The examples in this paper generally relate to the field of computer science, and in particular to methods, apparatuses, devices, and computer-readable storage media for task processing. Background Technology

[0002] With the development of information technology, intelligent systems are increasingly being applied to various task processing scenarios. In these applications, systems typically complete corresponding tasks automatically based on user input and generate corresponding processing results. As task complexity increases, how to organize and manage task processing flows within the system and improve the controllability of task execution has gradually become a focus of attention in related technical fields. Summary of the Invention

[0003] In a first aspect, a method for task processing is provided. The method includes: receiving a first input for selecting a first task to create an execution process, the execution of the first task having been completed; presenting the execution process, the execution process including multiple steps, one step including at least one action for performing the first task; and, in response to confirmation of the execution process, performing a second task based on the execution process, the second task being of the same type as the first task.

[0004] In a second aspect, an apparatus for task processing is provided. The apparatus includes: a receiving module configured to receive a first input for selecting a first task to create an execution process, the execution of which has been completed; a presenting module configured to present the execution process, the execution process including multiple steps, one step including at least one action for performing the first task; and an execution module configured to execute a second task based on the execution process in response to confirmation of the execution process, the second task being of the same type as the first task.

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

[0006] In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect, a computer program product is provided, which is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method of the first aspect.

[0008] This approach can improve the accuracy and controllability of task execution.

[0009] It should be understood that the content described in this section is not intended to limit the key or important features of the examples in this article, nor is it intended to restrict the scope of the solution. Other features will become readily apparent from the following description. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the various examples herein will become more apparent when taken in conjunction with the accompanying drawings and the following detailed description. In the accompanying drawings, the same or similar reference numerals denote the same or similar elements, wherein: Figure 1 A schematic diagram of the example environment is shown; Figures 2A to 2C Example interfaces for some scenarios are shown; Figure 2D Examples of standardized operating procedures for some scenarios are shown; Figures 2E to 2G Example interfaces for other scenarios are shown; Figure 3 Flowcharts of example processes for task handling are shown in some scenarios; Figure 4 Schematic block diagrams of example devices for task processing in several scenarios are shown; and Figure 5 A block diagram of an electronic device capable of implementing multiple illustrative scenarios is shown. Detailed Implementation

[0011] The examples in the text will now be described in more detail with reference to the accompanying drawings. While some examples are shown in the drawings, it should be understood that solutions can be implemented in various forms and should not be construed as limited to the examples presented herein. Rather, these examples are provided to provide a more thorough and complete understanding of the solutions. It should be understood that the drawings and examples in this document are for illustrative purposes only and are not intended to limit the scope of protection of the solutions.

[0012] It should be noted that the headings of any section / subsection provided herein are not restrictive. Various examples are described throughout this document, and examples of any type may be included under any section / subsection. Furthermore, examples described in any section / subsection may be combined in any way with any other examples described in the same section / subsection and / or different sections / subsections.

[0013] In the description of the examples in this document, the term "including" and similar terms should be understood as open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "an example" or "the example" should be understood as "at least one example". The term "some examples" should be understood as "at least some examples". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0014] The examples in this document may involve user data, data acquisition, and / or use. All of these aspects comply with relevant laws, regulations, and provisions. In the examples presented herein, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, when implementing each example, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained through appropriate means, in accordance with relevant laws and regulations. The specific methods of notification and / or authorization can vary depending on the actual situation and application scenario; the scope of the solution is not limited in this regard.

[0015] In this manual and the sample solutions, any processing of personal information will be conducted only under legal grounds (such as obtaining the consent of the data subject or being necessary for the performance of a contract) and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information beyond what is necessary for basic functions will not affect the user's use of basic functions.

[0016] In this paper, an intelligent system refers to a system capable of autonomous control based on machine learning models. An intelligent system is, for example, a virtual object or physical entity capable of making decisions and autonomously executing actions based on machine learning models to achieve preset goals or complete preset tasks. An intelligent system can be an automated program that understands user intent and can utilize models or invoke tools to complete various types of tasks. In some contexts, examples of intelligent systems may include, but are not limited to: agents, bots, chatbots, digital avatars, intelligent customer service, digital assistants, etc. Alternatively, an intelligent system can also be an intelligent role implemented based on machine learning models. An "intelligent system" can process user requests based on generative models (e.g., language models, multimodal models) to perform specified types of tasks.

[0017] In some scenarios, intelligent systems can be represented as virtual avatars for interaction with users. The term "virtual object" can refer to a digital entity capable of interacting with a user. Virtual objects can include, but are not limited to, digital assistants, intelligent assistants, AI assistants, chatbots, and virtual agents. Virtual objects can possess intelligent dialogue and information processing capabilities, responding to user queries and providing appropriate answers. In some examples, virtual objects can be presented in a graphical form within the interactive interface, such as as avatars, animated characters, or other visual representations.

[0018] As used in this disclosure, the term "machine learning model" refers to a computational model that performs tasks by learning patterns and rules from data. Machine learning models can include, but are not limited to, neural network models, deep learning models, and large language models. In some cases, large language models are an example of machine learning models that can understand and generate natural language text and can be used to perform operations such as task decomposition, tool invocation, and content generation.

[0019] As mentioned above, in many automated task processing systems, users can typically trigger the system to execute specific tasks by inputting task commands. For example, in application scenarios such as software development assistance, data analysis, information organization, or technical solution generation, the system can parse task requirements based on user input and generate corresponding processing results.

[0020] With the development of artificial intelligence technology, some task processing systems have introduced machine learning models to assist in completing complex tasks. By using machine learning models to understand and analyze user input, the system can automatically generate task processing solutions or generate the operational steps required to execute the task, thereby improving the automation level of task processing.

[0021] In some scenarios, completing a task often requires performing multiple actions. For example, a task may include multiple stages such as information retrieval, file reading, tool invocation, data processing, and result organization. To accomplish these operations, the system typically needs to break down the task into multiple execution actions and complete the overall task flow step by step according to a certain execution order.

[0022] In related technologies, machine learning models typically dynamically generate task processing steps based on the current input when performing a task, and then call relevant tools or perform corresponding operations accordingly. Since the task execution process may be adjusted based on the model's inference results at different stages, the specific execution path of the task may differ in different execution phases.

[0023] To improve the reusability of task execution, some systems attempt to process tasks using task templates. For example, the system can pre-configure task instructions and related variable parameters, so that users only need to input the corresponding parameters to trigger task execution when they need to perform similar tasks.

[0024] However, in some application scenarios, relying solely on task templates may still be insufficient to meet the execution requirements of complex tasks. For example, templates are typically used to solidify the task input format, while the actual execution process may still rely on machine learning models to autonomously determine the execution flow, leading to differences in execution paths at different stages. In application scenarios where maintaining a relatively stable execution flow is crucial, this approach may struggle to guarantee consistency in the task execution process.

[0025] On the one hand, during task execution, the system typically goes through multiple intermediate steps, such as tool invocation, file processing, or data generation. These actions cannot be clearly recorded or represented in the template. If the task execution result does not meet expectations, users or the system may lack sufficient information to analyze the cause of the problem, thus increasing the difficulty of problem localization and task debugging.

[0026] On the other hand, in practical applications, some successfully completed tasks often contain relatively efficient execution paths, such as how the task is broken down, what operations are performed at each stage, and what intermediate results are generated. The experience gained in these execution processes may have some reference value in subsequent similar tasks. However, these execution processes are usually not systematically extracted and saved, making it difficult to directly reuse them in subsequent tasks.

[0027] Therefore, in task processing systems based on machine learning models, how to organize and manage the task execution process more clearly, so that the task execution path can be recorded, reused or adjusted, thereby improving the consistency and maintainability of task execution, has become a key issue of concern in related technical fields.

[0028] In view of this, this paper proposes a scheme for task processing. According to this scheme, a first input can be received, which is used to select a first task to create an execution process, the execution of which has been completed. Further, the execution process can be presented, comprising multiple steps, each step including at least one action for performing the first task. Further still, in response to confirmation of the execution process, a second task, of the same type as the first task, is executed based on the execution process.

[0029] In this way, by receiving a first input for selecting a first task that has been completed, and creating and presenting an execution process including multiple steps based on the first task, the execution process of the first task can be organized and expressed step by step. In this way, the originally scattered execution behavior is transformed into a structured operation process, thereby realizing the structured expression and reuse of task execution paths, and overcoming the problem that it is impossible to effectively control the execution process when executing tasks based solely on instructions or templates.

[0030] Furthermore, in response to the confirmation of the execution process, a second task of the same type as the first task is executed based on the execution process. This ensures that the execution process of subsequent tasks is constrained by the execution process, thereby avoiding the problem of uncertain paths during execution and improving the stability of the task execution process. In addition, since the execution process includes multiple steps, and each step includes at least one action for executing the task, the task execution process can be presented in a structured form, which facilitates the understanding and analysis of the task execution process and improves the understandability and controllability of the task processing process.

[0031] The following describes various examples of this scheme in further detail with reference to the accompanying drawings.

[0032] Figure 1 A schematic diagram of example environment 100 is shown. (e.g.) Figure 1 As shown, example environment 100 may include electronic device 110.

[0033] In this example environment 100, electronic device 110 may run an application 120 that supports task processing. Application 120 may be any suitable type of application for task processing. User 140 may interact with application 120 via electronic device 110 and / or its attached devices.

[0034] exist Figure 1 In environment 100, if application 120 is active, electronic device 110 can use application 120 to present interface 150 for supporting task processing.

[0035] In some cases, electronic device 110 communicates with server 130 to provide services to application 120. Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, VR / AR devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some cases, electronic device 110 can also support any type of user-facing interface (such as "wearable" circuitry).

[0036] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide background services for applications 120 in electronic devices 110 that support task processing.

[0037] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection can include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (Wi-Fi) connections. In some cases, server 130 and electronic device 110 can exchange signaling information through their communication connection.

[0038] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of the scheme.

[0039] The following description of the example will continue with reference to the accompanying drawings.

[0040] Figures 2A to 2CExample interfaces 200A to 200C are shown according to some scenarios. Interfaces 200A to 200C can, for example, be provided by... Figure 1 The interface shown is provided by the electronic device 110. It should be understood that the interface shown in the figures is merely an example, and various interface designs may exist in practice. The various graphic elements in the interface may have different arrangements and different visual representations, one or more of which may be omitted or replaced, and one or more other elements may also be present.

[0041] The following text uses the user interface of an intelligent system as an example. Figure 2A In this example, interface 200A includes an interactive interface. Through interface 200A, the system can receive interactions between user 140 and the intelligent system to initiate new task requests or continue existing task processing.

[0042] In some cases, interface 200A may provide an input area 215 for task input, where the user can enter a request for the task to be triggered and initiate the task request via a "send" control 218. Input area 215 may support text input, such as entering text in a text input box, and may also support voice input, such as by triggering a voice control 217. Furthermore, input area 215 may also provide an upload control 216 to support uploading attachments to indicate the user's task request.

[0043] like Figure 2A As shown, interface 200A may include a template display area 211, in which multiple template cards, such as template A, template B, and template C, can be displayed. Each template card may include label information for identifying the purpose of the template and descriptive information for describing the function of the template.

[0044] In this paper, a task template can be understood as structured data used to describe a specific type of task. For example, a template can encapsulate a user's task requirements by defining task structure information corresponding to a specific type of task. For instance, each task template may include natural language instructions describing a type of task objective, and at least one variable. The values ​​of the variables are variable and can be configured individually in different task requests. The variables defined in the task template can be represented as variable slots to receive variable parameters from the task request. Through such task templates, complex task requirements can be transformed into standardized execution instructions. By using task templates, multiple tasks of the same type can be repeatedly initiated by filling in different variable values, thereby improving the consistency and efficiency of task execution.

[0045] Continue to refer to Figure 2AThe interface 200A may include a template tab bar 212. The template tab bar 212 may include multiple category options, such as public templates, favorite templates, and user-defined templates, to categorize and display templates from different sources or of different types.

[0046] In some cases, interface 200A may include a search control 213, which can be used to receive template query information and search for templates that match the query information in the template display area 211. Interface 200A may also include a filter control 214, which can be used to filter templates according to preset filtering conditions.

[0047] In some cases, the intelligent system can receive task requests initiated by user 140 based on templates. See also Figure 2B Upon triggering a task request, the electronic device 110 can present the user-initiated task request on the interface 200B, for example, as a message 221. During task execution, the intelligent system can analyze the user-initiated task request to determine task requirements, thereby generating an execution plan for the task. The task execution plan can indicate one or more sub-tasks required to complete the task.

[0048] In some cases, the intelligent system can present the task execution process and results on interface 200B. After the entire task is completed, the task execution results or access points to the execution results can be presented on the interactive interface (if the execution results require navigation to other interfaces for presentation). In this way, during the task execution process, user 140 can intuitively view the intelligent system's response to task requests; for example, the response could be a reply message 222 to the user's request.

[0049] In some cases, in response to the triggering of an execution action or execution plan presented in message 222, interface 200B may present detailed information 224 corresponding to that execution step or sub-action. For example, detailed information 224 may include execution parameters, information on the tools invoked, and the corresponding execution results, and be presented in a structured form.

[0050] The interaction methods described above are merely illustrative examples. In different situations, the interaction patterns between users and intelligent systems can take many forms. For example, interaction can revolve around a single task request or around task requests within a continuous conversation. Task requests can be presented as task instructions or formed through natural language dialogue or gestures.

[0051] After receiving a user's request message, a smart object can perform corresponding information processing, content generation, or other task processing operations based on the request message. The interaction process is not limited to a specific execution model; it can be a sequential processing process or a collaborative processing process that includes multiple stages or multiple processing units.

[0052] The following description continues with some examples, referring to the accompanying drawings. These examples can be implemented in electronic device 110. It should be noted that the operations performed by electronic device 110 may specifically be performed by relevant applications (e.g., smart systems) installed on electronic device 110. Some operations described herein with reference to electronic device 110 may require the assistance of server 130.

[0053] As mentioned earlier, task templates can be used to assist in initiating and processing a certain type of task. Task templates can be used to define the input structure or parameter form of a task, thereby processing task requests based on the template. However, task templates are difficult to effectively control and constrain the specific execution process of a task within an intelligent system. Therefore, even if the task request is the same, the specific execution path may differ in different task execution processes, leading to instability in the task processing results. To address this, the execution process can be used to further control and constrain the task's execution.

[0054] In this paper, the term "execution process" refers to a structured execution process derived from the analysis and summarization of completed tasks. For example, an execution process can be represented in the form of a standard operation procedure (SOP). For example, an execution process may include multiple steps, each of which may include at least one action for performing the task, and may contain constraint information associated with the action. For example, constraint information can be used to limit the scope or method of operation during task execution, thus providing clear guidance for each step during execution. Through execution processes, execution paths that were originally implicitly determined within the intelligent system can be explicitly expressed and controlled, thereby guiding subsequent tasks of the same type to be processed according to similar execution paths. Compared to templates that only describe task inputs or objectives, this execution process provides more granular execution guidance, transforming the task execution path from an invisible internal decision-making process into a perceptible and adjustable structured process, thereby enhancing the controllability and maintainability of the task processing.

[0055] In some cases, electronic device 110 can receive a first input. The first input is used to select a first task to create an execution process. The first task is a task that has already been completed. Based on the execution process and execution data of the first task, electronic device 110 can summarize and generalize the execution path of the task, thereby generating a corresponding execution process. The execution process can reflect the multiple execution steps and their relationships in completing the first task, thereby guiding the execution of subsequent tasks of the same type.

[0056] In some cases, electronic device 110 can receive the first input on the first interface. Electronic device 110 can present information such as the execution process, execution actions, and execution results of the task on the first interface. User 140 can select the task in the currently executing interface as the source for creating the execution process based on observation of the execution process.

[0057] As an example, the first interface can be the aforementioned interface 200B. After the first task is completed, a first input is received. For example, the first input can be a trigger operation on control 223. In response to the first input, the electronic device 110 can present interface 200C. In interface 200C, configuration content for creating the execution process based on the first task can be presented.

[0058] like Figure 2C As shown, interface 200C may include a template setting area. Within the template setting area, an instruction editing control 231 may be included. The instruction editing control 231 can be used to receive or edit instruction information from the template. In some cases, the instruction information may include at least one variable field. For example, the variable field may be used to represent dynamic parameters during task execution. The instruction information may be a templated instruction containing variable fields, such as "Get the task execution result of {task initiator} within {time range}". By editing the instruction information in the template, the execution process can be adapted to different task contexts during subsequent executions.

[0059] like Figure 2C As shown, the template settings area may also include a task information editing component 232. The task information editing component 232 can be used to set conditional information related to task execution. For example, the conditional information may include the task execution method (such as single execution or batch execution), the task initiator, and the task's time range. Through the task information editing component 232, the conditional information for subsequent task execution can be configured.

[0060] In some cases, electronic device 110 can receive a first input in interface 200B and create an execution process in response to the first input. For example, after entering interface 200C from interface 200B, the corresponding execution process can be directly determined based on the execution process of the first task.

[0061] Alternatively or additionally, in some cases, the interface 200C may include a first creation control 233. In response to triggering the first creation control 233, the electronic device 110 may create an execution process based on the execution progress of the current first task. By setting the first creation control 233, the creation of the execution process can be triggered more explicitly after relevant configuration is completed.

[0062] In some scenarios, the electronic device 110 can receive a first input via a task list, which includes at least one executed task. The first input is used to select a first task from the task list. For example, the task list can centrally display historically completed tasks, and the user can select a suitable task as the source for extracting the execution process based on information such as task name, task description, or execution effect.

[0063] As an example, interface 200C may include a second creation control 234. In response to a trigger on the second creation control 234, electronic device 110 may present a task list 236 in interface 200C. Task list 236 may include multiple completed tasks, each of which may include information such as a task name and task description. In some cases, each task in task list 236 may have a corresponding selection control to allow the user to select at least one task. In response to the selection of a first task in the task list, electronic device 110 may receive a first input to create an execution process based on the selected first task.

[0064] Alternatively or additionally, the first input can be used to select multiple tasks with the same or similar task types to generate an execution process based on the execution processes of multiple tasks. This approach can improve the stability and applicability of the generated execution process.

[0065] In some cases, electronic device 110 may receive a first input in response to the execution result of the first task meeting predetermined conditions. For example, after detecting that the execution result of the first task meets predetermined conditions, the intelligent system may trigger an interactive entry related to the creation of the execution process, thereby enabling the user to initiate the creation operation of the execution process based on the first task.

[0066] In some cases, predefined conditions may include, but are not limited to: successful task execution, no abnormal interruption during task execution, task execution results meeting preset quality requirements, and task execution results meeting preset integrity or consistency requirements. By setting predefined conditions, tasks suitable for extracting the execution process can be selected, thereby improving the stability and reliability of the generated execution process.

[0067] In some cases, the electronic device 110 can present an execution process. The execution process includes multiple steps, and each step includes at least one action for performing a first task. By presenting the execution process, users can intuitively understand the execution path of the task and the relationships between the various steps, and support the reuse or adjustment of the execution path.

[0068] like Figure 2C As shown, the electronic device 110 can present the execution process 235 in a structured node representation on the interface 200C. For example, the execution process may include multiple first nodes. A first node can be understood as a step node, used to represent multiple steps. The various step nodes can be connected in a predetermined order to describe the overall flow of task execution.

[0069] In some cases, in response to the triggering of a first node, the electronic device 110 can present at least one second node. For example, the first node may represent one of multiple steps, and at least one second node may represent at least one sub-step of that step. By triggering step nodes, users can expand or collapse the steps in the execution process 235, thereby presenting more granular execution information. In this way, access to detailed information can be provided while maintaining the clarity of the overall process.

[0070] As an example, Figure 2D A schematic diagram of the architecture of execution process 235 under certain circumstances is shown. Figure 2D As shown, the execution process 235 can be represented using a hierarchical structure. For example, the execution process 235 can include a step hierarchy and sub-step hierarchies under the step hierarchy. The step hierarchy can be used to describe the phased processing units in the task execution process, and the sub-step hierarchy is used to further refine the phased processing units.

[0071] In some cases, the execution process 235 can be a multi-level structure. In addition to step levels and sub-step levels, it can include more levels of node structures, such as third-level or higher-level nodes, to further refine the task execution process. Parent-child relationships can be formed between different levels, thus creating a tree-like or graph-like structure. By supporting multi-level structures, the execution granularity can be flexibly adjusted according to the task complexity.

[0072] In some cases, each step in execution process 235 may include at least one sub-step. Sub-steps describe the specific execution unit that implements the step. In this way, the task execution process can be divided into multiple steps with clear semantics, and fine-grained execution logic can be further defined within each step, thereby achieving hierarchical modeling of the task execution process.

[0073] In some cases, each step in execution process 235 may include first information for constraining the execution process. The first information may indicate at least one of the following: a step name, a module for performing the corresponding step, or a set of tool calls.

[0074] As an example, the first information may include the following fields: step name, used to identify the function of the step; execution subject, used to indicate the processing module or execution unit that performs the step; tool call set, used to limit the scope of tools that the step is allowed to call during execution; and sub-step set, used to represent at least one sub-step contained in the step. Each field in the first information can serve as a structured configuration field to define the execution boundaries or execution capability range of the step.

[0075] In some cases, each sub-step in execution process 235 may include second information describing the specific content to be executed. The second information may include descriptive information of the sub-step, which may describe at least one of the following: sub-step name, sub-step execution objective, sub-step execution action, or sub-step execution result.

[0076] In some cases, the description information for a sub-step can be in natural language, describing the execution logic of the sub-step and including the following fields: sub-step name, execution goal, execution action, and execution result. For example, the execution action in the description information may indicate in natural language that a tool needs to be invoked or a reference needs to be cited.

[0077] In some cases, the description information of sub-steps may include variable fields. These variable fields can reference parameters defined in the template and be replaced during execution based on the specific task context. This approach allows for dynamic adaptation of execution content while maintaining a stable execution structure.

[0078] In some cases, the second information may include configuration information for the sub-step. The configuration information can be used to indicate, in a structured manner, the scope of resources that can be used during the execution of the sub-step. The configuration information may indicate at least one of the following: a set of tool calls or a scope of reference information for the sub-step. The set of tool calls indicates the tools that the sub-step can invoke during execution. The scope of reference information indicates the external information or resources that the sub-step can access.

[0079] In some cases, sub-step hierarchies can serve as atomic units for task execution. For example, the actions defined in a sub-step can directly drive the invocation of corresponding execution modules or tools, thereby completing the corresponding processing task. Step hierarchies, on the other hand, are used to organize and orchestrate multiple sub-steps to form a complete execution flow.

[0080] In some cases, multiple sub-steps within the same step can share an execution context. For example, the execution context can include intermediate data, status information, or variable values ​​generated during the execution of that step, allowing each sub-step to process data based on a unified context.

[0081] In some situations, information can be exchanged between different steps through the execution results. For example, the result of the previous step can serve as the input for the next step, thus forming a sequentially related execution chain between multiple steps. This method enables cross-step information flow.

[0082] In some cases, the execution process can be generated based on the execution data of the first task. The execution data includes at least one of the following: multiple execution actions, a sequence of tool calls for multiple execution actions, execution parameters for multiple execution actions, or input data, output data, and intermediate results for multiple execution actions.

[0083] In some cases, execution data can correspond to a complete execution record of the intelligent system during the execution of the first task. For example, the execution record may include intermediate information generated during task execution, records of calls to external tools, data transfer relationships between steps, and the final result information. By tracing back the above execution data, the complete execution path of the task can be reconstructed.

[0084] In some situations, electronic device 110 can determine the relationships between multiple execution actions based on the execution data of the first task. For example, electronic device 110 can establish a relationship structure between execution actions based on input-output dependencies, execution order relationships, or semantic relationships. Through these relationships, the organization of multiple execution actions in the overall task execution process can be identified, thus providing a foundation for subsequent structured abstraction.

[0085] In some situations, electronic device 110 can obtain multiple sub-steps based on association relationships by identifying at least one action with the same goal as a sub-step. For example, for multiple consecutive actions performed to achieve the same stage goal, electronic device 110 can summarize them into a single sub-step instead of describing each action separately. In this way, the complexity of the execution process can be reduced while retaining the key execution logic, thereby improving its readability and reusability.

[0086] For example, execution data may include exploratory operations, failed attempts, or other actions unrelated to the final execution goal during task execution. When extracting the execution process, the electronic device 110 can filter the execution data based on task execution results or user feedback, thereby prioritizing the extraction of execution paths that can successfully complete the task and meet expected requirements. As a result, the created execution process can be more efficient, stable, and reliable.

[0087] In some scenarios, electronic device 110 can determine multiple steps by aggregating multiple sub-steps, each step including at least one of the multiple sub-steps. For example, at least one sub-step can be aggregated into one step based on dependencies between sub-steps, execution phase divisions, or functional similarities, thus obtaining multiple steps. Each step may include one or more sub-steps to represent a higher-level phase in the task execution process. By further aggregating sub-steps, a hierarchical execution process structure can be formed, thereby achieving a progressive abstraction from specific execution actions to the overall task flow.

[0088] In some cases, during the generation of the execution process, the electronic device 110 can perform semantic transformation on the operational details in the execution data. The execution data may include tool call information, such as operation instructions in the form of function calls. The electronic device 110 can convert the tool call information into natural language descriptions to generate a more easily understood expression. Through this transformation, the specific implementation details can be hidden while preserving the operational semantics, thereby improving the readability and editability of the execution process.

[0089] By generating execution processes based on the execution data of already executed tasks, the implicit execution paths of intelligent systems during task execution can be transformed into explicit execution flows. On the one hand, this improves the interpretability of the task execution process. On the other hand, it allows for constraints on the execution paths of subsequent similar tasks based on the execution process, thereby improving the consistency and stability of task execution results.

[0090] Figures 2E to 2G Example interfaces 200E to 200G are shown according to other scenarios. In some scenarios, the electronic device 110 can receive editing operations on the execution process. The editing operation is used to edit at least one step in the execution process. Further, the electronic device 110 can present the edited execution process.

[0091] As an example, electronic device 110 may receive a trigger on execution process 235 in interface 200C, and in response to the trigger, present interface 200E for editing execution process 235. Interface 200E may include an editing area 241 for execution process 235.

[0092] In some cases, electronic device 110 may receive editing operations via editing area 241. Editing operations may indicate at least one of the following: modification of information in at least one step of the execution process, or adjustment of the order of at least two steps in the execution process.

[0093] In some cases, information modification operations may include modifying the description or configuration information of a step or sub-step. For example, information such as the step name, execution target, execution action, execution result, or tool call set may be modified. In response to the modification of the edit operation instruction information, the electronic device 110 may update the description or configuration information of the corresponding step or sub-step during execution, and regenerate or present the execution process based on the updated information.

[0094] In some cases, the order adjustment operation can be achieved by dragging and dropping nodes. For example, a user can change the relative positions of multiple steps by dragging and dropping step nodes. In response to the order adjustment operation, the electronic device 110 can adjust the execution order of multiple steps during the execution process.

[0095] In some cases, editing operations can instruct the management of reference information scope. For example, electronic device 110 can add, delete, or replace reference information for sub-steps in the execution process. Reference information may include one or more external files or resources, such as script files or configuration files. Electronic device 110 can receive files uploaded by users and associate the files with the reference information of the corresponding sub-steps.

[0096] In some cases, in response to editing of the execution process or task template, the electronic device 110 may display prompts associated with the execution process. These prompts may indicate suggested modifications to the execution process. For example, refer to... Figure 2E During the editing of the execution process, the electronic device 110 can display prompt information 244 on the interface 200E. The prompt information 244 may include suggestions for modification regarding the structural rationality or content completeness of the execution process.

[0097] Alternatively or additionally, the electronic device 110 may dynamically generate prompt information 244 upon receiving input for the execution process. For example, if the user enters a predetermined character in the information of the execution process, the electronic device 110 may respond to the input by presenting a list of candidate variables for the user to select a predefined variable from the template, thereby inserting the selected variable into the current editing position.

[0098] In some cases, in response to a prompt message, the electronic device 110 may present an edited execution process. For example, the prompt message 244 may include a modification suggestion for modifying at least one step in the execution process. The modification suggestion may include replacing, completing, or rewriting descriptive information, or automatically supplementing configuration information. At least one step in the edited execution process may be updated based on the modification suggestion.

[0099] In some cases, during the editing of the execution process, the electronic device 110 can perform variable consistency and integrity checks on the description information in the execution process based on the task template. For example, the electronic device 110 can indicate through a prompt message that the description information of the first step does not match the task template. The first step can be a step (or a sub-step) in the execution process.

[0100] In some cases, a mismatch between the description information and the task template may include at least one of the following: variables referenced in the description information are not defined in the task template; variables that have been deleted or modified in the task template are still referenced in the description information; variable names in the description information are inconsistent with variable names in the task template; or the description information lacks necessary variables required by the task template.

[0101] In some cases, in response to the modification or deletion of variables in the task template, the electronic device 110 can perform a global scan of the execution process. For example, after detecting that a variable in the task template has been deleted, the electronic device 110 can display a prompt message 244 on the interface to indicate that the variable reference has become invalid. In response to the triggering of the prompt message 244, the electronic device 110 can jump to the part of the description information that references the invalid variable and highlight the part of the description information that referenced the invalid variable in the first step.

[0102] In some cases, in response to editing operations on the execution process, electronic device 110 can perform a global scan of the execution process. In response to the presence of undefined variables in the description information, electronic device 110 can present prompt information 244 and guide the user to update the task template. For example, electronic device 110 can add at least one variable to the task template in response to a triggering operation of prompt information 244. Through the above methods, bidirectional synchronization between the description information and the task template can be achieved.

[0103] In some cases, prompt message 244 can be used to indicate configuration recommendations for a second step, which is a step (or sub-step) in the execution process. The edited execution process includes an edited second step, which is updated based on the configuration recommendations.

[0104] In some cases, configuration suggestions include tool configuration suggestions, which are used to add tools to be invoked in the second step to the tool invocation set of the second step. For example, if electronic device 110 detects that the execution action of the second step includes a description of a specific tool capability, but the configuration information of the second step does not contain the corresponding tool, electronic device 110 can present a prompt message 244. For example, prompt message 244 is "Detected that the current step may require the use of the 'charting tool', do you want to add this toolset?" In response to the user triggering the prompt message 244, electronic device 110 can add the charting tool to the tool invocation set of the second step.

[0105] In some cases, configuration suggestions may include reference information configuration suggestions, which are used to add information to be referenced in the second step to the reference information scope of the second step. For example, if electronic device 110 detects that the description information of the second step references a specific file or data, but that file or data neither exists in the reference information set nor was generated by the preceding step, electronic device 110 may present a prompt message 244. For example, prompt message 244 may read, "The referenced file was not found. Please confirm the addition of the corresponding attachment or check the output of the preceding step." In response to the user's triggering operation of the prompt message, electronic device 110 may receive the file uploaded by the user and associate that file with the reference information set of the second step.

[0106] In some cases, electronic device 110 can receive editing operations on the execution process in interface 200E and save the edited execution process in response to triggering save control 245. In response to saving the edited execution process, electronic device 110 can present the updated execution process 255 in interface 200F.

[0107] In some cases, in response to confirmation of the execution process, electronic device 110 may perform a second task based on the execution process. For example, electronic device 110 may determine that confirmation of the execution process has been received in response to a triggering of save control 237 in interface 200C. The second task is of the same type as the first task.

[0108] In some cases, the electronic device 110 can fill the variable defined in the task template corresponding to the type of the first task with the parameter values ​​of the second task. Furthermore, the electronic device 110 can execute the second task based on the execution process and the filled task template. For example, the variable placeholders in the description information can be replaced with the actual parameter values ​​corresponding to the second task, thereby obtaining a specific execution instruction for the current task. In this way, the same execution process can be adapted to different task inputs, improving the reusability of the execution process.

[0109] In some cases, electronic device 110 can execute tasks in the order of steps and sub-steps during the execution process. For example, each sub-step can be regarded as an independent execution unit, and electronic device 110 can assign the execution unit to the corresponding processing module or execution subject for processing.

[0110] In some situations, session context information can be shared among multiple sub-steps within the same step. Session context information may include: intermediate results generated by preceding sub-steps, generated files or data objects, temporary information or status information stored in the system, etc. By sharing session context information, subsequent sub-steps can directly access the execution results of preceding sub-steps, thereby enabling the continuous transfer of information between multiple sub-steps.

[0111] By combining task templates and execution process methods, the task execution process can be transformed into a controllable execution process based on a structured workflow. On the one hand, through variable filling mechanisms, the same workflow can be adapted to different task inputs. On the other hand, through phased execution and context sharing mechanisms, the continuity and integrity of information during task execution can be guaranteed. Furthermore, by constraining specific execution processes through execution process constraints, uncertainties in the execution process can be effectively constrained, thereby improving the stability and predictability of task execution.

[0112] In some situations, electronic device 110 can perform version management of the execution process. For example, electronic device 110 can generate a corresponding version record each time the execution process is edited, updated, or its status changes, thereby recording the historical version information of the execution process. Figure 2E As shown, the electronic device 110 can provide a version management control 242 in the interface. In response to a triggering operation on the control 242, the electronic device 110 can present multiple historical versions of the execution process. For example, the electronic device 110 can display multiple versions in the interface in the form of a list or timeline, and support the user to select one of the versions to view or edit.

[0113] In some cases, such as Figure 2C , Figure 2F and Figure 2G As shown, the electronic device 110 can present the status of the execution process based on updates to the execution process. The status of the execution process includes at least one of the following: in progress, valid, invalid, or draft.

[0114] In some cases, the "Generating" status can indicate that the execution process is extracting or generating data based on task execution data. The "Valid" status indicates that the execution process is in a callable state. The "Invalid" status indicates that the execution process no longer meets execution requirements due to changes in associated conditions. The "Draft" status indicates that the execution process is editable but has not passed validation.

[0115] In some cases, electronic device 110 can determine or update the status of the execution process based on the consistency between the execution process and the task template. For example... Figure 2G As shown, if the execution process 265 no longer meets the execution requirements due to changes in associated conditions, the electronic device 110 may present the execution process 265 as a failure state.

[0116] In some cases, the electronic device 110 may determine the state of the execution process as a failure state in response to at least one of the following: in the updated execution process, at least one variable in the third step does not match the task template; in the updated execution process, the tool to be invoked in the fourth step is in a failure state; or in the updated execution process, the information to be referenced in the fifth step is in a failure state.

[0117] As an example, if a variable defined in the task template is deleted or renamed, but a reference to that variable still exists in the third step of the execution process, the electronic device 110 can mark the execution process as invalid. If the core instructions in the task template are modified, the electronic device 110 can perform a semantic consistency check on the instructions before and after the modification. If the check indicates that the semantics before and after the modification are inconsistent, the electronic device 110 can mark the execution process as invalid.

[0118] As another example, if the tools or reference information on which a step in the execution process depends changes, the electronic device 110 can detect the availability of the tools or reference information. For example, if a tool is unavailable, removed, or no longer supported for the current task type, or if a reference file is missing, deleted, or not accessible to the current task, the electronic device 110 can mark the execution process as in a failed state.

[0119] In some cases, in response to the execution process being in an invalid state, electronic device 110 can delete the execution process and regenerate it based on the execution data of the fourth task. For example, the user can choose to abandon the currently invalid execution process. In response to the selection, electronic device 110 can clear the execution process content associated with the task template. Subsequently, after the user executes a new task (e.g., the fourth task) based on the same task type, electronic device 110 can extract and generate a new execution process based on the execution data of the fourth task.

[0120] In some cases, in response to the execution process being in an invalid state, electronic device 110 can set the execution process to a draft state. Furthermore, electronic device 110 can update the execution process based on editing operations. For example, in response to a triggering of the draft control 261 in interface 200G, electronic device 110 can store the content of the execution process before it becomes invalid and provide it to the user as a draft version for editing. In some cases, electronic device 110 can combine the aforementioned prompt information 244 (e.g., variable invalidation highlighting, tool unavailable prompt, etc.) to guide the user to correct the executed process 265.

[0121] In some cases, in response to the updated execution process passing verification, the status of the updated execution process is set to a valid state. Verification may include, but is not limited to, variable consistency checks, tool availability checks, and reference information validity checks. If the updated standardized operation 265 process passes verification, the electronic device 110 can update the status of the execution process 265 from a draft state to a valid state.

[0122] The aforementioned state management method allows for lifecycle management based on the execution process's state. When task templates or the execution environment change, the availability of the execution process can be dynamically adjusted, thereby improving system stability and adaptability.

[0123] In summary, by generating execution processes based on task execution data and constraining and invoking these processes using task templates, structured modeling and controlled execution of task execution flows are achieved. This approach transforms task processing, which previously relied on dynamically generated models, into a structured process with clearly defined steps and execution paths, thereby reducing uncertainty during execution and improving the stability and consistency of task execution results.

[0124] On the one hand, by extracting successful task execution paths and transforming them into execution processes, a structured expression and persistent storage of task execution experience are achieved. This allows the execution experience to be repeatedly invoked in subsequent tasks, thereby improving the reusability of task processing capabilities and reducing the overhead of repeatedly building execution logic.

[0125] On the other hand, by providing a visual and editable representation of the execution process, and combining mechanisms such as variable consistency verification, tool configuration verification, and reference information verification, users can perform structured adjustments and optimizations to the task execution process. When task execution is abnormal or the results are unsatisfactory, users can locate the problem at the step-level or stage-level granularity and correct the corresponding execution logic, thereby improving the system's diagnostics and maintainability.

[0126] Furthermore, through automatic extraction of the execution process and failure status management mechanisms, users can build task flows with high execution stability without needing complex instruction design capabilities. Simultaneously, when the task template changes, the system can automatically identify the adaptation status of the execution process and guide users to update the process through failure marking, draft repair, and other methods, thereby reducing the maintenance cost of task templates and achieving effective management of the task flow lifecycle.

[0127] Figure 3 A flowchart of an example process 300 for task processing according to some scenarios is shown. Process 300 can be implemented at electronic device 110. See below for reference. Figure 1 To describe process 300.

[0128] like Figure 3 As shown, in box 310, electronic device 110 receives a first input, which is used to select a first task to create an execution process, and the execution of the first task has been completed.

[0129] In box 320, electronic device 110 presents an execution process, which includes multiple steps, one step including at least one action for performing a first task.

[0130] In box 330, in response to confirmation of the execution process, electronic device 110 performs a second task based on the execution process, the second task being of the same type as the first task.

[0131] In some cases, receiving the first input includes receiving the first input via a task list, the task list including at least one executed task, the first input being used to select a first task from the task list.

[0132] In some cases, receiving the first input includes receiving the first input on a first interface, where the first interface presents the execution process of the first task.

[0133] In some cases, receiving the first input includes: receiving the first input in response to the execution result of the first task satisfying predetermined conditions.

[0134] In some cases, presenting the execution process includes: presenting the execution process in the form of structured nodes, the structured node representation including a plurality of first nodes, the plurality of first nodes representing a plurality of steps; and in response to triggering a first node, presenting at least one second node, the first node representing one of the plurality of steps, the at least one second node representing at least one sub-step of that step.

[0135] In some cases, process 300 further includes: receiving an edit operation on the execution process, the edit operation being used to edit at least one step in the execution process; and presenting the edited execution process.

[0136] In some cases, performing a second task based on the execution process includes: in response to editing of the execution process, performing a second task based on the edited execution process.

[0137] In some cases, an editing operation instructs at least one of the following: modification of information in at least one step of the execution process, or adjustment of the order of at least two steps in the execution process.

[0138] In some cases, process 300 further includes: in response to editing of the execution process or task template, presenting a prompt message associated with the execution process, the prompt message indicating suggested modifications to the execution process, the task template being used to define a first task and a second task; and in response to triggering the prompt message, presenting an edited execution process, the edited execution process being updated based on the suggested modifications.

[0139] In some cases, the prompt message includes a first modification suggestion for modifying at least one step in the execution process, and at least one step in the edited execution process is updated based on the first modification suggestion.

[0140] In some cases, the prompt message is used to indicate that the description information of the first step does not match the task template. The first step is one of multiple steps, and the process 300 also includes, in response to the triggering of the prompt message, performing at least one of the following: highlighting a portion of the description information of the first step, or adding at least one variable to the task template, wherein at least one variable is extracted from the portion of the description information.

[0141] In some cases, the prompt message is used to indicate configuration recommendations for the second step, which is one of multiple steps, and the edited execution process includes an edited second step that is updated based on the configuration recommendations.

[0142] In some cases, configuration recommendations include at least one of the following: tool configuration recommendations, which are used to add the tools to be invoked in the second step to the tool invocation set of the second step, or reference information configuration recommendations, which are used to add the information to be referenced in the second step to the reference information scope of the second step.

[0143] In some cases, process 300 may also include: presenting the state of the execution process based on updates to the execution process, the state including at least one of the following: in-process state, valid state, invalid state, or draft state.

[0144] In some cases, executing a second task based on the execution process includes: filling the variable defined in the task template corresponding to the type of the first task with the parameter values ​​of the second task; and executing the second task based on the execution process and the filled task template.

[0145] In some cases, updating the execution process includes at least one of the following: updating the description information of at least one step in response to modification of the editing operation instruction information; or adjusting the execution order of multiple steps in the execution process in response to adjustment of the editing operation instruction order.

[0146] In some cases, the standard operating procedure includes first information for multiple steps and second information for each sub-step. The first information indicates at least one of the following: step name, module used to perform the corresponding step, or set of tool calls, and the second information includes at least one of the following: description information of the sub-step, which describes at least one of the following: sub-step name, execution target of the sub-step, execution action of the sub-step, or execution result of the sub-step; and configuration information of the sub-step, which indicates at least one of the following: set of tool calls for the sub-step or range of reference information for the sub-step.

[0147] In some cases, the execution process is generated based on the execution data of the first task, which includes at least one of the following: multiple execution actions, a sequence of tool calls for multiple execution actions, execution parameters for multiple execution actions, or input data, output data and intermediate results for multiple execution actions.

[0148] In some cases, multiple steps in the execution process are determined by: determining the relationship between multiple execution actions based on execution data; obtaining multiple sub-steps by determining at least one action with the same goal as a sub-step based on the relationship; and determining multiple steps by aggregating multiple sub-steps, each step including at least one sub-step among the multiple sub-steps.

[0149] In some cases, the execution process is determined to be in a failed state in response to at least one of the following: in the updated execution process, at least one variable in the third step does not match the task template; in the updated execution process, the tool to be invoked in the fourth step is in a failed state; or in the updated execution process, the information to be referenced in the fifth step is in a failed state.

[0150] In some cases, process 300 further includes: in response to the execution process being in an invalid state, performing at least one of the following: deleting the execution process and regenerating the execution process based on the execution data of the fourth task; or setting the state of the execution process to a draft state and updating the execution process based on the editing operation on the execution process.

[0151] In some cases, process 300 further includes setting the status of the updated execution process to a valid state in response to the updated execution process passing verification.

[0152] A corresponding apparatus for implementing the above methods or processes is also provided.

[0153] Figure 4 A schematic structural block diagram of an example device 400 for task processing under certain circumstances is shown. Device 400 may be implemented as or included in electronic device 110. The various modules / components in device 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0154] like Figure 4 As shown, the device 400 includes: a receiving module 410 configured to receive a first input for selecting a first task to create an execution process, the execution of which has been completed; a presenting module 420 configured to present the execution process, which includes multiple steps, one step including at least one action for performing the first task; and an execution module 430 configured to execute a second task based on the execution process in response to confirmation of the execution process, the second task being of the same type as the first task.

[0155] In some cases, the receiving module 410 is further configured to receive a first input via a task list, the task list including at least one executed task, the first input being used to select a first task from the task list.

[0156] In some cases, the receiving module 410 is further configured to receive a first input on a first interface, and the first interface presents the execution process of the first task.

[0157] In some cases, the receiving module 410 is further configured to receive the first input in response to the execution result of the first task meeting predetermined conditions.

[0158] In some cases, the presentation module 420 is further configured to: present the execution process in a structured node representation, the structured node representation including a plurality of first nodes, the plurality of first nodes representing a plurality of steps; and in response to a triggering of a first node, present at least one second node, the first node representing one of the plurality of steps, the at least one second node representing at least one sub-step of that step.

[0159] In some cases, the device 400 also includes an editing module configured to: receive an editing operation on the execution process, the editing operation being used to edit at least one step in the execution process; and present the edited execution process.

[0160] In some cases, the execution module 430 is further configured to: in response to editing of the execution process, perform a second task based on the edited execution process.

[0161] In some cases, an editing operation instructs at least one of the following: modification of information in at least one step of the execution process, or adjustment of the order of at least two steps in the execution process.

[0162] In some cases, the editing module is further configured to: in response to editing of the execution process or task template, present a prompt message associated with the execution process, the prompt message indicating suggested modifications to the execution process, the task template being used to define a first task and a second task; and in response to triggering the prompt message, present the edited execution process, the edited execution process being updated based on the suggested modifications.

[0163] In some cases, the prompt message includes a first modification suggestion for modifying at least one step in the execution process, and at least one step in the edited execution process is updated based on the first modification suggestion.

[0164] In some cases, the prompt message is used to indicate that the description information of the first step does not match the task template. The first step is one of multiple steps, and the editing module is further configured to perform at least one of the following in response to the prompt message: highlighting part of the description information of the first step, or adding at least one variable to the task template, at least one variable being extracted from the part of the description information.

[0165] In some cases, the prompt message is used to indicate configuration recommendations for the second step, which is one of multiple steps, and the edited execution process includes an edited second step that is updated based on the configuration recommendations.

[0166] In some cases, configuration recommendations include at least one of the following: tool configuration recommendations, which are used to add the tools to be invoked in the second step to the tool invocation set of the second step, or reference information configuration recommendations, which are used to add the information to be referenced in the second step to the reference information scope of the second step.

[0167] In some cases, the device 400 also includes a state management module configured to present the state of the execution process based on updates to the execution process, the state including at least one of the following: in-process state, valid state, invalid state, or draft state.

[0168] In some cases, the execution module 430 is further configured to: fill the parameter values ​​corresponding to the second task into the variables defined in the task template corresponding to the type of the first task; and execute the second task based on the execution process and the filled task template.

[0169] In some cases, updating the execution process includes at least one of the following: updating the description information of at least one step in response to modification of the editing operation instruction information; or adjusting the execution order of multiple steps in the execution process in response to adjustment of the editing operation instruction order.

[0170] In some cases, the standard operating procedure includes first information for multiple steps and second information for each sub-step. The first information indicates at least one of the following: step name, module used to perform the corresponding step, or set of tool calls, and the second information includes at least one of the following: description information of the sub-step, which describes at least one of the following: sub-step name, execution target of the sub-step, execution action of the sub-step, or execution result of the sub-step; and configuration information of the sub-step, which indicates at least one of the following: set of tool calls for the sub-step or range of reference information for the sub-step.

[0171] In some cases, the execution process is generated based on the execution data of the first task, which includes at least one of the following: multiple execution actions, a sequence of tool calls for multiple execution actions, execution parameters for multiple execution actions, or input data, output data and intermediate results for multiple execution actions.

[0172] In some cases, multiple steps in the execution process are determined by: determining the relationship between multiple execution actions based on execution data; obtaining multiple sub-steps by determining at least one action with the same goal as a sub-step based on the relationship; and determining multiple steps by aggregating multiple sub-steps, each step including at least one sub-step among the multiple sub-steps.

[0173] In some cases, the execution process is determined to be in a failed state in response to at least one of the following: in the updated execution process, at least one variable in the third step does not match the task template; in the updated execution process, the tool to be invoked in the fourth step is in a failed state; or in the updated execution process, the information to be referenced in the fifth step is in a failed state.

[0174] In some cases, the state management module is further configured to: in response to the execution process being in an invalid state, perform at least one of the following: delete the execution process and regenerate it based on the execution data of the fourth task; or set the execution process to a draft state and update it based on the editing operation on the execution process.

[0175] In some cases, the state management module is further configured to set the state of the updated execution process to a valid state in response to the updated execution process passing verification.

[0176] The modules included in device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some cases, one or more modules can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units in device 400 can be implemented at least partially by one or more hardware logic components. By way of example, and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and so on.

[0177] Figure 5 A block diagram of an electronic device 500 in which one or more examples can be implemented is shown. It should be understood that... Figure 5 The electronic device 500 shown is merely exemplary and should not be construed as limiting the functionality and scope of the examples described herein. Figure 5 The illustrated electronic device 500 can be used to implement the electronic device 110 or device 400 discussed above.

[0178] like Figure 5 As shown, electronic device 500 is in the form of a general-purpose electronic device. Components of electronic device 500 may include, but are not limited to, one or more processing units or processors 510, memory 520, storage devices 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. Processor 510 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 520. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 500.

[0179] Electronic device 500 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 530 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 500.

[0180] Electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 5 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various examples.

[0181] The communication unit 540 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 500 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 500 can operate in a networked environment using logical connections to one or more other servers, networked personal computers, or another network node.

[0182] Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 500, or with any device that enables electronic device 500 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via an input / output (I / O) interface (not shown).

[0183] A computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. A computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0184] The flowcharts and / or block diagrams of the methods, apparatus, devices, and computer program products referred to herein describe various aspects. It should be understood that each block of the flowcharts and / or block diagrams, as well as combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0185] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0186] Computer-readable program instructions can 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 data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0187] The flowcharts and block diagrams in the accompanying figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products under various scenarios. In this respect, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the figures. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0188] Various examples have been described above. The foregoing descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for task processing, comprising: Receive a first input, which is used to select a first task to create an execution process, and the execution of the first task has been completed; The execution process is presented, which includes multiple steps, one step including at least one action for performing the first task; as well as In response to confirmation of the execution process, a second task is executed based on the execution process, the second task being of the same type as the first task.

2. The method of claim 1, wherein receiving the first input comprises: The first input is received via a task list, which includes at least one executed task, and the first input is used to select the first task from the task list.

3. The method of claim 1, wherein receiving the first input comprises: The first input is received on the first interface, and the first interface presents the execution process of the first task.

4. The method of claim 1, wherein receiving the first input comprises: In response to the execution result of the first task satisfying a predetermined condition, the first input is received.

5. The method of claim 1, wherein presenting the execution process comprises: The execution process is presented using structured nodes, which include multiple first nodes, each representing a multiple step. as well as In response to a triggering of a first node, at least one second node is presented, wherein the first node represents one of the plurality of steps, and the at least one second node represents at least one sub-step of that step.

6. The method according to claim 1, further comprising: Receive an edit operation on the execution process, the edit operation being used to edit at least one step in the execution process; as well as Presents the edited execution process.

7. The method of claim 6, wherein performing the second task based on the execution process comprises: In response to the editing of the execution process, the second task is performed based on the edited execution process.

8. The method of claim 6, wherein the editing operation indicates at least one of the following: Information modification in at least one step of the execution process, or Adjusting the order of at least two steps in the execution process.

9. The method according to claim 1, further comprising: In response to the editing of the execution process or task template, a prompt message is presented in association with the execution process, the prompt message indicating suggested modifications to the execution process, and the task template is used to define the first task and the second task; as well as In response to the triggering of the prompt message, an edited execution process is presented, which is updated based on the modification suggestion.

10. The method of claim 9, wherein the prompting information includes a first modification suggestion for modifying at least one step in the execution process, and the at least one step in the edited execution process is updated based on the first modification suggestion.

11. The method of claim 9, wherein the prompt information is used to indicate that the description information of the first step does not match the task template, the first step being one of the plurality of steps, and The method further includes, in response to the triggering of the prompt message, performing at least one of the following: Highlighting the descriptive information of the first step, or Add at least one variable to the task template, the at least one variable being extracted from the partial description information.

12. The method of claim 9, wherein the prompting information is used to indicate a configuration suggestion for a second step, the second step being one of the plurality of steps, and The edited execution process includes an edited second step, which is updated based on the configuration recommendations.

13. The method of claim 12, wherein the configuration recommendation includes at least one of the following: Tool configuration suggestions, which are used to add the tools to be invoked in the second step to the tool invocation set of the second step, or The reference information configuration suggestion is used to add the information to be referenced in the second step to the reference information range of the second step.

14. The method according to claim 1, further comprising: Based on the updates of the execution process, the state of the execution process is presented, and the state includes at least one of the following: generating state, valid state, invalid state, or draft state.

15. An electronic device comprising: At least one processor; as well as At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 14 when executed by the at least one processor.

Images