Automatic processing method, device and equipment for artificial process nodes, medium and program product

Abstract

The invention discloses an automatic processing method and device for an artificial process node, equipment, a medium and a program product, which are used for improving the processing efficiency of a task process. The method comprises the following steps: acquiring node data of an artificial process node; reading an automatic processing condition corresponding to the artificial process node, wherein the automatic processing condition is preset when the task process is built or is set by a user with the processing authority of the artificial process node after the task process is built; determining whether the node data meets an automatic processing condition; and in response to the node data meeting the target automatic processing condition, executing according to an automatic processing rule corresponding to the target automatic processing condition to automatically process the artificial process node, the target automatic processing condition being any one of the automatic processing conditions.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, specifically to an automatic processing method, apparatus, equipment, medium, and program product for manual process nodes. Background Technology

[0002] Task workflows are involved in various business operations. Traditional manual task workflows require human intervention to determine whether a task should proceed based on the content of each workflow node. However, as business scales up, the workload of processing task workflows increases exponentially. If manual processing is inefficient, it can lead to severe delays in business processes, making it impossible to keep pace with rapid business growth. Summary of the Invention

[0003] In view of this, embodiments of this application provide an automatic processing method, apparatus, device, medium, and program product for manual process nodes, so as to improve the processing efficiency of task processes.

[0004] To address the above problems, the technical solutions provided in this application are as follows:

[0005] In a first aspect, embodiments of this application provide an automatic processing method for manual workflow nodes, the method comprising:

[0006] Obtain node data for manual workflow nodes;

[0007] Read the automatic processing conditions corresponding to the manual process node. The automatic processing conditions are either preset when the task process is built or set by a user with processing permissions for the manual process node after the task process is built.

[0008] Determine whether the node data meets the automatic processing conditions;

[0009] In response to the node data meeting the target automatic processing conditions, the automatic processing rules corresponding to the target automatic processing conditions are executed to automatically process the manual process node, wherein the target automatic processing conditions are any one of the automatic processing conditions.

[0010] In one possible implementation, the method further includes:

[0011] In response to the node data not meeting the automatic processing conditions, a manual processing task is generated for the manual process node.

[0012] In one possible implementation, the automatic processing conditions are preset during task flow setup, and determining whether the node data meets the automatic processing conditions includes:

[0013] The variable value of the target variable in the node data is compared with the target value of the target variable in the target automatic processing condition. If the variable value of the target variable meets the target value of the target variable, it is determined that the node data meets the target automatic processing condition.

[0014] In one possible implementation, the automatic processing conditions are preset during task flow setup, and determining whether the node data meets the automatic processing conditions includes:

[0015] Input the pre-set automatic processing conditions and the node data into the large language model;

[0016] The node data output by the large language model either meets the target automatic processing conditions or does not meet the automatic processing conditions.

[0017] In one possible implementation, the automatic processing conditions are set by a user with processing permissions for the manual workflow nodes after the task flow is built. Determining whether the node data meets the automatic processing conditions includes:

[0018] The automatic processing conditions set by the user with processing permissions for the aforementioned manual process nodes, along with the node data, are input into the large language model.

[0019] The node data output by the large language model either meets the target automatic processing conditions or does not meet the automatic processing conditions.

[0020] In one possible implementation, the prompt words for the large language model are pre-set.

[0021] In one possible implementation, the method further includes:

[0022] In response to the editing of the automatic processing conditions, the automatic processing conditions are updated.

[0023] In one possible implementation, the method further includes:

[0024] Obtain the processing opinions corresponding to the target automatic processing conditions.

[0025] In one possible implementation, the automatic processing condition corresponding to the manual process node is one or more, and each automatic processing condition corresponds to an automatic processing rule;

[0026] Determining whether the node data meets the automatic processing conditions includes:

[0027] According to the priority order of each of the automatic processing conditions, determine whether the node data meets the target automatic processing conditions one by one.

[0028] In one possible implementation, the method further includes:

[0029] After generating a manual processing task for the manual process node in response to the node data not meeting the automatic processing conditions, the timer starts.

[0030] When the timer reaches the time threshold, the time-limited processing rules of the manual process node shall be followed.

[0031] Secondly, embodiments of this application provide an automatic processing device for manual process nodes, the device comprising:

[0032] The first acquisition unit is used to acquire node data of manual process nodes;

[0033] The reading unit is used to read the automatic processing conditions corresponding to the manual process node. The automatic processing conditions are preset when the task process is built, or set by a user with processing permissions for the manual process node after the task process is built.

[0034] A determining unit is used to determine whether the node data meets the automatic processing conditions;

[0035] The first execution unit is configured to, in response to the node data meeting the target automatic processing condition, execute according to the automatic processing rule corresponding to the target automatic processing condition to automatically process the manual process node, wherein the target automatic processing condition is any one of the automatic processing conditions.

[0036] Thirdly, embodiments of this application provide an automatic processing device for manual process nodes, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the automatic processing method for manual process nodes as described in any of the preceding claims.

[0037] Fourthly, embodiments of this application provide a computer-readable storage medium, characterized in that the computer-readable storage medium stores instructions that, when executed on a terminal device, cause the terminal device to perform an automatic processing method for manual process nodes as described in any of the preceding claims.

[0038] Fifthly, embodiments of this application provide a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program including program code for performing an automated processing method for manual process nodes as described in any of the preceding claims.

[0039] Therefore, the embodiments of this application have the following beneficial effects:

[0040] This application embodiment acquires node data of manual workflow nodes and corresponding automatic processing conditions, automatically determining whether the node data meets preset automatic processing conditions. In specific implementation, automatic processing conditions can be pre-set during task workflow construction or set by a user with processing permissions for manual workflow nodes after task workflow construction is completed. In response to node data meeting any automatic processing condition, execution is performed according to the automatic processing rule corresponding to that condition to complete the automatic processing of the manual workflow node. Condition-based automatic processing improves the efficiency of task workflow implementation. This makes automated task workflows more intelligent, reducing unnecessary manual intervention while ensuring processing quality, thus saving on labor costs. Attached Figure Description

[0041] Figure 1 A schematic diagram illustrating an exemplary application scenario provided in this application embodiment;

[0042] Figure 2 A flowchart illustrating an automatic processing method for manual workflow nodes provided in this application embodiment;

[0043] Figure 3 This is a schematic diagram of an automatic processing method for manual process nodes in an embodiment of this application;

[0044] Figure 4 This is a schematic diagram of another method for automatically processing manual process nodes in an embodiment of this application;

[0045] Figure 5 This is a schematic diagram of the form for filling in the automatic processing conditions in the embodiments of this application;

[0046] Figure 6 This is a schematic diagram illustrating the time-limited processing of manual tasks in the embodiments of this application;

[0047] Figure 7 A schematic diagram of an automatic processing device for a manual process node provided in an embodiment of this application;

[0048] Figure 8 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0049] To make the above-mentioned objectives, features and advantages of the embodiments of this application more apparent and understandable, the embodiments of this application will be further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0050] To facilitate understanding and explanation of the technical solutions provided in the embodiments of this application, the background technology of the embodiments of this application will be described first below.

[0051] Traditional manual task processes require human intervention and judgment based on the content of each process node. However, as business scales up, the workload of processing these tasks increases exponentially. If manual processing is inefficient, it can lead to severe delays in business processes, making it impossible to keep pace with rapid business growth.

[0052] Task processes can be approval processes. For example, in e-commerce platforms, a large number of merchant applications and product reviews would require manual approval, which would lengthen the onboarding process for new merchants, delay the launch of new products, and negatively impact the platform's competitiveness. Manual approval also requires significant investment in human resources, including recruitment, training, and salaries, increasing the operational burden on businesses. Furthermore, manual approval may be subject to subjectivity; different approvers may have varying understandings and interpretations of the same standards, leading to inconsistent and unjust approval results.

[0053] Based on this, embodiments of this application provide an automatic processing method, apparatus, device, medium, and program product for manual process nodes, which can realize the automatic processing of task processes based on automatic processing conditions, making the automatic task processes more intelligent, reducing the involvement of unnecessary manual operations and saving labor costs while ensuring processing quality.

[0054] To facilitate understanding of the automatic processing method for manual workflow nodes provided in the embodiments of this application, the following is combined with... Figure 1 The example scenario is shown below. See also... Figure 1 As shown in the figure, this figure is a schematic diagram of an exemplary application scenario provided in the embodiments of this application.

[0055] This application embodiment can be applied to a terminal running a task flow. Specifically, during the task flow's execution, a user submits a task form, triggering the task flow's initiation. The task form carries node data, which can be understood as the specific data to be processed. The task flow includes one or more manual process nodes. When the task flow reaches a manual process node, the corresponding automatic processing conditions are obtained. This determines whether the node data meets the automatic processing conditions for that manual process node. If the node data meets the automatic processing conditions, the automatic processing rules corresponding to those conditions are executed, and the corresponding operation record is displayed in the task flow. If the node data does not meet the automatic processing conditions, or the automatic processing rules fail to execute, a manual processing task is generated, and a user with the necessary permissions for that manual process node is notified to handle it.

[0056] In the first method of setting automatic processing conditions, during the design phase (i.e., when developers are building the task flow), the automatic processing conditions and corresponding rules for each manual workflow node are determined in communication with the business side. These automatic processing conditions for each manual workflow node are pre-set during task flow construction. In the second method, during the design phase, developers focus on the task flow construction logic and enable the ability to intelligently parse automatic processing conditions. After the task flow is built, users with processing permissions for each manual workflow node set the corresponding automatic processing conditions using natural language.

[0057] Both of these automatic processing condition setting methods can realize the automatic approval method provided in the embodiments of this application, and realize automatic approval based on automatic processing conditions.

[0058] Those skilled in the art will understand that Figure 1 The schematic diagram shown is merely one example in which embodiments of this application can be implemented. The scope of application of the embodiments of this application is not limited by any aspect of this framework.

[0059] To facilitate understanding of the embodiments of this application, the following description, in conjunction with the accompanying drawings, illustrates an automatic processing method for manual process nodes provided by the embodiments of this application.

[0060] See Figure 2 As shown, this figure is a flowchart of an automatic processing method for manual workflow nodes provided in an embodiment of this application. Figure 2 As shown, the method may include S201-S204:

[0061] S201: Obtain node data for manual process nodes.

[0062] When needed, users can initiate task flows. A task flow can include one or more human workflow nodes, which process node data, such as form data from submitted task forms. For example, when a user needs approval, they can submit an approval form and initiate an approval process as a task flow. This approval process can include one or more approval nodes, which are human workflow nodes, and the approval form carries the node data. Specifically, for example, when a user needs to request leave, they can submit an approval form to initiate an approval process for the leave request. The node data can include the number of leave days, the reason for leave, etc. If this leave request task flow requires approval from both the department head and the HR specialist, then the task flow can include two human workflow nodes: one for approving the department head and the other for approving the HR specialist.

[0063] During the task flow, when the task reaches a certain manual process node, the node data of that manual process node can be obtained. Based on the node data, it can be determined whether the manual process node can be passed.

[0064] S202: Read the automatic processing conditions corresponding to the manual process node. The automatic processing conditions are set in advance when the task process is built, or set by a user with processing permissions for the manual process node after the task process is built.

[0065] During the execution of a task flow, when it reaches a manual workflow node, if that node has automatic processing conditions set, it means that the node can automatically process data based on those conditions, and these automatic processing conditions can be obtained. For example, during the execution of an approval flow, when it reaches an approval node, if that node has automatic processing conditions set, it means that the node can automatically approve data based on those conditions, and these automatic processing conditions can be obtained.

[0066] In the embodiments of this application, in the first implementation, the automatic processing conditions can be pre-set when the task flow is built. In this setting method, the automatic processing conditions corresponding to each manual process node are pre-set during the task flow construction. The automatic processing conditions can be set to automatically approve or automatically reject, for example, automatically rejecting when the reimbursement amount is greater than 500 yuan, automatically approving when the leave days are less than or equal to 1 day, etc. In the second implementation, the automatic processing conditions can be set by a user with processing permissions for the manual process nodes after the task flow is built. For example, if the task flow is an approval process, and the approver is a user with processing permissions for the manual process nodes after the approval process is built, the approver can set the automatic processing conditions for the approval nodes.

[0067] The methods for setting the two automatic processing conditions will be further explained in subsequent embodiments, and will not be elaborated here.

[0068] S203: Determine whether the node data meets the automatic processing conditions.

[0069] After reading the automatic processing conditions and node data corresponding to the manual workflow nodes, it can be determined whether the node data meets the automatic processing conditions. When setting automatic processing conditions in advance during task workflow construction, this can be determined by whether the node data matches the automatic processing conditions. For example, if the number of leave days in the node data is 1 day, it meets the automatic processing condition of automatically approving when the number of leave days is less than or equal to 1 day. When users with processing permissions for manual workflow nodes set automatic processing conditions, the large language model can parse and determine whether the node data meets the automatic processing conditions.

[0070] S204: In response to the node data meeting the target automatic processing conditions, execute according to the automatic processing rules corresponding to the target automatic processing conditions to automatically process the manual process nodes. The target automatic processing conditions are any one of the automatic processing conditions.

[0071] Automatic processing conditions correspond to automatic processing rules, such as automatic approval and automatic rejection. When node data meets any automatic processing condition, the automatic processing rule corresponding to that condition can be executed. For example, if the automatic processing condition of automatically approving when the number of leave days is less than or equal to 1 day is met, then the automatic processing rule for this manual workflow node is automatic approval.

[0072] In one possible implementation, it may also include: generating a manual processing task for a manual process node in response to the node data not meeting the conditions for automatic processing.

[0073] If the node data does not meet the automatic processing conditions, it means that the automatic processing conditions cannot determine how to process the manual process node. In this case, a manual processing task for the manual process node needs to be generated, and the relevant users of the manual process node need to be notified to process it manually to ensure that the manual process node can be processed correctly.

[0074] This application embodiment acquires node data of manual workflow nodes and corresponding automatic processing conditions, automatically determining whether the node data meets preset automatic processing conditions. In specific implementation, automatic processing conditions can be pre-set during task workflow construction or set by a user with processing permissions for manual workflow nodes after task workflow construction is completed. In response to node data meeting any automatic processing condition, execution is performed according to the automatic processing rule corresponding to that condition to complete the automatic processing of the manual workflow node. Condition-based automatic processing improves the efficiency of task workflow implementation. This makes automated task workflows more intelligent, reducing unnecessary manual intervention while ensuring processing quality, thus saving on labor costs.

[0075] The following section will continue to describe the automatic processing method for manual process nodes in the embodiments of this application, based on the different automatic processing condition setting methods.

[0076] When setting up automatic processing conditions during task workflow construction, developers build the task workflow based on business logic, understand the business processing specifications, and thus configure the automatic processing conditions. During task workflow execution, the automatic processing conditions corresponding to the manual workflow nodes are used to determine whether to automatically approve or reject the task.

[0077] See Figure 3The diagram illustrates an automatic processing method for manual workflow nodes in this application embodiment, where automatic processing conditions are pre-set during task workflow construction.

[0078] When setting up the task flow, developers pre-set corresponding automatic processing conditions for each manual workflow node that can be automated. The automatic processing conditions can reuse the left-hand side, operator, and right-hand side modes of rules. The left-hand side and right-hand side support consuming workflow variables, including variables output by upstream nodes, system variables, workflow input parameters, manually added variables, and environment variables. Each automatic processing condition corresponds to an automatic processing rule, which can include, for example, automatic approval or automatic rejection. For example, setting the left-hand side to the leave days variable in the node data, with the operator and corresponding target value being less than or equal to 1 day, and the right-hand side to the leave days variable in the automatic processing conditions, with the corresponding automatic processing rule being automatic approval.

[0079] In one possible implementation, the automatic processing conditions are pre-set during task flow setup. The specific implementation of S203 determining whether node data meets the automatic processing conditions may include:

[0080] The value of the target variable in the node data is compared with the target value of the target variable in the automatic target processing conditions. If the value of the target variable meets the target value of the target variable, the node data is determined to meet the automatic target processing conditions.

[0081] During the task flow execution via the workflow engine, for a specific manual workflow node, if an automatic processing condition is set for that node, it is determined that automatic processing is enabled. The automatic processing condition and node data corresponding to that manual workflow node are read, and the target variable in the node data is compared with the target variable in the target automatic processing condition for that node. If the value of the target variable in the node data meets the target value of the target variable in the target automatic processing condition, the node data is determined to meet the target automatic processing condition, and the automatic processing rule corresponding to the target automatic processing condition (automatic approval or automatic rejection) is executed, and the task flow is updated. For example, if the value of the leave days variable in the node data (0.5 days) meets the target value of the leave days variable in the target automatic processing condition (less than or equal to 1 day), then the node data is determined to meet the target automatic processing condition, and the manual workflow node can be automatically approved.

[0082] In one possible implementation, the automatic processing conditions corresponding to the manual process nodes are one or more, and each automatic processing condition corresponds to an automatic processing rule; then the specific implementation of S203 determining whether the node data meets the automatic processing conditions may include:

[0083] Based on the priority order of each automatic processing condition, determine whether the node data meets the target automatic processing condition one by one.

[0084] In this embodiment, the automatic processing conditions corresponding to a manual workflow node can be one or more, and each automatic processing condition corresponds to an automatic processing rule. For example, a certain manual workflow node may have two sets of automatic processing conditions. When the first set of automatic processing conditions is met, the process is automatically approved; when the second set of automatic processing conditions is met, the process is automatically rejected. During runtime, the conditions are judged in the order they are set. If the first set of automatic processing conditions has already been met, the second set of automatic processing conditions is not judged. If neither condition is met, it is determined that the node data does not meet the automatic processing conditions, and a manual processing task for the manual workflow node can be generated.

[0085] In one possible implementation, the automatic processing conditions are pre-set during task flow setup. The specific implementation of S203 determining whether node data meets the automatic processing conditions may include:

[0086] Input the pre-set automatic processing conditions and node data into the large language model;

[0087] The output node data from the large language model either meets the target automatic processing conditions or does not meet the automatic processing conditions.

[0088] Automated processing conditions can also be set via natural language, in which case an AI (Artificial Intelligence) large language model is needed to determine whether the conditions are met. In practical applications, the large language model can read the pre-set automated processing conditions and node data for the manual workflow node. After parsing, the large language model will provide a judgment, outputting whether the node data meets the target automated processing conditions or not. For example, if the large language model parses the node data and the travel destination is domestic, the travel time is no more than 3 days, and the travel dates are consistent with and reasonable in the work plan, then the large language model will output that the node data meets the target automated processing conditions and will be automatically approved.

[0089] In one possible implementation, the prompt words for the large language model are pre-set.

[0090] In practical applications, the prompts of a large language model can be set according to the actual scenario, so that the output of the large language model is more compatible with automatic processing scenarios such as automatic approval scenarios.

[0091] One possible implementation may also include: obtaining the processing opinions corresponding to the target automatic processing conditions.

[0092] In practical applications, corresponding processing opinions can be obtained when a manual workflow node is automatically approved or rejected, allowing users to clearly understand the basis for the execution of the manual workflow node. In one scenario, developers can customize the processing opinions corresponding to the automatic processing conditions. For example, when the node data meets the target automatic processing conditions and the manual workflow node is automatically approved, the processing opinion can be "Conditions met, automatically approved"; when the node data meets the target automatic processing conditions and the manual workflow node is automatically rejected, the processing opinion can be "Conditions not met, automatically rejected". In another scenario, when a large language model is used to parse and judge a manual workflow node, the processing opinion can be the processing opinion output by the large language model.

[0093] In this embodiment, the automatic processing conditions can be preset during the task flow setup, thereby automatically determining whether the node data meets the preset automatic processing conditions. The implementation of automatic processing is relatively simple and improves the efficiency of task flow implementation.

[0094] When the automatic processing conditions are set by users with manual workflow node processing permissions after the task flow is built, developers only need to build the task flow and enable the large language model's intelligent parsing and automatic processing capabilities; they do not need to concern themselves with the specific automatic processing conditions. Users with manual workflow node processing permissions configure the corresponding automatic processing conditions for the manual workflow nodes based on their understanding of the business specifications. During task flow execution, the automatic processing conditions set by users with manual workflow node processing permissions and the prompts set by the developer for intelligent parsing by the large language model are read. The large language model then provides the processing conclusion, thus achieving automatic processing of the manual workflow nodes.

[0095] See Figure 4 The diagram illustrates an automatic processing method for manual workflow nodes, where automatic processing conditions are set by a user with processing permissions for manual workflow nodes after the task flow is built.

[0096] Developers build a task flow and select a large language model to parse the automated processing conditions set by users with processing permissions for manual workflow nodes. They also pre-set the prompts for the large language model. Specifically, they set the prompts input to the large language model, defining the content to be analyzed and the output format. By default, the current manual workflow node's node data and the automated processing conditions set by users with processing permissions for that node are used as input to the large language model. Alternatively, other input content and rules required for parsing conditions can be customized in the prompts. In practical applications, a prompt template can be preset, for example, prompts such as: "Please output the processing conclusion and basis based on the content of the current node data and the automated processing rules set by users with processing permissions for the manual workflow node. Output requirements include: clearly stating the final conclusion of 'agree,' 'reject,' or 'cannot be determined,' with the judgment basis being a point-by-point comparison with the automated processing conditions." Thus, the large language model can output a processing conclusion and processing reason based on the current manual workflow node's node data and the automated processing conditions set by users with processing permissions for that node. The processing reason can serve as a processing opinion.

[0097] When a user with manual workflow permissions enables the automatic processing function for a manually configured workflow node in a developer-built task flow, that user can set automatic processing conditions for that node. These conditions can be set using natural language, including setting the condition name, applicable workflow, automatic processing rules, and status. The automatic processing rule description can specify the conditions under which automatic approval or rejection occurs, allowing the large language model to better parse and process the request. For example, automatic processing rules could include: automatically approving requests under amounts less than 100 yuan and automatically rejecting requests without a stated reason; automatically approving requests under 500 yuan, with the category being travel expenses or office miscellaneous expenses, and with uploaded invoices; and automatically approving leave requests of no more than one day and automatically rejecting requests exceeding one day without a stated reason, etc.

[0098] In practical applications, an auto-processing condition input form can be provided, allowing users with manual workflow node processing permissions to set the auto-processing conditions. These auto-processing conditions can be edited. In one possible implementation, the auto-processing conditions can also be updated in response to editing. For example, in response to editing the auto-processing conditions set by the approver (a user with manual workflow node processing permissions), the auto-processing conditions set by the approver can be updated.

[0099] See Figure 5The diagram illustrates a form for entering automatic processing conditions in an embodiment of this application. Users with manual workflow node processing permissions can create new automatic processing conditions. Once created, these conditions can be manipulated within the form, including editing, deleting, enabling, or disabling them. This allows for flexible and convenient setting and editing of automatic processing conditions.

[0100] In one possible implementation, the automatic processing conditions are set by a user with manual workflow node processing permissions after the task flow is built. The specific implementation of S203 determining whether the node data meets the automatic processing conditions may include:

[0101] Input the automatic processing conditions and node data set by users with manual process node processing permissions into the large language model;

[0102] The output node data from the large language model either meets the target automatic processing conditions or does not meet the automatic processing conditions.

[0103] During the task flow execution, the workflow engine identifies a specific manual workflow node. If automatic processing conditions are set for that node, automatic processing is enabled. The engine can then read the automatic processing conditions set by the user with processing permissions for that node, along with the node data, to automatically process the manual workflow node. By using a large language model to read the automatic processing conditions set by the user with processing permissions for the manual workflow node, as well as the node data for the current node, and combining this with prompts, the large language model determines whether automatic approval or rejection is possible. If the automatic processing conditions are met, the manual workflow node will be automatically processed.

[0104] One possible implementation may also include: obtaining the processing opinions corresponding to the target automatic processing conditions.

[0105] In practical applications, the processing reasons output by the large language model can be used as processing opinions, so that users can clearly understand the basis for the execution of manual process nodes.

[0106] In this embodiment, users with processing permissions for manual workflow nodes can set automatic processing conditions using natural language based on their own judgment criteria. When the task flow reaches a manual workflow node, the system automatically reads the automatic processing conditions set by the user with processing permissions for that node, and uses an AI large language model to parse the form content and the automatic processing conditions set by the user with processing permissions for the manual workflow node, then performs automatic processing. This makes the automated task flow more intelligent, reducing unnecessary manual intervention while ensuring processing quality, thus saving on labor costs.

[0107] In response to node data not meeting the conditions for automatic processing, a manual processing task will be generated, and the execution time limit of the manual processing task can be monitored. In one possible implementation, it may also include:

[0108] After generating a manual processing task for a manual process node in response to node data not meeting the automatic processing conditions, a timer is started; when the timer reaches the time threshold, the manual process node is executed according to the time limit processing rules.

[0109] See Figure 6 The diagram shown illustrates a time-limited manual task processing method in an embodiment of this application.

[0110] After the process is triggered, upon reaching any review node, it is determined whether the node data corresponding to that node meets the automatic processing conditions. If the node data does not meet any automatic processing condition, the automatic processing rule corresponding to that condition is executed. If the node data does not meet the automatic processing conditions, a manual processing task for the manual process node is generated, and a timer begins. It is then determined whether the timer has reached a time threshold. If it has not reached the time threshold, the process continues to wait for a user with processing authority for the manual process node to process it, and then returns to determine whether the timer has reached the time threshold. If the time threshold has been reached, the manual process node's time-limited processing rules are followed. The time-limited processing rules can be set according to time constraints, such as returning the task to the initiator of the process. This ensures that the manual processing task does not remain unprocessed for an extended period.

[0111] Based on the above-described method embodiments, this application also provides an automatic processing device for manual process nodes, which will be described below with reference to the accompanying drawings.

[0112] See Figure 7 As shown, this figure is a structural schematic diagram of an automated processing device for manual process nodes provided in an embodiment of this application. Figure 7 As shown, the automated processing device for this manual process node includes:

[0113] The first acquisition unit 701 is used to acquire node data of manual process nodes;

[0114] The reading unit 702 is used to read the automatic processing conditions corresponding to the manual process node. The automatic processing conditions are preset when the task process is built, or set by a user with processing permissions for the manual process node after the task process is built.

[0115] The determining unit 703 is used to determine whether the node data meets the automatic processing conditions;

[0116] The first execution unit 704 is configured to, in response to the node data meeting the target automatic processing condition, execute according to the automatic processing rule corresponding to the target automatic processing condition to automatically process the manual process node, wherein the target automatic processing condition is any one of the automatic processing conditions.

[0117] In one possible implementation, the device further includes:

[0118] A generation unit is used to generate a manual processing task for the manual process node in response to the node data not meeting the automatic processing conditions.

[0119] In one possible implementation, when the automatic processing conditions are preset during task flow setup, the determining unit is specifically used for:

[0120] The variable value of the target variable in the node data is compared with the target value of the target variable in the target automatic processing condition. If the variable value of the target variable meets the target value of the target variable, it is determined that the node data meets the target automatic processing condition.

[0121] In one possible implementation, the automatic processing conditions are preset during task flow setup, and the determining unit is specifically used for:

[0122] Input the pre-set automatic processing conditions and the node data into the large language model;

[0123] The node data output by the large language model either meets the target automatic processing conditions or does not meet the automatic processing conditions.

[0124] In one possible implementation, the automatic processing conditions are set by a user with processing permissions for the manual process nodes after the task flow is built, and the determining unit is specifically used for:

[0125] The automatic processing conditions set by the user with processing permissions for the aforementioned manual process nodes, along with the node data, are input into the large language model.

[0126] The node data output by the large language model either meets the target automatic processing conditions or does not meet the automatic processing conditions.

[0127] In one possible implementation, the prompt words for the large language model are pre-set.

[0128] In one possible implementation, the device further includes:

[0129] An update unit is configured to update the automatic processing conditions in response to an edit of the automatic processing conditions.

[0130] In one possible implementation, the device further includes:

[0131] The second acquisition unit is used to acquire the processing opinions corresponding to the target automatic processing conditions.

[0132] In one possible implementation, the automatic processing condition corresponding to the manual process node is one or more, and each automatic processing condition corresponds to an automatic processing rule;

[0133] The determining unit is specifically used for:

[0134] According to the priority order of each of the automatic processing conditions, determine whether the node data meets the target automatic processing conditions one by one.

[0135] In one possible implementation, the device further includes:

[0136] A timing unit is used to start timing after generating a manual processing task for the manual process node in response to the node data not meeting the automatic processing conditions;

[0137] The second execution unit is used to execute the manual process node according to the time limit processing rules when the timer reaches the time threshold.

[0138] This application embodiment acquires node data of manual workflow nodes and corresponding automatic processing conditions, automatically determining whether the node data meets preset automatic processing conditions. In specific implementation, automatic processing conditions can be pre-set during task workflow construction or set by a user with processing permissions for manual workflow nodes after task workflow construction is completed. In response to node data meeting any automatic processing condition, execution is performed according to the automatic processing rule corresponding to that condition to complete the automatic processing of the manual workflow node. Condition-based automatic processing improves the efficiency of task workflow implementation. This makes automated task workflows more intelligent, reducing unnecessary manual intervention while ensuring processing quality, thus saving on labor costs.

[0139] This application also provides a computer program product, including computer program instructions, which, when executed on a computer, cause the computer to perform an automatic processing method for manual process nodes as described in any of the preceding embodiments.

[0140] Based on the above-described method embodiments, this application also provides an electronic device, including: one or more processors; and a storage device storing one or more programs thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the above-described method for automatically processing manual process nodes.

[0141] The following is for reference. Figure 8 The diagram illustrates a structural schematic of an electronic device 1300 suitable for implementing embodiments of this application. The terminal devices in these embodiments may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Android Devices), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs (televisions), desktop computers, etc. Figure 8 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0142] like Figure 8 As shown, electronic device 1300 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 1301, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1302 or a program loaded from storage device 1306 into random access memory (RAM) 1303. RAM 1303 also stores various programs and data required for the operation of electronic device 1300. Processing device 1301, ROM 1302, and RAM 1303 are interconnected via bus 1304. Input / output (I / O) interface 1305 is also connected to bus 1304.

[0143] Typically, the following devices can be connected to I / O interface 1305: input devices 1306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 1307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1306 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1309. Communication device 1309 allows electronic device 1300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 An electronic device 1300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0144] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 1309, or installed from storage device 1306, or installed from ROM 1302. When the computer program is executed by processing device 1301, it performs the functions defined in the methods of embodiments of this application.

[0145] The electronic device provided in this application embodiment and the automatic processing method for manual process nodes provided in the above embodiment belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0146] Based on the above-described method embodiments, this application provides a computer-readable medium storing a computer program thereon, wherein the program, when executed by a processor, implements the automatic processing method for manual process nodes as described in any of the above embodiments.

[0147] It should be noted that the computer-readable medium described in the embodiments of this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the embodiments of this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the embodiments of this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0148] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0149] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0150] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the automatic processing method for the aforementioned manual process nodes.

[0151] Computer program code for performing the operations of the embodiments of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0152] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated 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 operation, or using a combination of dedicated hardware and computer instructions.

[0153] The units described in the embodiments of this application can be implemented in software or hardware. The names of the units / modules do not necessarily limit the specific unit itself.

[0154] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0155] In the context of embodiments of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0156] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0157] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0158] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0159] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0160] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for automatic processing of artificial process nodes, characterized in that, The method comprises: acquiring node data of an artificial process node; reading an automatic processing condition corresponding to the artificial process node, the automatic processing condition being pre-set during task process building or being set by a user having processing authority of the artificial process node after completion of task process building; determining whether the node data meets the automatic processing condition; in response to the node data meeting a target automatic processing condition, performing according to an automatic processing rule corresponding to the target automatic processing condition to automatically process the artificial process node, the target automatic processing condition being any one of the automatic processing conditions.

2. The method of claim 1, wherein, The method further comprises: in response to the node data not meeting the automatic processing condition, generating an artificial processing task of the artificial process node.

3. The method of claim 1, wherein, The automatic processing condition is pre-set during task process building, and the determination of whether the node data meets the automatic processing condition comprises: comparing a variable value of a target variable in the node data with a target value of the target variable in a target automatic processing condition, and if the variable value of the target variable meets the target value of the target variable, determining that the node data meets the target automatic processing condition.

4. The method of claim 1, wherein, The automatic processing condition is pre-set during task process building, and the determination of whether the node data meets the automatic processing condition comprises: inputting the pre-set automatic processing condition and the node data into a large language model; outputting, by the large language model, that the node data meets a target automatic processing condition or that the node data does not meet the automatic processing condition.

5. The method of claim 1, wherein, The automatic processing condition is set by a user having processing authority of the artificial process node after completion of task process building, and the determination of whether the node data meets the automatic processing condition comprises: inputting the automatic processing condition set by the user having processing authority of the artificial process node and the node data into a large language model; outputting, by the large language model, that the node data meets a target automatic processing condition or that the node data does not meet the automatic processing condition.

6. The method of any one of claims 1, 4-5, wherein the prompt word of the large language model is pre-set.

7. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: in response to editing of the automatic processing condition, updating the automatic processing condition.

8. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: acquiring a processing opinion corresponding to the target automatic processing condition.

9. The method according to any one of claims 1 to 3, characterized in that, The automatic processing condition corresponding to the artificial process node is one or more, and each of the automatic processing conditions corresponds to an automatic processing rule; The determination of whether the node data meets the automatic processing condition comprises: determining, according to a priority order of each of the automatic processing conditions, whether the node data meets a target automatic processing condition one by one.

10. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: after generating the artificial processing task of the artificial process node in response to the node data not meeting the automatic processing condition, starting timing; when the timing reaches a time threshold, performing according to a time-limited processing rule of the artificial process node.

11. An apparatus for automatic processing of artificial process nodes, characterized by The device comprises: The first obtaining unit is configured to obtain node data of an artificial process node. The reading unit is configured to read an automatic processing condition corresponding to the artificial process node, the automatic processing condition being set in advance when a task flow is built or being set by a user having a processing right of the artificial process node after the task flow is built. The determining unit is configured to determine whether the node data meets the automatic processing condition. The first executing unit is configured to perform an automatic processing on the artificial process node according to an automatic processing rule corresponding to a target automatic processing condition in response to the node data meeting the target automatic processing condition, the target automatic processing condition being any one of the automatic processing conditions.

12. An apparatus for the automated processing of artificial process nodes, characterized by The computer program product comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the automatic processing method of the artificial process node according to any one of claims 1-10 when executing the computer program. The computer readable storage medium stores instructions, and when the instructions run on the terminal device, the terminal device executes the automatic processing method of the artificial process node according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer program product comprises a computer program carried on a non-transitory computer readable medium, and the computer program comprises program codes for executing the automatic processing method of the artificial process node according to any one of claims 1-10.

14. A computer program product, characterised in that, ​

Images