Flow processing method, device and equipment, readable storage medium and program product
By introducing a target process node identification model based on data training based on multiple business process rules in process processing, the problems of poor process processing flexibility and low modification efficiency in the prior art are solved, and higher process processing flexibility and faster response to process changes are achieved.
Patent Information
- Application Number
- CN202411661974.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-20
- Publication Date
- 2025-03-07
AI Technical Summary
In the prior art, process processing methods have poor processing flexibility, and when business processes change, program codes need to be manually modified, resulting in low modification efficiency.
By introducing a target process node identification model in the business process, the model is trained based on the process rule data of multiple business processes, and the next process node corresponding to the process data can be identified, thereby improving the flexibility of process processing and quickly responding to process changes through model fine-tuning.
Improves the flexibility of business process processing, reduces the need for manual code modification when process changes, and improves modification efficiency.
Smart Images
Figure CN119579104A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a process processing method, device, equipment, readable storage medium and program product. Background Art
[0002] When an enterprise conducts business activities, the information generated needs to go through multiple undertakers to complete. With the development of office automation, enterprises usually use relevant business systems to process the information generated in different business project processes.
[0003] In the related art, developers usually write program codes related to each business process, and in the process of processing the business process, the processing logic of the business process is implemented based on the program code of the business process.
[0004] However, the above process processing method has the problem of poor processing flexibility. Summary of the invention
[0005] Based on this, it is necessary to provide a process processing method, device, equipment, readable storage medium and program product that can improve processing flexibility in response to the above technical problems.
[0006] In a first aspect, the present application provides a process processing method, comprising:
[0007] Acquire process data corresponding to the target business process based on the first process node;
[0008] Determine a second process node corresponding to the process data according to the process data and a target process node identification model, wherein the target process node identification model is obtained by training according to process rule data corresponding to each business process, and each business process includes the target business process;
[0009] The process data is processed through the second process node.
[0010] In one embodiment, determining the second process node corresponding to the process data according to the process data and the target process node identification model includes:
[0011] Performing data preprocessing on the process data to obtain preprocessed process data, the process data including a process identifier, a first node identifier of a first process node, and a process file, the data preprocessing at least including data desensitization processing;
[0012] The preprocessed process data is input into a target process node identification model to obtain a second node identifier of a second process node.
[0013] In one embodiment, before determining the second process node corresponding to the process data according to the process data and the target process node identification model, the method further includes:
[0014] comparing the first node identifier with a reference node identifier corresponding to the process data;
[0015] Determining a second process node corresponding to the process data according to the process data and the target process node identification model includes:
[0016] If the first node identifier is consistent with the reference node identifier, the second process node is determined according to the process data and the target process node identification model.
[0017] In one embodiment, processing the process data by the second process node includes:
[0018] Establishing a communication connection with a node device corresponding to a second process node according to the second node identifier;
[0019] The process file included in the process data is sent to the node device, and the process file is used by the node device to process the process file.
[0020] In one embodiment, the method further comprises:
[0021] Acquire each process rule data, and generate multiple training data according to each process rule data, the training data including sample process data and sample node identifiers of sample second process nodes corresponding to the sample process data;
[0022] The initial process node recognition model is trained according to each training data to obtain the target process node recognition model.
[0023] In one embodiment, the method further comprises:
[0024] When there is an update to the target business process, obtain the update process rule data corresponding to the target business process, and generate update training data according to the update process rule data;
[0025] Fine-tune the model parameters of the target process node recognition model according to the updated training number.
[0026] In a second aspect, the present application also provides a process processing device, including:
[0027] An acquisition module, used for acquiring process data based on the first process node;
[0028] An identification module, used to determine a second process node corresponding to the process data according to the process data and a target process node identification model, wherein the target process node identification model is a model trained according to process rule data corresponding to the process data;
[0029] The processing module is used to process the process data through the second process node.
[0030] In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method of the first aspect when executing the computer program.
[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method of the first aspect described above.
[0032] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method in the first aspect are implemented.
[0033] The above-mentioned process processing method, device, equipment, readable storage medium and program product obtain the process data corresponding to the target business process based on the first process node, and determine the second process node corresponding to the process data according to the process data and the target process node identification model, so that the process data can be processed through the second process node, wherein the target process node identification model is obtained by training according to the process rule data corresponding to each business process, and each business process includes the target business process. In this way, by adding a target process node identification model that can identify the next second process node corresponding to the process data to the business process, the target process node identification model is obtained by training the process rule data corresponding to multiple business processes, thereby avoiding the problem of poor process processing flexibility in the traditional technology of determining the next process node based on the program code. The technical solution provided by the present application identifies the second process node corresponding to the process data through the target process node identification model, and the flexibility of business process processing is higher. In addition, when the target business process needs to be modified later, it is only necessary to fine-tune the target process node identification model according to the process rule data corresponding to the target business process, thereby avoiding the problem of low modification efficiency in the traditional technology of manually modifying the entire program code. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0035] Figure 1An application environment diagram of a process processing method in an embodiment;
[0036] Figure 2 A schematic diagram of a process flow diagram of a process processing method in an embodiment;
[0037] Figure 3 is a flow chart of step 202 in another embodiment;
[0038] Figure 4 A flowchart of an exemplary process processing method in another embodiment;
[0039] Figure 5 is a structural block diagram of a process processing device in an embodiment;
[0040] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0042] When an enterprise conducts business activities, the information generated needs to go through multiple undertakers to complete. With the development of office automation, enterprises usually use relevant business systems to process the information generated in different business project processes, such as office automation systems. This system is a new office system that applies modern technologies such as computers and communications to traditional office methods.
[0043] In the related art, developers usually write program codes related to each business process, and in the process of processing the business process, the processing logic of the business process is implemented based on the program code of the business process.
[0044] However, when the business process is processed based on the program code, the processing flexibility is poor. If there is a change in the business process, the entire program code needs to be manually modified, which makes the modification inefficient.
[0045] In view of this, the present application provides a process processing method, device, equipment, readable storage medium and program product, which obtains process data corresponding to the target business process based on the first process node, and determines the second process node corresponding to the process data according to the process data and the target process node identification model, so that the process data can be processed through the second process node, wherein the target process node identification model is obtained by training according to the process rule data corresponding to each business process, and each business process includes the target business process. In this way, by adding a target process node identification model that can identify the next second process node corresponding to the process data to the business process, the target process node identification model is obtained by training the process rule data corresponding to multiple business processes, thereby avoiding the problem of poor process processing flexibility in the traditional technology of determining the next process node based on the program code. The technical solution provided by the present application identifies the second process node corresponding to the process data through the target process node identification model, and the flexibility of business process processing is higher. In addition, when the target business process needs to be modified later, it is only necessary to fine-tune the target process node identification model according to the process rule data corresponding to the target business process, thereby avoiding the problem of low modification efficiency in the traditional technology of manually modifying the entire program code.
[0046] The process processing method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the data storage system can store the data that the server 101 needs to process, and the server 101 can communicate with multiple node devices 102, and the business processes corresponding to each node device 102 are different. The data storage system can be integrated on the server 101, or it can be placed on the cloud or other network servers. The server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.
[0047] In an exemplary embodiment, Figure 2 As shown, a process processing method is provided, which is applied to Figure 1 The server 101 in the example is used as an example to illustrate, including the following steps 201 to 203. Among them:
[0048] Step 201: Acquire process data corresponding to a target business process based on a first process node.
[0049] When an enterprise is conducting a certain business, the business may correspond to multiple business processes. For example, when the business is software development, the business process may include the product manager submitting requirement documents to the R&D manager, the R&D manager submitting design documents to each developer, and each developer submitting coding files to the tester, etc.
[0050] In an embodiment of the present application, the first process node may be the initiation node of the corresponding target business process. For example, the business process is for a product manager to submit a requirement document to a R&D manager, and the first process node is the node corresponding to the product manager.
[0051] Process data may be data generated when the target business process is in progress. For example, when the business process is for a product manager to submit a requirement document to a R&D manager, the process data may include the process identifier corresponding to the target business process, the first node identifier corresponding to the first process node (i.e., the identifier corresponding to the product manager), the process document (i.e., the requirement document), etc.
[0052] Optionally, the server may directly obtain the process data input by the user according to the node device corresponding to the first process node; optionally, the server may obtain previously archived unprocessed process data from the process database.
[0053] Step 202 : determining a second process node corresponding to the process data according to the process data and the target process node identification model.
[0054] In an embodiment of the present application, the second process node may be the end node of the target business process. For example, the business process is for a product manager to submit a requirement document to a R&D manager, and the first process node is the node corresponding to the R&D manager.
[0055] Optionally, the server can directly input the process data into the target process node identification model to obtain the second process node output by the target process node identification model; optionally, the server can perform data preprocessing on the process data according to the requirements of the target process node identification model for input data. The data preprocessing can include data desensitization processing, data standardization processing, etc. Then, the server can input the preprocessed process data into the target process node identification model to obtain the second process node output by the target process node identification model.
[0056] In an embodiment of the present application, the target process node identification model may be obtained by training based on process rule data corresponding to each business process, and each business process includes a target business process.
[0057] The basic model of the target process node recognition model can be a neural network model or a generative artificial intelligence model with a context memory module.
[0058] Regarding the process of target process node identification model, in one possible implementation, the server can obtain each process rule data and generate multiple training data based on each process rule data. In this way, the initial process node identification model can be trained according to each training data to obtain the target process node identification model, wherein the training data includes sample process data and the sample node identifier of the sample second process node corresponding to the sample process data.
[0059] In an embodiment of the present application, the process rule data may be in text form, or may be data that has been digitized. Based on the process rule data, the server may generate a plurality of training data for training a target process node recognition model.
[0060] Taking the business process of a product manager submitting a requirement document to a R&D manager (i.e., the requirement submission process) as an example, the corresponding process rule data may be "Product Manager A completes the requirement specification "Requirement Specification" and submits it to R&D Manager B for requirement analysis". The training data includes the sample process data such as "Work Order Number: abc (randomly generated). Process: Requirement Submission Process, Process File: "A Project Requirement Specification", First Process Node: Product Manager A", and the sample node identifier of the sample second process node corresponding to the sample process data is "R&D Manager B".
[0061] The server can train the initial process node recognition model based on multiple training data until the model meets the preset convergence conditions, and then obtain the target process node recognition model.
[0062] In one possible implementation, when the target business process is updated, the server can adjust the target process node identification model by fine-tuning the model parameters, thereby avoiding the problem of low adjustment efficiency in traditional technologies that require manual modification of program codes.
[0063] In an embodiment of the present application, when there is an update to the target business process, the server can obtain the updated process rule data corresponding to the target business process, and generate updated training data based on the updated process rule data. In this way, the model parameters of the target process node identification model can be fine-tuned according to the updated training data.
[0064] Step 203: Process the process data through the second process node.
[0065] After determining the second process node, the server can process the process data through the second process node. Optionally, the server can determine the account information corresponding to the second process node based on the second process node, and send the current process data to the account corresponding to the second process node; optionally, the server can determine the node device corresponding to the second process node based on the second process node, and send the current process data to the node device corresponding to the second process node.
[0066] In the above embodiment, a target process node identification model that can identify the next second process node corresponding to the process data is added to the business process. The target process node identification model is obtained by training the process rule data corresponding to multiple business processes, thereby avoiding the problem of poor process processing flexibility in the traditional technology of determining the next process node based on the program code. The technical solution provided in the present application identifies the second process node corresponding to the process data through the target process node identification model, and the business process processing flexibility is higher. In addition, when the target business process needs to be modified subsequently, it is only necessary to fine-tune the target process node identification model according to the process rule data corresponding to the target business process, thereby avoiding the problem of low modification efficiency in the traditional technology that requires manual modification of the entire program code.
[0067] In one embodiment, based on the above Figure 2 The embodiment shown, see Figure 3 This embodiment relates to a process of determining a second process node corresponding to the process data according to the process data and the target process node identification model. Figure 3 As shown, step 202 may include step 301 and step 302 .
[0068] Step 301 , preprocessing the process data to obtain preprocessed process data.
[0069] Among them, data preprocessing at least includes data desensitization processing.
[0070] Step 302: input the preprocessed process data into a target process node identification model to obtain a second node identifier of a second process node.
[0071] In an embodiment of the present application, the process data may include a process identifier, a first node identifier of a first process node, and a process file. In some cases, the target process node identification model may be a generative artificial intelligence model. In order to avoid leakage of sensitive information, the server may perform data desensitization on the process data. For example, the file name of the process file and the name of the person corresponding to the first process node may be desensitized in the form of a digital signature. That is, different identifiers are assigned to sensitive information, and a desensitized mapping relationship is established and stored between each sensitive information and its corresponding desensitized information.
[0072] After the server preprocesses the process data, the preprocessed process data can be obtained. The preprocessed process data may include a process identifier, a first node identifier after desensitization processing, a desensitized process file, and the like.
[0073] The process data obtained after data preprocessing is input into the target process node identification model, and the server can obtain the second node identifier output by the target process node identification model that can uniquely identify the second process node.
[0074] In a possible implementation, in order to facilitate subsequent management of the process data, the server may archive the process data, the process data after data preprocessing, and the second node identifier output by the target process node identification model in a database.
[0075] Based on the above embodiments, in order to make the process processing more secure, before determining the second process node corresponding to the process data according to the process data and the target process node identification model, the server may also compare the first node identifier with the reference node identifier corresponding to the process data. In this way, determining the second process node corresponding to the process data according to the process data and the target process node identification model may include: if the first node identifier is consistent with the reference node identifier, determining the second process node according to the process data and the target process node identification model.
[0076] In an embodiment of the present application, the first process node for submitting process data may be different from the reference process node corresponding to the process data. For example, the business process is for a product manager to submit a requirement document to a R&D manager. The reference process node may be the product manager, while the first process node for submitting process data may or may not be the product manager. In order to ensure the correctness of the process processing, the server needs to restrict the permissions of the first process node, that is, compare the first node identifier with the reference node identifier corresponding to the process data. Optionally, if the first node identifier is consistent with the reference node identifier, the server may execute subsequent process processing; optionally, if the first node identifier is inconsistent with the reference node identifier, the server may output a permission error message.
[0077] Based on the above embodiment, the process of the server processing the process data through the second process node may include: the server establishes a communication connection with the node device corresponding to the second process node according to the second node identifier, and then sends the process file included in the process data to the node device, and the process file is used by the node device to process the process file.
[0078] Since different node identifiers can correspond to different node devices, the server can establish a communication connection with the node device corresponding to the second process node according to a preset communication protocol, and then send the process file included in the process data to the node device, and the process file is used by the node device to process the process file.
[0079] Regarding the process of node devices processing flow files, in a possible implementation, since the flow files are processed by data desensitization, the node device can determine the original flow files from the database according to the above-mentioned desensitization mapping relationship, and then process the original flow files.
[0080] In one embodiment, referring to Figure 4 , provides an exemplary process processing method that can be applied to Figure 1 In the implementation environment shown.
[0081] Step 401 , obtaining each process rule data, and generating a plurality of training data according to each process rule data.
[0082] The training data includes sample process data and sample node identifiers of sample second process nodes corresponding to the sample process data.
[0083] Step 402: train an initial process node recognition model according to each training data to obtain a target process node recognition model.
[0084] Step 403: Acquire process data corresponding to the target business process based on the first process node.
[0085] Step 404: compare the first node identifier with a reference node identifier corresponding to the process data.
[0086] Step 405: If the first node identifier is consistent with the reference node identifier, preprocess the process data to obtain preprocessed process data.
[0087] The process data includes a process identifier, a first node identifier of a first process node, and a process file, and data preprocessing includes at least data desensitization processing.
[0088] Step 406 , input the preprocessed process data into the target process node identification model to obtain a second node identifier of a second process node.
[0089] The target process node identification model is obtained by training according to process rule data corresponding to each business process, and each business process includes the target business process.
[0090] Step 407: Establish a communication connection with a node device corresponding to the second process node according to the second node identifier.
[0091] Step 408: Send the process file included in the process data to the node device.
[0092] The process file is used by the node device to process the process file.
[0093] Step 409 , when there is an update to the target business process, obtain update process rule data corresponding to the target business process, and generate update training data according to the update process rule data.
[0094] Step 410 , fine-tuning the model parameters of the target process node recognition model according to the updated training number.
[0095] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these 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 part of the steps or stages in other steps.
[0096] Based on the same inventive concept, the embodiment of the present application also provides a process processing device for implementing the process processing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more process processing device embodiments provided below can refer to the limitations on the process processing method above, and will not be repeated here.
[0097] In an exemplary embodiment, Figure 5 As shown, a process processing device is provided, including: an acquisition module 501, an identification module 502 and a processing module 503, wherein:
[0098] An acquisition module 501 is used to acquire process data based on a first process node;
[0099] An identification module 502, configured to determine a second process node corresponding to the process data according to the process data and a target process node identification model, wherein the target process node identification model is a model trained according to process rule data corresponding to the process data;
[0100] The processing module 503 is used to process the process data through the second process node.
[0101] In one embodiment, the identification module 502 includes:
[0102] A preprocessing unit, configured to perform data preprocessing on the process data to obtain preprocessed process data, wherein the process data includes a process identifier, a first node identifier of the first process node, and a process file, and the data preprocessing includes at least data desensitization processing;
[0103] The identification unit is used to input the preprocessed process data into the target process node identification model to obtain a second node identification of the second process node.
[0104] In one embodiment, the apparatus further comprises:
[0105] an authority comparison module, configured to compare the first node identifier with a reference node identifier corresponding to the process data;
[0106] The identification module 502 includes:
[0107] The authority compliance unit is used to determine the second process node according to the process data and the target process node identification model if the first node identifier is consistent with the reference node identifier.
[0108] In one embodiment, the processing module 503 includes:
[0109] a communication unit, configured to establish a communication connection with a node device corresponding to the second process node according to the second node identifier;
[0110] The sending unit is used to send the process file included in the process data to the node device, and the process file is used for the node device to process the process file.
[0111] In one embodiment, the apparatus further comprises:
[0112] A rule acquisition module, used to acquire each of the process rule data, and generate a plurality of training data according to each of the process rule data, wherein the training data includes sample process data and a sample node identifier of a sample second process node corresponding to the sample process data;
[0113] The training module is used to train the initial process node recognition model according to each of the training data to obtain the target process node recognition model.
[0114] In one embodiment, the apparatus further comprises:
[0115] A sample generation module is used to obtain update process rule data corresponding to the target business process when there is an update in the target business process, and generate update training data according to the update process rule data;
[0116] A fine-tuning module is used to perform model parameter fine-tuning processing on the target process node recognition model according to the updated training number.
[0117] Each module in the above-mentioned process processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.
[0118] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store process processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a process processing method is implemented.
[0119] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0120] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0121] Acquire process data corresponding to the target business process based on the first process node;
[0122] Determine a second process node corresponding to the process data according to the process data and a target process node identification model, wherein the target process node identification model is obtained by training according to process rule data corresponding to each business process, and each business process includes the target business process;
[0123] The process data is processed by the second process node.
[0124] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0125] Performing data preprocessing on the process data to obtain preprocessed process data, the process data including a process identifier, a first node identifier of the first process node, and a process file, the data preprocessing at least including data desensitization processing;
[0126] The preprocessed process data is input into the target process node identification model to obtain a second node identifier of the second process node.
[0127] In one embodiment, before determining the second process node corresponding to the process data according to the process data and the target process node identification model, the processor further implements the following steps when executing the computer program:
[0128] comparing the first node identifier with a reference node identifier corresponding to the process data;
[0129] The determining, according to the process data and the target process node identification model, a second process node corresponding to the process data includes:
[0130] If the first node identifier is consistent with the reference node identifier, the second process node is determined according to the process data and the target process node identification model.
[0131] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0132] Establishing a communication connection with a node device corresponding to the second process node according to the second node identifier;
[0133] The process file included in the process data is sent to the node device, and the process file is used by the node device to process the process file.
[0134] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0135] Acquire each of the process rule data, and generate a plurality of training data according to each of the process rule data, wherein the training data includes sample process data and a sample node identifier of a sample second process node corresponding to the sample process data;
[0136] An initial process node recognition model is trained according to each of the training data to obtain the target process node recognition model.
[0137] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0138] When there is an update to the target business process, obtaining update process rule data corresponding to the target business process, and generating update training data according to the update process rule data;
[0139] The target process node recognition model is fine-tuned according to the updated training number.
[0140] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0141] Acquire process data corresponding to the target business process based on the first process node;
[0142] Determine a second process node corresponding to the process data according to the process data and a target process node identification model, wherein the target process node identification model is obtained by training according to process rule data corresponding to each business process, and each business process includes the target business process;
[0143] The process data is processed by the second process node.
[0144] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0145] Performing data preprocessing on the process data to obtain preprocessed process data, the process data including a process identifier, a first node identifier of the first process node, and a process file, the data preprocessing at least including data desensitization processing;
[0146] The preprocessed process data is input into the target process node identification model to obtain a second node identifier of the second process node.
[0147] In one embodiment, before determining the second process node corresponding to the process data according to the process data and the target process node identification model, the computer program further implements the following steps when executed by the processor:
[0148] comparing the first node identifier with a reference node identifier corresponding to the process data;
[0149] The determining, according to the process data and the target process node identification model, a second process node corresponding to the process data includes:
[0150] If the first node identifier is consistent with the reference node identifier, the second process node is determined according to the process data and the target process node identification model.
[0151] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0152] Establishing a communication connection with a node device corresponding to the second process node according to the second node identifier;
[0153] The process file included in the process data is sent to the node device, and the process file is used by the node device to process the process file.
[0154] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0155] Acquire each of the process rule data, and generate a plurality of training data according to each of the process rule data, wherein the training data includes sample process data and a sample node identifier of a sample second process node corresponding to the sample process data;
[0156] An initial process node recognition model is trained according to each of the training data to obtain the target process node recognition model.
[0157] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0158] When there is an update to the target business process, obtaining update process rule data corresponding to the target business process, and generating update training data according to the update process rule data;
[0159] The target process node recognition model is fine-tuned according to the updated training number.
[0160] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:
[0161] Acquire process data corresponding to the target business process based on the first process node;
[0162] Determine a second process node corresponding to the process data according to the process data and a target process node identification model, wherein the target process node identification model is obtained by training according to process rule data corresponding to each business process, and each business process includes the target business process;
[0163] The process data is processed by the second process node.
[0164] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0165] Performing data preprocessing on the process data to obtain preprocessed process data, the process data including a process identifier, a first node identifier of the first process node, and a process file, the data preprocessing at least including data desensitization processing;
[0166] The preprocessed process data is input into the target process node identification model to obtain a second node identifier of the second process node.
[0167] In one embodiment, before determining the second process node corresponding to the process data according to the process data and the target process node identification model, the computer program further implements the following steps when executed by the processor:
[0168] comparing the first node identifier with a reference node identifier corresponding to the process data;
[0169] The determining, according to the process data and the target process node identification model, a second process node corresponding to the process data includes:
[0170] If the first node identifier is consistent with the reference node identifier, the second process node is determined according to the process data and the target process node identification model.
[0171] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0172] Establishing a communication connection with a node device corresponding to the second process node according to the second node identifier;
[0173] The process file included in the process data is sent to the node device, and the process file is used by the node device to process the process file.
[0174] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0175] Acquire each of the process rule data, and generate a plurality of training data according to each of the process rule data, wherein the training data includes sample process data and a sample node identifier of a sample second process node corresponding to the sample process data;
[0176] An initial process node recognition model is trained according to each of the training data to obtain the target process node recognition model.
[0177] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0178] When there is an update to the target business process, obtaining update process rule data corresponding to the target business process, and generating update training data according to the update process rule data;
[0179] The target process node recognition model is fine-tuned according to the updated training number.
[0180] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0181] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0182] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are 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 application.
[0183] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A process processing method, characterized in that: The method comprises: Acquire process data corresponding to the target business process based on the first process node; Determine a second process node corresponding to the process data according to the process data and a target process node identification model, wherein the target process node identification model is obtained by training according to process rule data corresponding to each business process, and each business process includes the target business process; The process data is processed by the second process node.
2. The method according to claim 1, characterized in that The determining, according to the process data and the target process node identification model, a second process node corresponding to the process data includes: Performing data preprocessing on the process data to obtain preprocessed process data, the process data including a process identifier, a first node identifier of the first process node, and a process file, the data preprocessing at least including data desensitization processing; The preprocessed process data is input into the target process node identification model to obtain a second node identifier of the second process node.
3. The method according to claim 2, characterized in that Before determining the second process node corresponding to the process data according to the process data and the target process node identification model, the method further includes: comparing the first node identifier with a reference node identifier corresponding to the process data; The determining, according to the process data and the target process node identification model, a second process node corresponding to the process data includes: If the first node identifier is consistent with the reference node identifier, the second process node is determined according to the process data and the target process node identification model.
4. The method according to claim 2, characterized in that: The processing of the process data by the second process node includes: Establishing a communication connection with a node device corresponding to the second process node according to the second node identifier; The process file included in the process data is sent to the node device, and the process file is used by the node device to process the process file.
5. The method according to claim 1, characterized in that: The method further comprises: Acquire each of the process rule data, and generate a plurality of training data according to each of the process rule data, wherein the training data includes sample process data and a sample node identifier of a sample second process node corresponding to the sample process data; An initial process node recognition model is trained according to each of the training data to obtain the target process node recognition model.
6. The method according to claim 5, characterized in that The method further comprises: When there is an update to the target business process, obtaining update process rule data corresponding to the target business process, and generating update training data according to the update process rule data; The target process node recognition model is fine-tuned according to the updated training number.
7. A process processing device, characterized in that: The device comprises: An acquisition module, used for acquiring process data based on the first process node; an identification module, configured to determine a second process node corresponding to the process data according to the process data and a target process node identification model, wherein the target process node identification model is a model trained according to process rule data corresponding to the process data; A processing module is used to process the process data through the second process node.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.