Business process processing method, device, electronic device, storage medium and program product

Abstract

The present application provides a business process processing method, device, electronic device, storage medium and program product. The method includes: obtaining process application information of a target process, the process application information is used to indicate at least one process node of the target process; if at least one process node includes an approval node, and the process application information includes information for indicating a task listener, then determining a target approval strategy in a pre-trained network model based on the process application information; determining target approval account information of the target process based on the target approval strategy, the target approval account information is information of an account that approves the target process at the approval node; and constructing a workflow of the target process based on the process application information and the target approval account information. The method of the present application can improve the efficiency of business process processing.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a business process processing method, device, electronic device, storage medium and program product. Background Art

[0002] Business processes can be streamlined online to improve work efficiency. Some business process processing is implemented through tools, but when generating the workflow corresponding to the business process, the business processes supported by the tools are relatively simple and most require manual intervention, such as manual configuration of process nodes, manual configuration of approval nodes, etc., resulting in low business process processing efficiency and high cost. Summary of the invention

[0003] The present application provides a business process processing method, device, electronic device, storage medium and program product to solve the problem of low business process processing efficiency.

[0004] In a first aspect, the present application provides a business process processing method, comprising:

[0005] Acquire process application information of a target process, where the process application information is used to indicate at least one process node of the target process;

[0006] If the at least one process node includes an approval node, and the process application information includes information for indicating a task listener, determining a target approval strategy in a pre-trained network model based on the process application information;

[0007] Determine target approval account information of the target process based on the target approval policy, where the target approval account information is information of an account that approves the target process at the approval node;

[0008] A workflow of the target process is constructed based on the process application information and the target approval account information.

[0009] In an achievable manner, before determining the target approval strategy in the pre-trained network model based on the process application information, the method further includes:

[0010] Obtaining historical process application information and historical approval strategies corresponding to the historical process application information;

[0011] Preprocessing the historical process application information, and inputting the preprocessed historical process application information into the initial network model to determine the predicted approval strategy output by the initial network model;

[0012] The initial network model is trained based on the historical approval strategy and the predicted approval strategy to determine the pre-trained network model.

[0013] This method obtains historical process application information and the historical approval strategy corresponding to the historical process application information, and performs corresponding preprocessing on the historical process application information, thereby obtaining the pre-trained network model through the preprocessed historical process application information and historical approval strategy training.

[0014] In an implementable manner, the historical process application information includes first historical process application information corresponding to a process including an approval node and second historical process application information corresponding to a process not including an approval node; the step of obtaining the historical process application information and the historical approval strategy corresponding to the historical process application information includes:

[0015] Clustering the first historical process application information and the second historical process application information to obtain at least one cluster set;

[0016] The historical approval strategy corresponding to the first historical process application information in each cluster set is determined as the historical approval strategy corresponding to the second historical process application information in the cluster set.

[0017] This method clusters the first historical process application information including the approval node and the second historical process application information not including the approval node, and the historical process application information combined with the same cluster share a historical approval strategy, thereby increasing the volume of training data.

[0018] In one achievable manner, the preprocessing of the historical process application information includes:

[0019] Performing data cleaning and standardization processing on the historical process application information to determine standardized historical process application information;

[0020] Features in the standardized historical process application information are extracted, and feature enhancement processing is performed on the extracted features to determine pre-processed historical process application information.

[0021] In an implementable manner, determining the target approval account information of the target process based on the target approval policy includes:

[0022] Determine the target indicator based on the target approval strategy, where different approval strategies correspond to different indicators;

[0023] Determining a value corresponding to the target indicator in the process application information;

[0024] Based on the value corresponding to the target indicator, the target approval account information is matched in the preset approval account information.

[0025] This method sets different indicators through different approval strategies, so that after determining the target indicator, the target indicator can be used to match the approval account information that is the same as the process application information in the preset approval account information, and the matched approval account information is determined as the target approval account information, so that the approval account information that needs to be forwarded by the approval node can be obtained.

[0026] In one possible implementation, the method further includes:

[0027] If the at least one process node includes an approval node, and the process application information does not include information for indicating a task listener, determining the preset approval account information as the target approval account information;

[0028] A workflow of the target process is constructed based on the process application information and the target approval account information.

[0029] In a second aspect, the present application provides a business process processing device for a distributed system, the device comprising:

[0030] An information acquisition module, used to acquire process application information of a target process, wherein the process application information is used to indicate at least one process node of the target process;

[0031] an approval strategy determination module, configured to determine a target approval strategy in a pre-trained network model based on the process application information if the at least one process node includes an approval node and the process application information includes information for indicating a task listener;

[0032] An approval account determination module, used to determine target approval account information of the target process based on the target approval policy, wherein the target approval account information is information of an account that approves the target process at the approval node;

[0033] A workflow creation module is used to construct a workflow of the target process based on the process application information and the target approval account information.

[0034] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0035] The memory stores computer-executable instructions;

[0036] The processor executes the computer-executable instructions stored in the memory to implement the method according to the first aspect.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0038] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.

[0039] The business process processing method, device, electronic device, storage medium and program product provided by the present application, after obtaining the process application information, determine whether the approval node needs to determine the target approval strategy by whether there is a task listener on the approval node. When the approval strategy needs to be determined, the target approval strategy can be automatically determined by inputting the process application information into a pre-trained network model. This process does not require manual setting of approval personnel, and can automatically obtain the target approval strategy when the approval node needs the target approval strategy. Subsequently, the account information that the approval node needs to forward for approval can be automatically determined based on the target approval strategy. In this way, the target approval account information can be automatically matched based on the process application information to generate the corresponding workflow. This process does not require manual intervention and has high business process processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0041] Figure 1 is an implementation scenario diagram shown in an exemplary embodiment;

[0042] Figure 2 is a flowchart of a business process processing method shown in an exemplary embodiment;

[0043] Figure 3 is a flow chart of a business process processing method shown in an exemplary embodiment;

[0044] Figure 4 is a flowchart of a business process processing method shown in another exemplary embodiment;

[0045] Figure 5 is a structural diagram of a business process processing device shown in an exemplary embodiment;

[0046] Figure 6 It is a block diagram of an electronic device shown in an exemplary embodiment.

[0047] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0048] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0049] The workflow is applicable to a variety of scenarios and can be streamlined online to improve work efficiency.

[0050] In some workflow processing solutions, workflows are edited through tools, such as jBPM (Java Business Process Management, an open source business process management framework) and OSWorkflow (an open source workflow engine).

[0051] The processes supported by OSWorkflow are relatively simple, and a simple GUI (Graphical User Interface) can be provided for workflow editing, but it cannot support operations such as counter-signing, jumping, returning, and adding signatures to change the workflow.

[0052] jBPM supports fewer functions and its integration is relatively complex. The workflow engine framework Activiti (an open source workflow engine) proposed on its basis has simple integration and supports most workflow-related functions. It can also be used for secondary development to complete customized research and development of enterprise content such as transfer within a process and transfer between processes.

[0053] However, the above workflow framework can only be used to simply generate workflows, such as creating each node in the workflow according to the input information. When there are approval nodes in the workflow, it is impossible to determine the corresponding approver of the workflow according to different scenarios, resulting in low workflow generation efficiency and low adaptability.

[0054] The business process processing method, device, electronic device, storage medium and program product provided in this application are intended to solve the above technical problems of the prior art.

[0055] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0056] The business process processing method provided in this application can be implemented on any electronic device with data processing capabilities, or it can be a business process processing system. It should be noted that the business process processing system can be deployed separately on an electronic device in any environment (for example: deployed separately on an edge server in an edge environment), or it can be deployed entirely in a cloud environment, or it can be deployed in a distributed manner in different environments.

[0057] For example, the business process processing system can be logically divided into multiple parts, each with different functions. The various parts in the business process processing system can be deployed in any two or three of the electronic device (located on the user side, such as the client), the edge environment, and the cloud environment. The edge environment is an environment that includes a collection of edge electronic devices that are close to the electronic device. The edge electronic devices include: edge servers, edge stations with computing power, etc. The various parts of the container startup system deployed in different environments or devices collaborate to realize the functions of the data processing platform.

[0058] It should be understood that this application does not make any restrictive division on which parts of the business process processing system are deployed in what specific environment. In actual application, it can be adaptively deployed according to the computing power of the electronic device, the resource usage of the edge environment and the cloud environment, or the specific application requirements.

[0059] like Figure 1 This is an implementation scenario diagram showing an exemplary embodiment. The business process processing system corresponding to the implementation scenario includes a client 10 and a server 11. The client 10 and the server 11 are connected via network communication.

[0060] The executor of the method of the embodiment of the present application is the server 11, and the client 10 can receive process application information. The client 10 sends the process application information to the server 11 through the network. The server 11 performs business process processing and can feed back the business process processing results to the client 10 through the network. The client 10 has a graphic user interface, and the business process processing results can be displayed on the graphic interface.

[0061] In some embodiments, after receiving the process application information, the server 11 determines at least one process node of the target process indicated by the process application information. If the at least one process node includes an approval node and the process application information includes information for indicating a task listener, the target approval strategy is determined in a pre-trained network model based on the process application information; the target approval account information of the target process is determined based on the target approval strategy, and the target approval account information is the information of the account that approves the target process at the approval node; and the workflow of the target process is constructed based on the process application information and the target approval account information.

[0062] It is understandable that the business process processing device can be set at Figure 1 In the server 11, but the example shown in this embodiment Figure 1 The implementation environment shown is only exemplary. In other embodiments, the business process processing method may also be applied to other implementation environments, and the business process processing device may also be set in other structures in other implementation environments. No specific limitations are made here.

[0063] In this embodiment, the client 10 is an electronic device on the user side, which can be a wired terminal with a visualization structure or a wireless terminal. In other embodiments, the terminal can be an electronic device with a visualization structure such as a mobile phone, a computer, a tablet, and a vehicle-mounted device.

[0064] The server 11 can be an edge environment and a cloud environment, such as a physical server, a server cluster, and a cloud server, etc., and no specific limitations are made here.

[0065] Figure 2 is a flowchart of a business process processing method shown in an exemplary embodiment, which is applied to Figure 1 The server 11 in Figure 2 As shown, the method includes steps S201 to S203, which are described in detail as follows:

[0066] S201. Obtain process application information of a target process, where the process application information is used to indicate at least one process node of the target process.

[0067] In some embodiments, the process application information is a workflow of a target process that needs to be created.

[0068] The process application information is used to indicate at least one process node of the target process. For a target process, it may include at least one process node. The process application information may also include information such as the name of the process node corresponding to each process node, the type of the process node, the status of the process node, and the priority of the process node.

[0069] The types of process nodes may include common task types and approval task types.

[0070] The status of a process node is the status for different process node types. For example, for an approval task type, the status may include approved and pending approval; for an ordinary task type, the status may include processed and pending processing, etc. No specific restrictions are made here.

[0071] The priority of a process node is used to indicate the execution order among multiple process nodes when there are multiple process nodes in the target process.

[0072] In some embodiments, the process application information may also include the name of the target process, the creation time of the target process, the creator information of the target process, a content summary of the process application information, attachment information of the process application information, the submission time of the process application information, the organization and its hierarchical structure corresponding to the creator information, the address of the data center or logical cluster associated with the process application information, etc., and no specific restrictions are made here.

[0073] For the target process with a process node of approval task type, it also includes the approval type of the target process, such as service application, expense reimbursement and other categories.

[0074] S202: If at least one process node includes an approval node, and the process application information includes information for indicating a task listener, a target approval strategy is determined in a pre-trained network model based on the process application information.

[0075] In some embodiments, the process node of the approval task type is called an approval node. When an approval node exists in the target process, it is determined whether a task listener is set for the approval node. If a task listener is set, the target approval strategy can be determined based on the task listener.

[0076] In some embodiments, the pre-trained network model may include a neural network model, a random forest model, a binary classification model, etc., without specific limitation here.

[0077] In some embodiments, the task listener is used to determine whether the approval node corresponding to the target process needs to determine the target approval policy.

[0078] In some embodiments, a plurality of approval strategies are preset, and a target approval strategy among the plurality of approval strategies is determined by using a network model pre-trained with process application information input values.

[0079] In some embodiments, if the approval node does not have a corresponding task listener, the preset approval account information is determined as the target approval account information; a workflow of the target process is constructed based on the process application information and the target approval account information. The preset approval account information may include all approval account information and may also include deployment approval account information.

[0080] S203. Determine target approval account information of the target process based on the target approval strategy. The target approval account information is information of an account that approves the target process at an approval node.

[0081] In some embodiments, for the same process application information, different approval strategies correspond to different screened Mubao approval account information. Therefore, the target approval account information can be determined through the target approval strategy. When the target application account information is determined, it can be determined that at the approval node, the workflow node of the approval node needs to be forwarded to the account corresponding to the target application account information for approval.

[0082] S204: Construct a workflow of the target process based on the process application information and the target approval account information.

[0083] In some embodiments, the process application information includes each process node and the priority of each process node, and determines the target approval account information of the approval node, so as to construct the workflow of the target process. In the approval node corresponding to the workflow of the target process, the workflow needs to be forwarded to the account corresponding to the target approval account information.

[0084] In an embodiment of the present application, after obtaining the process application information, whether the approval node needs to determine the target approval strategy is determined by whether there is a task listener on the approval node. When the approval strategy needs to be determined, the target approval strategy can be automatically determined by inputting the process application information into a pre-trained network model. This process does not require manual setting of approval personnel, and can automatically obtain the target approval strategy when the approval node needs the target approval strategy. Subsequently, the account information that the approval node needs to forward for approval can be automatically determined based on the target approval strategy. In this way, the target approval account information can be automatically matched based on the process application information to generate the corresponding workflow. This process does not require manual intervention, and the business process processing efficiency is high.

[0085] Figure 3 is a flowchart of a business process processing method shown in an exemplary embodiment, which is applied to Figure 1 The server 11 in Figure 3 As shown, a training method of a network model is proposed, and the method includes step S301 and step S303, which are described in detail as follows:

[0086] S301. Obtain historical process application information and historical approval strategies corresponding to the historical process application information.

[0087] In some embodiments, the historical approval policy is one of multiple approval policies.

[0088] It can be understood that the approval strategy is related to the approval behavior. Therefore, when determining the historical approval strategy of the historical process application information, the historical approval behavior data corresponding to the historical approval strategy is also determined as training data. The historical approval behavior data may include historical approval results, historical approval time, average approval time, approval success rate, etc., so as to increase the richness of the training data.

[0089] After obtaining the historical process application information, historical approval behavior data, and the historical approval strategy corresponding to the historical process application information, the historical process application information and the historical approval behavior data are used as input data to the network model to be trained, and the historical approval strategy is used as a training label to train the network model.

[0090] In some implementations, the historical process application information includes first historical process application information corresponding to a process including an approval node and second historical process application information corresponding to a process not including an approval node.

[0091] The first historical process application information and the second historical process application information are clustered to obtain at least one cluster set; the historical approval policy corresponding to the first historical process application information in each cluster set is determined as the historical approval policy of the second historical process application information in the corresponding cluster set.

[0092] The historical process application information obtained may include historical process application information for which no approval node exists. In this case, there is no corresponding historical approval strategy for the second historical process application information. Thus, the historical approval application information in the same clustering set can share the historical approval strategy of other historical approval application information of the same category through clustering.

[0093] The clustering processing method may include binary classification, classification by feature distance, etc., which is not specifically limited here.

[0094] In an embodiment of the present application, by clustering the first historical process application information including the approval node and the second historical process application information not including the approval node, the historical process application information combined with the same cluster shares a historical approval strategy, so that the second historical process application information not including the approval node also has a corresponding historical approval strategy, thereby increasing the volume of training data and obtaining a more accurate pre-trained network model.

[0095] S302: pre-process the historical process application information, and input the pre-processed historical process application information into the initial network model to determine the prediction approval strategy output by the initial network model.

[0096] In some embodiments, the historical process application information is preprocessed to obtain preprocessed historical process application information that can be recognized by the network model to be trained.

[0097] In some embodiments, historical process application information and historical approval behavior data are preprocessed to obtain preprocessed historical process application information that can be recognized by the network model to be trained.

[0098] In some implementations, a preprocessing method is proposed to perform data cleaning and standardization processing on historical process application information to determine standardized historical process application information; extract features from the standardized historical process application information, and perform feature enhancement processing on the extracted features to determine preprocessed historical process application information.

[0099] In some embodiments, data cleaning is performed on the historical process application information to remove noise and incomplete information, and then the data-cleaned historical process application information is standardized to ensure that features of different scales do not affect the performance of subsequent training models.

[0100] In other embodiments, in addition to data cleaning and standardization of historical process application information, other preprocessing may also be performed on the data, such as encoding categorical variables for the cleaned historical process application information, converting text information into numerical representation, and then standardizing the data processed with coded categorical variables to obtain standardized historical process application information.

[0101] After obtaining the standardized historical process application information, the features in the standardized historical process application information are extracted, and feature enhancement processing is performed on the extracted features. The feature enhancement processing can be for constructing new features to enhance the performance of the model, such as calculating the similarity between information of different approval accounts, predicting the time required for approval, etc., and no specific restrictions are made here.

[0102] In some embodiments, after feature enhancement processing, time series features can also be extracted from the features after feature enhancement processing, such as the submission time and approval cycle of historical process application information, and the features after feature enhancement processing are input into the network model to be trained for training according to certain time series characteristics.

[0103] In some embodiments, the network model to be trained is referred to as an initial network model, and the preprocessed historical process application information corresponding to each historical process application information is input into the initial network model to determine the predicted approval strategy output by the initial network model.

[0104] S303: Train the initial network model based on the historical approval strategy and the predicted approval strategy to determine the pre-trained network model.

[0105] In some embodiments, the predicted approval strategy and the historical approval strategy of the historical process application information are determined, and the initial network model can be trained through the historical approval strategy and the predicted approval strategy, that is, the parameters of the initial network model are adjusted so that the predicted approval strategy output by it is close to the historical approval strategy, until the initial network model converges, and the pre-trained network model can be obtained.

[0106] In some embodiments, taking the random forest model as the initial network model as an example, the hyperparameters of the initial network model during training are set as follows: the number of decision trees n_estimators = 100, the maximum depth max_depth = 10, the minimum number of sample splits min_samples_split = 2, and the minimum number of leaf node samples min_samples_leaf = 1.

[0107] The accuracy and generalization ability of the random forest model were evaluated using 5-fold cross validation, and the performance of the model was measured using indicators such as confusion matrix, precision, recall, and F1 score. The random forest model was trained using historical approval strategies and predicted approval strategies to determine the pre-trained network model.

[0108] The pre-trained network model is deployed to the production environment. When receiving the process application information of the target process, if there is an approval node and the approval node corresponds to a task listener, the target approval strategy corresponding to the process application information is determined based on the pre-trained network model.

[0109] In an embodiment of the present application, a training method for a pre-trained network model is proposed. By obtaining historical process application information and historical approval policies corresponding to the historical process application information, the historical process application information is pre-processed accordingly, so that the pre-trained network model is obtained through the pre-processed historical process application information and historical approval policy training. Subsequently, the target approval policy of the approval node can be directly determined through the pre-trained network model, and the forwarding of the approval node in the workflow can be achieved without manually selecting the approval policy or selecting the approver.

[0110] Figure 4 is a flowchart of a business process processing method shown in an exemplary embodiment, which is applied to Figure 1 The server 11 in Figure 4 As shown, a method for determining target approval account information of a target process based on a target approval strategy is proposed. The method includes steps S401 and S403. Figure 4 Can be implemented in Figure 2 Step S203 is described in detail as follows:

[0111] S401. Determine target indicators based on target approval strategies, where different approval strategies correspond to different indicators.

[0112] In some embodiments, the target approval policy corresponds to different target indicators. For example, if the target approval policy is an administrator forwarding policy, the target indicator is the administrator; if the target approval policy is a data center forwarding policy, the target indicator is the data center; if the target approval policy is an organization forwarding policy, the target indicator is the organization. No specific restrictions are made here.

[0113] S402. Determine the value corresponding to the target indicator in the process application information.

[0114] In some embodiments, for the target indicator, the value corresponding to the target indicator is determined. If the target indicator is an organization, the value corresponding to the target indicator is the value corresponding to the organization in the process application information. If the target indicator is a data center, the value corresponding to the target indicator is the value corresponding to the data center in the process application information.

[0115] S403: Match target approval account information in preset approval account information based on the value corresponding to the target indicator.

[0116] In some embodiments, there is preset approval account information, which includes attribute information of the corresponding approval account, and the attribute information includes a value corresponding to the target indicator. In this way, by matching the value corresponding to the target indicator determined in the process application information with the value corresponding to the target indicator in the preset approval account information, a successfully matched approval account information can be obtained, and the successfully matched approval account information is the target approval account information.

[0117] The matching process may be to screen the preset approval account information for approval account information whose target indicator value is the same as the value corresponding to the target indicator determined in the process application information.

[0118] In an embodiment of the present application, different indicators are set through different approval strategies, so that after the target indicator is determined, the approval account information that is the same as the process application information can be matched in the preset approval account information through the target indicator, and the matched approval account information is determined as the target approval account information, so that the approval account information that needs to be forwarded by the approval node can be obtained.

[0119] In some implementations, if at least one process node includes an approval node, and the process application information does not include information for indicating a task listener, the preset approval account information is determined as the target approval account information; and a workflow of the target process is constructed based on the process application information and the target approval account information.

[0120] In some embodiments, the task listener is used to determine the target approval policy through a pre-trained network model at the approval node. If there is no task listener and there is an approval node, then the approval account information corresponding to the approval node can be directly determined as the preset approval account information, that is, it is sent in full. In this way, the process forwarding of the approval node can be realized.

[0121] In the embodiment of the present application, when there is no task listener, the preset approval account information is used to determine the target approval account information, so that the information of the account that the approval node needs to forward can be obtained.

[0122] In some embodiments, when the approval node corresponding to the workflow is executed, the account corresponding to the target approval account information can receive the six points of the process and perform node and approval operations.

[0123] In some embodiments, after the workload corresponding to the target process is completed, it can be determined based on a preset execution listener whether the target process has a next-level workflow that needs to flow. If so, the next-level process is triggered to start after the corresponding workflow of the target process ends.

[0124] In some embodiments, a corresponding task end event may be set for the target process. When the execution listener listens to the task end event, it may be determined whether there is a next-level workflow that needs to be transferred.

[0125] In other embodiments, other network models may be set up to predict whether the target process has a next-level workflow that needs to flow, and to predict the process application information of the next-level workflow.

[0126] A business process processing method is proposed in the embodiment of the present application. Through a pre-trained network model, the target approval strategy can be automatically determined, and the target approval account information can be determined, thereby reducing manual intervention. The method intelligently matches the appropriate target approval account information, shortens the approval cycle, and improves overall work efficiency. It can also be adaptively adjusted according to different business scenarios and is suitable for various types of approval processes. The processing-related data of the approval node are all traceable, which is convenient for subsequent auditing and analysis.

[0127] Figure 5 : is a structural diagram of a business process processing device shown in an exemplary embodiment. The business process processing device 500 may include:

[0128] An information acquisition module 510 is used to acquire process application information of a target process, where the process application information is used to indicate at least one process node of the target process;

[0129] An approval strategy determination module 530 is configured to determine a target approval strategy in a pre-trained network model based on the process application information if at least one process node includes an approval node and the process application information includes information for indicating a task listener;

[0130] An approval account determination module 550 is used to determine target approval account information of a target process based on a target approval policy, where the target approval account information is information of an account that approves the target process at an approval node;

[0131] The workflow creation module 570 is used to construct a workflow of a target process based on the process application information and the target approval account information.

[0132] In one possible implementation, the business process processing device further includes:

[0133] A training data acquisition module is used to acquire historical process application information and historical approval strategies corresponding to the historical process application information. The process corresponding to the historical process application information includes approval nodes.

[0134] A preprocessing module, used to preprocess the historical process application information, and input the preprocessed historical process application information into the initial network model to determine the prediction approval strategy output by the initial network model;

[0135] The training is based on the historical approval strategy and the predicted approval strategy to train the initial network model and determine the pre-trained network model.

[0136] In an implementable manner, the historical process application information includes first historical process application information corresponding to a process including an approval node and second historical process application information corresponding to a process not including an approval node; the training data acquisition module includes:

[0137] A clustering unit, configured to cluster the first historical process application information and the second historical process application information to obtain at least one cluster set;

[0138] The strategy clustering unit is used to determine the historical approval strategy corresponding to the first historical process application information in each cluster set as the historical approval strategy for the second historical process application information in the corresponding cluster set.

[0139] In one possible implementation, the preprocessing module includes:

[0140] A data preprocessing unit, used for performing data cleaning and standardization processing on the historical process application information to determine the standardized historical process application information;

[0141] The feature preprocessing unit is used to extract features from the standardized historical process application information and perform feature enhancement processing on the extracted features to determine the preprocessed historical process application information.

[0142] In one possible implementation, the approval account determination module includes:

[0143] An indicator determination unit is used to determine the target indicator based on the target approval strategy. Different approval strategies correspond to different indicators.

[0144] A value acquisition unit, used to determine the value corresponding to the target indicator in the process application information;

[0145] The approval account determination unit is used to match the target approval account information in the preset approval account information based on the value corresponding to the target indicator.

[0146] In one possible implementation, the device further includes:

[0147] A full approval account determination module, used for determining preset approval account information as target approval account information if at least one process node includes an approval node and the process application information does not include information for indicating a task listener;

[0148] The workload generation module is used to build the workflow of the target process based on the process application information and the target approval account information.

[0149] The business process processing device provided in this embodiment can be used to execute the above-mentioned business process processing method. Its implementation principle and technical effects are similar, and this embodiment will not be repeated here.

[0150] Figure 6 is a block diagram of an electronic device shown in an exemplary embodiment, see Figure 6 The electronic device 600 may include: a processor 61 and a memory 62, wherein the processor 61 and the memory 62 can communicate; illustratively, the processor 61 and the memory 62 communicate via a communication bus 63, the memory 62 is used to store computer execution instructions, and the processor 61 is used to call the computer execution instructions in the memory to execute the business process processing method shown in any of the above method embodiments.

[0151] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the present application may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0152] The present application provides a computer-readable storage medium, on which computer-executable instructions are stored; when the computer-executable instructions are executed by a processor, they are used to implement a business process processing method as described in any of the above embodiments.

[0153] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the business process processing method of the above-mentioned distributed system is implemented.

[0154] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0155] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0156] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0157] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0158] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. If not specifically stated, the processor may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. If not specifically stated, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc.

[0159] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0160] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0161] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0162] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A business process processing method, characterized in that: include: Acquire process application information of a target process, where the process application information is used to indicate at least one process node of the target process; If the at least one process node includes an approval node, and the process application information includes information for indicating a task listener, determining a target approval strategy in a pre-trained network model based on the process application information; Determine target approval account information of the target process based on the target approval policy, where the target approval account information is information of an account that approves the target process at the approval node; A workflow of the target process is constructed based on the process application information and the target approval account information.

2. The method according to claim 1, characterized in that Before determining the target approval strategy in the pre-trained network model based on the process application information, the method further includes: Obtaining historical process application information and historical approval strategies corresponding to the historical process application information; Preprocessing the historical process application information, and inputting the preprocessed historical process application information into the initial network model to determine the predicted approval strategy output by the initial network model; The initial network model is trained based on the historical approval strategy and the predicted approval strategy to determine the pre-trained network model.

3. The method according to claim 2, characterized in that The historical process application information includes first historical process application information corresponding to a process including an approval node and second historical process application information corresponding to a process not including an approval node; The obtaining of historical process application information and historical approval strategies corresponding to the historical process application information includes: Clustering the first historical process application information and the second historical process application information to obtain at least one cluster set; The historical approval strategy corresponding to the first historical process application information in each cluster set is determined as the historical approval strategy corresponding to the second historical process application information in the cluster set.

4. The method according to claim 2, characterized in that: The preprocessing of the historical process application information includes: Performing data cleaning and standardization processing on the historical process application information to determine standardized historical process application information; Features in the standardized historical process application information are extracted, and feature enhancement processing is performed on the extracted features to determine pre-processed historical process application information.

5. The method according to claim 1, characterized in that The determining the target approval account information of the target process based on the target approval policy includes: Determine the target indicator based on the target approval strategy, where different approval strategies correspond to different indicators; Determining a value corresponding to the target indicator in the process application information; Based on the value corresponding to the target indicator, the target approval account information is matched in the preset approval account information.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: If the at least one process node includes an approval node, and the process application information does not include information for indicating a task listener, determining the preset approval account information as the target approval account information; A workflow of the target process is constructed based on the process application information and the target approval account information.

7. A business process processing device, characterized in that: include: An information acquisition module, used to acquire process application information of a target process, wherein the process application information is used to indicate at least one process node of the target process; an approval strategy determination module, configured to determine a target approval strategy in a pre-trained network model based on the process application information if the at least one process node includes an approval node and the process application information includes information for indicating a task listener; An approval account determination module, used to determine target approval account information of the target process based on the target approval policy, wherein the target approval account information is information of an account that approves the target process at the approval node; A workflow creation module is used to construct a workflow of the target process based on the process application information and the target approval account information.

8. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.

Images