Method and apparatus for determining operation flow, and electronic device

Abstract

The method and device for determining an operation process, and the electronic device provided by the present disclosure perform data decision processing on acquired real-time operation data to obtain a plurality of first recommended data; perform data marking processing on the first recommended data according to the real-time operation data and a preset operation database to obtain first target data; perform data decision processing on acquired second operation data to obtain a plurality of second recommended data; perform data marking processing on the second recommended data according to the second operation data and the preset operation database to obtain second target data, and until a response operation completion instruction is received, the determination of the operation process is ended. Compared with related technologies, the embodiments of the present disclosure can quickly identify the current processing step when processing a system process, determine the best next operation step and operation sequence, make the system operation process in an enterprise more flexible, and improve the efficiency and accuracy when processing a relatively complex operation system process.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, and particularly relates to a method and device for determining an operation process, and an electronic device. BACKGROUND

[0002] With the continuous expansion of the scale of enterprises, the system operation process in enterprises is increasingly complex, and operation personnel need to master a large number of operation steps and sequences to ensure that the business proceeds smoothly. The system operation process in enterprises mainly includes the following points:

[0003] Process design: using process design tools, such as business process management (BPM) systems, to define and configure system operation processes, process design is usually based on business rules and the experience of operation personnel to customize. Process execution: operation personnel execute tasks on the operation system according to the pre-designed process steps, and in the execution of tasks, operation personnel must strictly follow the pre-designed process steps to complete the work. Process monitoring: real-time tracking of process execution through process monitoring tools to ensure that the business proceeds according to the established process, and to facilitate management to evaluate the efficiency of the process.

[0004] However, the existing system operation process in enterprises mainly relies on pre-set process steps, resulting in a relatively fixed system operation process in enterprises, and when dealing with more complex operation system processes, the accuracy and efficiency are relatively low. SUMMARY

[0005] The present disclosure provides a method and device for determining an operation process, and an electronic device. The main purpose is to solve the problem that the existing operation system process in enterprises mainly relies on pre-set process steps, resulting in a relatively fixed operation system process in enterprises, and when dealing with more complex operation system processes, the accuracy and efficiency are relatively low.

[0006] According to a first aspect of the present disclosure, a method for determining an operation process is provided, which comprises:

[0007] According to the obtained real-time operation data, data decision processing is performed to obtain a plurality of first recommended data; wherein the first recommended data is the next operation data adjacent to the real-time operation data in the operation path containing the real-time operation data;

[0008] According to the real-time operation data and a preset operation database, data marking processing is performed on the plurality of first recommended data to obtain first target data; wherein the preset operation database comprises a plurality of first operation paths, the first operation path is a target operation path corresponding to each operation scenario obtained by reinforcement learning, and the first target data is determined by the first operation path;

[0009] According to the obtained second operation data, data decision processing is performed to obtain a plurality of second recommended data; wherein the second operation data is the next operation data obtained after obtaining the real-time operation data, and the second recommended data is the next operation data adjacent to the second operation data in the operation path containing the second operation data;

[0010] According to the second operation data and the preset operation database, data marking processing is performed on the plurality of second recommended data to obtain second target data, until a response operation completion instruction is received to end the determination of the operation process, wherein the second target data is determined through the first operation path.

[0011] Optionally, before the data decision processing is performed according to the obtained real-time operation data to obtain a plurality of first recommended data, the method further comprises:

[0012] Obtaining historical operation data and operation success data corresponding to each operation scenario; wherein the operation success data is operation data that can successfully execute the corresponding operation scenario;

[0013] According to the historical operation data and the operation success data, path recognition processing is performed through a reinforcement learning algorithm to obtain the first operation path corresponding to each operation scenario, and data set construction processing is performed according to the first operation path to obtain a path data set;

[0014] Obtaining first flow data corresponding to each operation scenario, and performing flowchart construction processing according to the first flow data to obtain a flowchart data set; wherein the first flow data includes a flowchart of all operation paths corresponding to each operation scenario;

[0015] According to a preset operation rule, the path data set and the flowchart data set, database construction processing is performed to obtain the preset operation database.

[0016] Optionally, the data marking processing from the plurality of first recommended data according to the real-time operation data and the preset operation database to obtain first target data comprises:

[0017] According to the real-time operation data, matching processing is performed in the preset operation database to obtain a first matching result;

[0018] In a case where it is determined according to the first matching result that there is a first operation path containing the real-time operation data in the preset operation database, the first operation path containing the real-time operation data is determined as a first target path;

[0019] According to the first target path, data matching processing is performed on the plurality of first recommended data to obtain first to-be-labeled data; wherein the first to-be-labeled data is first recommended data in the first target path;

[0020] According to the preset operation database, the first to-be-labeled data is labeled to obtain the first target data.

[0021] Optionally, after the matching processing is performed on the real-time operation data in the preset operation database to obtain a first matching result, the method further comprises:

[0022] In a case where it is determined according to the first matching result that there is no first operation path containing the real-time operation data in the preset operation database, data labeling processing is performed on the plurality of first recommended data according to the preset operation rule to obtain the first target data.

[0023] Optionally, before the data decision processing is performed on the obtained real-time operation data to obtain a plurality of first recommended data, the method further comprises:

[0024] Determine whether the flow information of the operation flow in which the real-time operation data is located is obtained;

[0025] In a case where it is determined that the flow information is not obtained, data decision processing is performed on the obtained real-time operation data to obtain a plurality of first recommended data.

[0026] Optionally, after it is determined whether the flow information of the operation flow in which the real-time operation data is located is obtained, the method further comprises:

[0027] In a case where it is determined that the flow information is obtained, path selection processing is performed on the real-time operation data and the flow information in the preset operation database to obtain a second operation path; wherein the second operation path is a first operation path containing the real-time operation data.

[0028] According to the second operation path, flowchart data matching processing is performed in the preset operation database to obtain target flowchart data corresponding to the second operation path; wherein the preset flowchart data set includes flowchart data corresponding to all operation paths.

[0029] According to the target flowchart data, a target operation flow is determined, wherein the target operation flow at least includes target operation data, and the target operation data is next operation data adjacent to the real-time operation data in the second operation path.

[0030] Optionally, before the data decision processing is performed on the acquired second operation data to obtain a plurality of second recommended data, the method further comprises:

[0031] performing data detection processing on the second operation data to obtain a data detection result;

[0032] in a case where it is determined according to the data detection result that the second operation data is an irregular operation, a pop-up window displays preset warning information and preset suggestion information.

[0033] Optionally, the data detection processing on the real-time operation data to obtain a data detection result comprises:

[0034] performing matching processing on the second operation data in the preset path library to obtain a second matching result, wherein the preset path library contains all operation paths;

[0035] in a case where it is determined according to the second matching result that there is no operation path containing the second operation data in the preset path library, determining that the second operation data is an irregular operation; and / or,

[0036] acquiring an operation frequency of the second operation data, and in a case where the operation frequency is less than a preset frequency threshold, determining that the second operation data is an irregular operation, wherein the operation frequency is the number of occurrences of the second operation data in the all operation paths.

[0037] According to a second aspect of the present disclosure, a determination apparatus of an operation flow is provided, comprising:

[0038] a first decision unit configured to perform data decision processing on acquired real-time operation data to obtain a plurality of first recommended data, wherein the first recommended data is a next operation data adjacent to the real-time operation data in an operation path containing the real-time operation data;

[0039] a first marking unit configured to perform data marking processing on the real-time operation data and a preset operation database from the plurality of first recommended data to obtain first target data, wherein the preset operation database comprises a plurality of first operation paths, the first operation path is a target operation path corresponding to each different operation scenario obtained by reinforcement learning, and the first target data is determined by the first operation path;

[0040] a second decision unit, configured to perform data decision processing according to the obtained second operation data, to obtain a plurality of second recommended data; wherein the second operation data is next operation data obtained after the real-time operation data is obtained, and the second recommended data is next operation data adjacent to the second operation data in an operation path containing the second operation data;

[0041] a second marking unit, configured to perform data marking processing on the plurality of second recommended data according to the second operation data and the preset operation database, to obtain second target data, and to end the operation process according to a response operation completion instruction, wherein the second target data is determined by the first operation path.

[0042] Optionally, the apparatus further comprises:

[0043] an obtaining unit, configured to obtain historical operation data and operation success data corresponding to each operation scenario; wherein the operation success data is operation data that can successfully execute the corresponding operation scenario;

[0044] a recognition unit, configured to perform path recognition processing on the historical operation data and the operation success data by using a reinforcement learning algorithm, to obtain the first operation path corresponding to each operation scenario;

[0045] a construction unit, configured to perform data set construction processing according to the first operation path, to obtain a path data set;

[0046] the obtaining unit is further configured to obtain first process data corresponding to each operation scenario, and to perform process graph construction processing according to the first process data, to obtain a process graph data set; wherein the first process data includes a process graph of all operation paths corresponding to each operation scenario;

[0047] the construction unit is further configured to perform database construction processing according to a preset operation rule, the path data set and the process graph data set, to obtain the preset operation database.

[0048] Optionally, the first marking unit comprises:

[0049] a first matching module, configured to perform matching processing in the preset operation database according to the real-time operation data, to obtain a first matching result;

[0050] a determination module, configured to determine, according to the first matching result, that the first operation path containing the real-time operation data exists in the preset operation database, and to determine the first operation path containing the real-time operation data as a first target path;

[0051] The second matching module is configured to perform data matching processing on the first target path from a plurality of the first recommended data to obtain first to-be-labeled data; wherein the first to-be-labeled data is first recommended data in the first target path.

[0052] The labeling module is configured to perform labeling processing on the first to-be-labeled data according to the preset operation database to obtain the first target data.

[0053] Optionally, the labeling module in the first labeling unit is further configured to, in a case where it is determined according to the first matching result that the first operation path containing the real-time operation data does not exist in the preset operation database, perform data labeling processing on the plurality of the first recommended data according to the preset operation rule to obtain the first target data.

[0054] Optionally, the apparatus further comprises:

[0055] The first determining unit is configured to determine whether to obtain flow information of an operation flow in which the real-time operation data is located.

[0056] The first decision-making unit is further configured to, in a case where it is determined that the flow information is not obtained, perform data decision-making processing on the obtained real-time operation data to obtain a plurality of the first recommended data.

[0057] Optionally, the apparatus further comprises:

[0058] The selection unit is configured to, in a case where it is determined that the flow information is obtained, perform path selection processing on the preset operation database according to the flow information and the real-time operation data to obtain a second operation path; wherein the second operation path is a first operation path containing the real-time operation data.

[0059] The matching unit is configured to perform flowchart data matching processing on the preset operation database according to the second operation path to obtain target flowchart data corresponding to the second operation path; wherein the preset flowchart data set comprises flowchart data corresponding to all operation paths.

[0060] The second determining unit is configured to determine a target operation flow according to the target flowchart data, wherein the target operation flow at least comprises target operation data, and the target operation data is next operation data adjacent to the real-time operation data in the second operation path.

[0061] Optionally, the apparatus further comprises:

[0062] The detection unit is configured to perform data detection processing on the second operation data to obtain a data detection result.

[0063] The display unit is configured to display preset warning information and preset suggestion information in a pop-up window in a case where it is determined according to the data detection result that the second operation data is non-compliant operation.

[0064] Optionally, the detection unit comprises:

[0065] The matching module is configured to perform matching processing on the second operation data in the preset path library to obtain a second matching result, wherein the preset path library contains all operation paths.

[0066] The determination module is configured to determine that the second operation data is non-compliant operation in a case where it is determined according to the second matching result that there is no operation path containing the second operation data in the preset path library; and / or,

[0067] The determination module is further configured to obtain an operation frequency of the second operation data, and determine that the second operation data is non-compliant operation in a case where the operation frequency is less than a preset frequency threshold, wherein the operation frequency is the number of occurrences of the second operation data in the all operation paths.

[0068] According to a third aspect of the present disclosure, an electronic device is provided, comprising:

[0069] at least one processor; and

[0070] a memory connected to the at least one processor in communication; wherein

[0071] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the first aspect.

[0072] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to perform the method of the first aspect.

[0073] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of the first aspect.

[0074] The method and device for determining an operation process, and the electronic device provided in the present disclosure perform data decision processing according to obtained real-time operation data to obtain a plurality of first recommended data, wherein the first recommended data is next operation data adjacent to the real-time operation data in an operation path containing the real-time operation data; data marking processing is performed on the plurality of first recommended data according to the real-time operation data and a preset operation database to obtain first target data, wherein the preset operation database includes a plurality of first operation paths, the first operation paths are target operation paths corresponding to different operation scenarios respectively obtained through reinforcement learning, and the first target data is determined through the first operation paths; data decision processing is performed according to obtained second operation data to obtain a plurality of second recommended data, wherein the second operation data is next operation data obtained after the real-time operation data is obtained, and the second recommended data is next operation data adjacent to the second operation data in an operation path containing the second operation data; data marking processing is performed on the plurality of second recommended data according to the second operation data and the preset operation database to obtain second target data, until a response operation completion instruction is received to end the determination of the operation process, wherein the second target data is determined through the first operation paths. Compared with related technologies, the embodiments of the present disclosure determine a plurality of next operation data corresponding to the real-time operation data, that is, a plurality of first recommended data, and mark more suitable next operation data from the plurality of first recommended data, that is, first target data, and then determine more suitable next operation data of the second operation data, that is, second target data, according to the next operation of the real-time operation data, that is, the second operation data, until the operation is completed. When the system process is processed, the current processing step can be quickly identified, and the best next operation step and operation sequence, that is, the operation step and operation sequence obtained through reinforcement learning, are determined, so that the system operation process in the enterprise is more flexible, and the efficiency and accuracy when processing a more complex operation system process are improved.

[0075] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0076] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0077] Figure 1 A flowchart of a method for determining an operation process provided by the embodiments of the present disclosure;

[0078] Figure 2 A construction flowchart of a preset operation database provided by the embodiments of the present disclosure;

[0079] Figure 3 A flowchart of another method for determining an operation flow provided by an embodiment of the present disclosure;

[0080] Figure 4 A structural diagram of a device for determining an operation flow provided by an embodiment of the present disclosure;

[0081] Figure 5 A structural diagram of another device for determining an operation flow provided by an embodiment of the present disclosure;

[0082] Figure 6 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0083] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to help in understanding, which should be considered in the context of the present disclosure. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, for the sake of clarity and conciseness, the description below omits the description of well-known functions and structures.

[0084] The method and device for determining an operation flow, and the electronic device of an embodiment of the present disclosure are described below with reference to the accompanying drawings.

[0085] Figure 1 A flowchart of a method for determining an operation flow provided by an embodiment of the present disclosure.

[0086] As shown in Figure 1 , the method comprises the following steps:

[0087] Step 101: performing data decision processing according to the obtained real-time operation data to obtain a plurality of first recommended data; wherein the first recommended data is a next operation data adjacent to the real-time operation data in an operation path containing the real-time operation data.

[0088] In an embodiment of the present disclosure, the real-time operation data is operation data generated by a real-time operation step in a corresponding operation flow, for example, clicking, inputting, selecting, etc. According to the real-time operation data, the current operation step, i.e., the real-time operation step, can be located. Specifically, the content of the real-time operation data is not limited by the present disclosure.

[0089] The plurality of first recommended data at least includes next operation data adjacent to the real-time operation data in all operation paths containing real-time operation data, that is, the plurality of first recommended data refers to operation data corresponding to all possible operation steps after the real-time operation step. The plurality of first recommended data can determine all operation steps after the real-time operation step.

[0090] By making a decision on the operation data corresponding to the real-time operation step, all operation steps after the real-time operation step are determined, which can facilitate the operator to determine the operation to be performed subsequently and improve efficiency.

[0091] In step 102, first target data is obtained by performing data marking processing on the real-time operation data and the preset operation database from the plurality of first recommended data. The preset operation database includes a plurality of first operation paths, the first operation path is a target operation path corresponding to each different operation scenario obtained by reinforcement learning, and the first target data is determined by the first operation path.

[0092] In the embodiment of the present disclosure, the preset operation database is a database pre-constructed to include a best operation path (i.e., a plurality of first operation paths) in different operation scenarios and a visual operation flowchart corresponding to each operation path. The best operation path is the first operation path obtained by reinforcement learning based on historical operation data and operation success data in the current scenario. Different operation scenarios can be different system operation flows, such as an account creation flow, an account cancellation flow, etc. Specifically, the content of the preset operation database and the content of the operation scenario are not limited in the embodiment of the present disclosure.

[0093] The first target data is the next best operation data of the real-time operation data, that is, the next operation data adjacent to the real-time operation data in the first operation path.

[0094] The process of data marking according to the preset operation database is a process of determining the next best operation data corresponding to the real-time operation data. The preset operation database needs to be pre-constructed. For example, a machine learning algorithm (such as a decision tree, reinforcement learning, etc.) is used to analyze historical operation data and successful cases of operators, identify the best operation path in different scenarios, and construct a path data set. Based on the specification process automation technology, the standardized and fixed operation steps in the enterprise are modeled to form a visual operation flowchart to obtain a flowchart data set. The path data set and the flowchart data set are used to construct the preset operation database together.

[0095] In step 103, data decision processing is performed according to the obtained second operation data to obtain a plurality of second recommended data; wherein the second operation data is the next operation data obtained after the real-time operation data is obtained, and the second recommended data is the next operation data adjacent to the second operation data in the operation path containing the second operation data.

[0096] In the embodiment of the present disclosure, the second operation data is the operation data corresponding to the next operation step performed by the operator after performing the operation step corresponding to the real-time operation data. Meanwhile, the operator does not necessarily perform the recommended steps when performing the process operation, that is, the operator does not necessarily perform the operation step corresponding to the first target data after performing the operation step corresponding to the real-time operation data, but can perform other operation step, i.e., the second operation step (the operation step corresponding to the second operation data). At this time, the operation data corresponding to all operation steps performed after the second operation step, i.e., the plurality of second recommended data, can be determined according to the second operation data, and all operation steps after the second operation step can be determined through the plurality of second recommended data.

[0097] Specifically, reference can be made to the description in step 101 above, and thus the description will not be repeated here.

[0098] In step 104, data marking processing is performed on the plurality of second recommended data according to the second operation data and the preset operation database to obtain a second target data, and the determination of the end of the operation process is ended in response to an operation completion instruction, wherein the second target data is determined through the first operation path.

[0099] In the embodiment of the present disclosure, after all operation steps after the second operation step are determined through the plurality of second recommended data, the best operation step after the second operation step, i.e., the operation step corresponding to the second target data, is determined, and the same is repeated. After the operator performs the operation, the best step after the current step is determined according to the operation data until the operation is completed.

[0100] The operation completion instruction is an instruction automatically generated after the operator completes the operation process, and through the operation completion instruction, it can be determined that the operation process can be directly ended without subsequent operation.

[0101] Specifically, for the embodiment of the present disclosure, reference can be made to the description in step 102 above, and thus the description will not be repeated here.

[0102] Further, the first target data and the second target data are equivalent to automatically deciding and recommending an optimal operation step according to the real-time operation data and the second operation data, and subsequent operation personnel can perform corresponding operations according to the optimal operation step, which can improve the efficiency and accuracy of operation personnel in processing various operations, while ensuring that the operation process meets the specification requirements, and enhancing the compliance and smoothness of work.

[0103] The method for determining an operation process provided by the present disclosure includes: performing data decision processing on acquired real-time operation data to obtain a plurality of first recommended data; wherein the first recommended data is next operation data adjacent to the real-time operation data in an operation path containing the real-time operation data; performing data marking processing on the real-time operation data and a preset operation database from the plurality of first recommended data to obtain first target data; wherein the preset operation database includes a plurality of first operation paths, the first operation path is a target operation path corresponding to each operation scenario obtained through reinforcement learning, and the first target data is determined through the first operation path; performing data decision processing on acquired second operation data to obtain a plurality of second recommended data; wherein the second operation data is next operation data acquired after the real-time operation data, and the second recommended data is next operation data adjacent to the second operation data in an operation path containing the second operation data; performing data marking processing on the second operation data and the preset operation database from the plurality of second recommended data to obtain second target data, until a response operation completion instruction is received to end the determination of the operation process, wherein the second target data is determined through the first operation path. Compared with related technologies, the embodiment of the present disclosure determines a plurality of next operation data corresponding to the real-time operation data, i.e., a plurality of first recommended data, and marks a more suitable next operation data from the plurality of first recommended data, i.e., a first target data, and then determines a more suitable next operation data of the second operation data, i.e., a second target data, according to the next operation of the real-time operation data, i.e., a second operation data, until the operation is completed. When processing a system process, the current processing step can be quickly identified, and the best next operation step and operation sequence, i.e., the operation step and operation sequence obtained through reinforcement learning, can be determined, so that the system operation process within an enterprise is more flexible, and the efficiency and accuracy in processing a complex operation system process are improved.

[0104] In one implementation manner of the embodiment of the present disclosure, before the path selection processing is performed, a preset operation database needs to be constructed, so that the next optimal operation step can be automatically decided and recommended. Regarding the construction of the preset operation database, the embodiment of the present disclosure provides a construction process diagram of a preset operation database, as shown in Figure 2As shown, comprising:

[0105] In step 201, the respective historical operation data and operation success data corresponding to each operation scenario are obtained; wherein the operation success data is operation data that can successfully execute the corresponding operation scenario.

[0106] In the embodiments of the present disclosure, the historical operation data contains the respective historical operation data of all system operation processes (i.e., operation scenarios), and since the historical operation data refers to the records of all operations in the system operation process in the past period of time, including but not limited to: operation time, operator, operation steps, operation results (whether successful or not) and any other information related to operation, therefore, the operation error data is included in the historical operation data, and the operation error data is operation data that cannot successfully execute the corresponding system operation process.

[0107] It should be noted that the historical operation data also contains the operation success data, that is, the historical operation data provides a comprehensive record of the operation, and the operation success data is a subset of the historical operation data, focusing on records of successful completion and achieving the expected results.

[0108] Since the historical operation data contains operation success data, operation error data and other operation data, it is necessary to extract the operation success data (i.e., obtain the historical operation data and operation success data side by side) for data verification to ensure that the first operation path obtained subsequently is constructed on the basis of the operation success data.

[0109] In step 202, the path recognition processing is performed according to the historical operation data and the operation success data through a reinforcement learning algorithm, the respective first operation path corresponding to each operation scenario is obtained, and the data set construction processing is performed according to the first operation path, and the path data set is obtained.

[0110] In the embodiments of the present disclosure, when performing path recognition processing, reinforcement learning algorithm can be used, and other recognition algorithms such as decision tree can also be used.

[0111] By using machine learning algorithms (such as decision tree, reinforcement learning, etc.) to analyze the historical operation data and successful cases of operation personnel, the best operation path in different scenarios can be identified. Through path recognition processing, the system operation process can be optimized, and errors can be reduced and efficiency can be improved. For example, if reinforcement learning can determine that a certain step combination has the advantages of high efficiency, high operation frequency, etc. on the basis of successfully completing the task, then this step combination can be recommended as the first operation path.

[0112] In the process of constructing the data set, the first operation data can be collected and processed to obtain the path data set.

[0113] In step 203, the first flow data corresponding to each operation scene is obtained, and a flowchart construction process is performed according to the first flow data to obtain a flowchart data set; wherein the first flow data includes flowcharts of all operation paths corresponding to each operation scene.

[0114] In the embodiments of the present disclosure, the first flow data includes all possible operation paths involved in each system operation process (operation scene) and corresponding flowchart data, including but not limited to all standardized and fixed operation steps within an enterprise. Specifically, the first flow data is not limited in the embodiments of the present disclosure.

[0115] In the process of constructing the flowchart, a preset construction algorithm can be used, such as Business Process Automation (BPA). Business Process Automation can use software and technical means to perform repetitive business tasks, with the purpose of reducing human intervention, improving efficiency, reducing error rate, and optimizing the entire business process. Specifically, the preset construction algorithm for constructing the flowchart is not limited in the embodiments of the present disclosure.

[0116] By using the standardized and fixed operation steps within an enterprise to model the standardized and fixed operation steps within an enterprise, a visual operation flowchart (preset flowchart data) is formed. The system can automatically generate and recommend operation steps according to real-time operation status.

[0117] In step 204, a database construction process is performed according to the preset operation rule, the path data set, and the flowchart data set to obtain the preset operation database.

[0118] In the embodiments of the present disclosure, the preset operation rule is a rule set by the user, which is used to process some specific system operation processes (operation scenes). For example, the system operation processes required in an enterprise are only registration and deregistration, and now an additional storage system operation process needs to be added. At this time, a storage process can be set to add to the preset operation database. If the real-time data is unique to the storage process, the recommendation can be directly performed.

[0119] The database construction process is a database design and filling process. The preset operation rule, the path data set, and the flowchart data set can be organized into a structured database to facilitate the query, management, and optimization of the system operation process.

[0120] By constructing the preset operation database, the optimal operation path in each system operation process can be fixed, and quick access and efficient management can be provided in the form of the database, thereby improving the efficiency of the entire system operation process and user experience.

[0121] In an implementation manner of the embodiment of the present disclosure, as a refinement of the above step 102, when performing data labeling processing, the following manner can be used, but is not limited thereto: performing matching processing on the real-time operation data in the preset operation database to obtain a first matching result; in a case where it is determined according to the first matching result that there is a first operation path containing the real-time operation data in the preset operation database, determining the first operation path containing the real-time operation data as a first target path; performing data matching processing on the first target path from a plurality of first recommended data to obtain first to-be-labeled data; wherein the first to-be-labeled data is first recommended data in the first target path; performing labeling processing on the flowchart data corresponding to the first to-be-labeled data according to the preset operation database to obtain the first target data.

[0122] In the embodiment of the present disclosure, since the first operation path is the optimal operation path under different operation scenarios, when the real-time data is matched, two cases can occur, case one: there is a first operation path containing the real-time operation data; case two: there is no first operation path containing the real-time operation data, when case one occurs, the optimal operation data after the real-time operation data, that is, the first to-be-labeled data, can be determined according to the matched first operation path, that is, the first target path.

[0123] The first to-be-labeled data is labeled in the flowchart, that is, the first target data, the difference between the first to-be-labeled data and the first target data is only whether to be labeled in the visual flowchart, and the labeling manner includes but is not limited to: highlighting the flowchart data corresponding to the target operation path, color labeling (or text labeling and other labeling manners) the flowchart data corresponding to the target operation path, and the specific labeling manner is not limited in the embodiment of the present disclosure.

[0124] The above describes the implementation manner of case one, and next, when case two occurs, the following manner can be used, but is not limited thereto: in a case where it is determined according to the first matching result that there is no first operation path containing the real-time operation data in the preset operation database, performing data labeling processing on the first recommended data according to the preset operation rule to obtain the first target data.

[0125] In the embodiments of the present disclosure, the preset operation rule is one rule set by the user, which is used to process some specific system operation process, i.e., operation scenario. For the preset operation rule, refer to the description in step 204 above, and thus will not be repeated here.

[0126] When the first operation path containing the real-time operation data does not exist, it means that the real-time operation data is the data corresponding to the operation step unique in the preset operation rule. At this time, the operation step in the preset operation rule (i.e., the first recommended data in the preset operation rule) can be directly marked.

[0127] In one implementation manner of the embodiments of the present disclosure, when the operator performs the system operation process, two cases will also occur. Case 1: the operator forgets to determine the system operation process in advance and directly performs the operation. Case 2: the operator determines the operation process in advance. When case 1 occurs, all operation data after the real-time operation data need to be determined, and the best operation step in all operation data after the real-time operation data needs to be determined. At this time, the best operation step determined is the operation step obtained through reinforcement learning, which does not necessarily only contain the best operation step in the system operation process that the operator needs to perform, i.e., when case 1 occurs, the operation step obtained through reinforcement learning needs to be determined. Figure 1 The method is used for processing. When case 2 occurs, only the best step under this process needs to be recommended according to the flow information of the determined system operation process.

[0128] Therefore, when determining the operation process, it is necessary to first determine whether the flow information of the pre-determined system operation process is obtained, and then determine the operation process according to the possible cases. Specifically, in the case judgment, the following methods can also be used, but are not limited to: determining whether the flow information of the operation process in which the real-time operation data is located is obtained; in the case where it is determined that the flow information is not obtained, performing data decision processing according to the obtained real-time operation data to obtain a plurality of first recommended data.

[0129] In the embodiments of the present disclosure, when it is determined that the flow information is not obtained, i.e., case 1 occurs, the method for processing can be performed. Figure 1

[0130] When case 2 occurs, i.e., when it is determined that the flow information is obtained, the present disclosure further provides another flowchart of a method for determining the operation process, as shown in Figure 3 , which includes:

[0131] ​In step 301, in a case where it is determined that the process information is acquired, path selection processing is performed in the preset operation database according to the process information and the real-time operation data, and a second operation path is obtained; the second operation path is a first operation path containing the real-time operation data.

[0132] In the embodiments of the present disclosure, the real-time operation data is operation data generated by a real-time operation step in a corresponding system operation process, for example, clicking, inputting, selecting, etc. According to the real-time operation data, the current operation step, i.e., the real-time operation step, can be located. The preset operation database is a database pre-constructed to include optimal operation paths (i.e., a plurality of first operation paths respectively corresponding to system operation processes) in different scenarios. The optimal operation path is the first operation path, which represents an operation path with the highest operation frequency in the current scenario. Different scenarios refer to different system operation processes, for example, an account creation process, an account cancellation process, etc. Specifically, the content of the real-time operation data, the content of the preset operation database, and the content of the system operation process are not limited in the embodiments of the present disclosure.

[0133] The second operation path is an optimal operation path in a system operation process corresponding to the real-time operation data. Through the second operation path, the next optimal operation data of the real-time operation data, i.e., the next operation data adjacent to the real-time operation data in the second operation path, can be determined.

[0134] The process of path selection in the preset operation database is a process of determining the optimal operation path corresponding to the real-time operation data.

[0135] In step 302, process diagram data matching processing is performed in the preset operation database according to the second operation path, and target process diagram data corresponding to the second operation path is obtained; the preset process diagram data set includes process diagram data corresponding to all operation paths.

[0136] In the embodiments of the present disclosure, the preset operation database contains a process diagram data set. The process diagram data set is a data set pre-constructed to contain process diagrams of all operation paths in an enterprise. Through the second operation path, a corresponding process diagram, i.e., the target process diagram data, can be found from the process diagram data set.

[0137] The flowchart data set is a visualized flowchart data set, and thus the target flowchart data can be regarded as data obtained by visualizing the second operation path through a flowchart. The target flowchart data can be used to accurately determine the operation step corresponding to each operation data in the second operation path. After the target flowchart data is obtained, the next best operation step of the operation step corresponding to the real-time operation data can be determined according to the target flowchart data. Since the second operation path is the best operation step in the system operation process corresponding to the real-time operation data, the next best operation step is the operation step corresponding to the next operation data adjacent to the real-time operation data in the second operation path.

[0138] In step 303, the target operation process is determined according to the target flowchart data. The target operation process at least includes target operation data, which is the next operation data adjacent to the real-time operation data in the second operation path.

[0139] In the embodiments of the present disclosure, the target operation process is the best overall operation step of the system operation process corresponding to the real-time operation data. According to the step corresponding to the target operation process, the system operation process corresponding to the real-time operation data can be accurately and efficiently completed.

[0140] It should be noted that the target operation process not only includes target operation data, but also includes operation data in the entire second operation path. Therefore, the target operation process is data obtained by marking the target flowchart data in the flowchart data set, for example, by highlighting the target flowchart data in the flowchart data set.

[0141] Further, the target operation process is equivalent to automatically deciding and recommending a best operation step according to the real-time operation data. Subsequent operators can perform corresponding operations according to the target operation process, which can improve the efficiency and accuracy of operators in processing various operations, and ensure that the operation process meets the specification requirements, thereby enhancing the compliance and smoothness of work.

[0142] In one implementation manner of the embodiments of the present disclosure, the operation step also needs to be monitored to ensure the accuracy of the operator during operation. Specifically, the monitoring of the operation step can also use, but is not limited to, the following method: performing data detection processing on the second operation data to obtain a data detection result; in a case where it is determined according to the data detection result that the second operation data is an illegal operation, a pop-up window displays preset warning information and preset suggestion information.

[0143] In the embodiments of the present disclosure, the second operation data is operation data corresponding to a next operation step performed after the operation personnel performs an operation step corresponding to the real-time operation data. Since the operation personnel may not operate according to the target operation process when performing the process operation, the second operation data needs to be detected to determine whether the process operation of the operation personnel is compliant.

[0144] The preset warning information and the preset suggestion information are self-defined information. For example, the preset warning information is "operation step may be wrong, please check!", and the preset suggestion information is "please determine whether the second operation data is correct". The embodiments of the present disclosure do not limit the preset warning information and the preset suggestion information.

[0145] In an implementation manner of the embodiments of the present disclosure, when the second operation data is subjected to data detection processing, the following manner can be used but is not limited thereto: performing matching processing on the second operation data in the preset path library to obtain a second matching result; the preset path library contains all operation paths; in a case where it is determined according to the second matching result that there is no operation path containing the second operation data in the preset path library, it is determined that the second operation data is non-compliant operation; and / or, obtaining an operation frequency of the second operation data, and in a case where the operation frequency is less than a preset frequency threshold, it is determined that the second operation data is non-compliant operation, wherein the operation frequency is the number of occurrences of the second operation data in the all operation paths.

[0146] In the embodiments of the present disclosure, the operation frequency of the second operation data in all operation paths can be used to represent the frequency of use of the real-time operation data.

[0147] The preset frequency threshold is a self-defined value used to determine whether the second operation data is compliant. The preset frequency threshold can be set according to business requirements, security requirements or operation specifications, for example, 10 times, 5 times, etc. The embodiments of the present disclosure do not limit the preset frequency threshold.

[0148] In summary, the embodiments of the present disclosure can achieve the following technical effects:

[0149] The embodiments of the present disclosure can quickly identify the current processing step and determine the optimal next operation step and operation sequence, i.e., the operation step and operation sequence obtained through reinforcement learning, when processing the system flow, so that the system operation flow within the enterprise is more flexible, and the efficiency and accuracy when processing a more complex operation system flow are improved.

[0150] Corresponding to the above-mentioned operation flow determination method, the present application also provides an operation flow determination device. Since the device embodiments of the present application correspond to the above-mentioned method embodiments, the details not disclosed in the device embodiments can be referred to the above-mentioned method embodiments, which will not be described in detail herein.

[0151] Figure 4 The structure diagram of an operation flow determination device provided by the embodiments of the present disclosure is shown in FIG. 1, which includes: Figure 4

[0152] The first decision unit 401 is configured to perform data decision processing according to the obtained real-time operation data to obtain a plurality of first recommended data; wherein the first recommended data is the next operation data adjacent to the real-time operation data in the operation path containing the real-time operation data.

[0153] The first marking unit 402 is configured to perform data marking processing on the plurality of first recommended data according to the real-time operation data and a preset operation database to obtain first target data; wherein the preset operation database includes a plurality of first operation paths, the first operation path is a target operation path corresponding to each different operation scenario obtained through reinforcement learning, and the first target data is determined through the first operation path.

[0154] The second decision unit 403 is configured to perform data decision processing according to the obtained second operation data to obtain a plurality of second recommended data; wherein the second operation data is the next operation data obtained after the real-time operation data is obtained, and the second recommended data is the next operation data adjacent to the second operation data in the operation path containing the second operation data.

[0155] ​The second marking unit 404 is configured to perform data marking processing on the second recommended data according to the second operation data and the preset operation database, to obtain second target data, and to end the operation process in response to an operation completion instruction, wherein the second target data is determined by the first operation path.

[0156] The operation process determination apparatus provided in the present disclosure performs path selection processing in a preset operation database according to obtained real-time operation data, to obtain a target operation path; wherein the preset operation database includes a plurality of first operation paths corresponding to respective system operation processes, and the first operation path is an operation path with the highest operation frequency in the corresponding system operation process; data matching processing is performed on a preset flowchart data set according to the target operation path, to obtain target flowchart data corresponding to the target operation path; wherein the preset flowchart data set includes flowchart data corresponding to all operation paths; and a target operation process is determined according to the target flowchart data, wherein the target operation process at least includes target operation data, and the target operation data is next operation data adjacent to the real-time operation data in the target operation path. Compared with related technologies, the embodiment of the present disclosure determines the corresponding target operation path according to real-time operation data, determines the corresponding target flowchart according to the target operation path, and determines the target operation process containing the next operation step (target operation data) of the real-time operation data according to the indication of the target flowchart, so that the current processing step can be quickly identified when processing the system flowchart, and the next operation step and operation sequence with higher operation frequency are determined, so that the system operation process in an enterprise is more flexible, and the efficiency and accuracy when processing a complex operation system flowchart are improved.

[0157] Further, in a possible implementation manner of the embodiment of the present disclosure, as shown in Figure 5 The apparatus further includes:

[0158] The acquisition unit 405 is configured to acquire historical operation data and operation success data corresponding to each operation scene; wherein the operation success data is operation data that can successfully execute the corresponding operation scene;

[0159] The identification unit 406 is configured to perform path identification processing on the historical operation data and the operation success data by using a reinforcement learning algorithm, to obtain the first operation path corresponding to each operation scene;

[0160] The construction unit 407 is configured to perform data set construction processing according to the first operation path, to obtain a path data set;

[0161] The acquisition unit 405 is further configured to acquire first flow data corresponding to each of the operation scenarios, and perform flowchart construction processing according to the first flow data to obtain a flowchart data set; wherein the first flow data includes flowcharts of all operation paths corresponding to each of the operation scenarios.

[0162] The construction unit 407 is further configured to perform database construction processing according to a preset operation rule, the path data set, and the flowchart data set to obtain the preset operation database.

[0163] Further, in a possible implementation manner of the embodiment of the present disclosure, as shown in Figure 5 The first marking unit 402 includes:

[0164] The first matching module 4021 is configured to perform matching processing in the preset operation database according to the real-time operation data to obtain a first matching result.

[0165] The determination module 4022 is configured to determine, according to the first matching result, that a first operation path containing the real-time operation data exists in the preset operation database, and determine the first operation path containing the real-time operation data as a first target path.

[0166] The second matching module 4023 is configured to perform data matching processing from a plurality of first recommended data according to the first target path to obtain first to-be-marked data; wherein the first to-be-marked data is first recommended data in the first target path.

[0167] The marking module 4024 is configured to perform marking processing on flowchart data corresponding to the first to-be-marked data according to the preset operation database to obtain the first target data.

[0168] Further, in a possible implementation manner of the embodiment of the present disclosure, the marking module 4024 in the first marking unit 402 is further configured to, in a case where it is determined according to the first matching result that no first operation path containing the real-time operation data exists in the preset operation database, perform data marking processing from a plurality of first recommended data according to the preset operation rule to obtain the first target data.

[0169] Further, in a possible implementation manner of the embodiment of the present disclosure, as shown in Figure 5 The apparatus further includes:

[0170] The first determination unit 408 is configured to determine whether flow information of an operation flow in which the real-time operation data is located is acquired.

[0171] The first decision unit 408 is further configured to, in a case where it is determined that the process information is not acquired, perform data decision processing according to the acquired real-time operation data, to obtain a plurality of first recommended data.

[0172] Further, in a possible implementation of the embodiment of the present disclosure, as shown in Figure 5 The apparatus further includes:

[0173] The selection unit 409 is configured to, in a case where it is determined that the process information is acquired, perform path selection processing in the preset operation database according to the process information and the real-time operation data, to obtain a second operation path; wherein the second operation path is a first operation path containing the real-time operation data.

[0174] The matching unit 410 is configured to perform process graph data matching processing in the preset operation database according to the second operation path, to obtain target process graph data corresponding to the second operation path; wherein the preset process graph data set includes process graph data corresponding to all operation paths.

[0175] The second determination unit 411 is configured to determine a target operation process according to the target process graph data, wherein the target operation process at least includes target operation data, and the target operation data is next operation data adjacent to the real-time operation data in the second operation path.

[0176] Further, in a possible implementation of the embodiment of the present disclosure, as shown in Figure 5 The apparatus further includes:

[0177] The detection unit 412 is configured to perform data detection processing on the second operation data, to obtain a data detection result.

[0178] The display unit 413 is configured to, in a case where it is determined according to the data detection result that the second operation data is an out-of-compliance operation, pop-up display preset warning information and preset suggestion information.

[0179] Further, in a possible implementation of the embodiment of the present disclosure, as shown in Figure 5 The detection unit 412 includes:

[0180] The matching module 4121 is configured to perform matching processing in the preset path library according to the second operation data, to obtain a second matching result; wherein the preset path library contains all operation paths.

[0181] The determining module 4122 is configured to determine that the second operation data is non-compliant operation in a case where it is determined according to the second matching result that there is no operation path containing the second operation data in the preset path library.

[0182] The determining module 4122 is further configured to acquire an operation frequency of the second operation data, and determine that the second operation data is non-compliant operation in a case where the operation frequency is less than a preset frequency threshold, where the operation frequency is a number of occurrences of the second operation data in the all operation paths.

[0183] It should be noted that the foregoing explanations and descriptions of the method embodiments are also applicable to the device of the embodiments of the present disclosure, and the principles are the same, and the device of the embodiments of the present disclosure is not limited herein.

[0184] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0185] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0186] As shown in Figure 6 The electronic device 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 602 or a computer program loaded into a RAM (Random Access Memory) 603 from a storage unit 608. Various programs and data required for the operation of the electronic device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An I / O (Input / Output) interface 605 is also connected to the bus 604.

[0187] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through computer networks, such as the Internet, and / or various telecommunication networks.

[0188] The computing unit 601 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 601 performs various methods and processes described above, such as the method of determining an operational flow. For example, in some embodiments, the method of determining an operational flow can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the aforementioned method of determining an operational flow by any other appropriate means, such as by means of firmware.

[0189] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a Field Programmable Gate Array (FPGA), an Application-Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a System on a Chip (SOC), a Complex Programmable Logic Device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0190] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general or special purpose computer, such that the program code, when executed by the processor or controller, causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0191] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include a linearly-programmed electrical connection, a portable computer diskette, a hard disk, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory), or flash memory, an optical fiber, a compact disc (CD) ROM, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0192] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0193] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a LAN (local area network), a WAN (wide area network), the Internet, and a blockchain network.

[0194] The computer system can include clients and servers. This relationship can be between a client and a server that are typically remote from each other and typically interact through a communication network. The relationship between client and server exists by virtue of computer programs running on the respective computer systems and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS (Virtual Private Server, or VPS for short) services. The server can also be a server of a distributed system, or a server combined with a blockchain.

[0195] It should be noted that artificial intelligence is a discipline that studies enabling computers to simulate some thinking processes and intelligent behaviors of humans (such as learning, reasoning, thinking, planning, etc.), both hardware and software technologies. Artificial intelligence hardware technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing, etc.; artificial intelligence software technology mainly includes computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, knowledge graph technology, etc. several major directions.

[0196] It should be understood that the various forms of the flow shown above can be used to reorder, add or delete steps. For example, each step described in the present disclosure can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, which is not limited herein.

[0197] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for determining an operation procedure, characterized in that, include: Data decision processing is performed based on the acquired real-time operation data to obtain multiple first recommended data; wherein, the first recommended data is the next operation data adjacent to the real-time operation data in the operation path containing the real-time operation data; Based on the real-time operation data and the preset operation database, data labeling processing is performed on multiple first recommended data to obtain first target data; wherein, the preset operation database includes multiple first operation paths, and the first operation paths are target operation paths corresponding to different operation scenarios obtained through reinforcement learning, and the first target data is determined through the first operation paths; Data decision processing is performed based on the acquired second operation data to obtain multiple second recommended data; wherein, the second operation data is the next operation data acquired after the real-time operation data is acquired, and the second recommended data is the next operation data adjacent to the second operation data in the operation path containing the second operation data; Based on the second operation data and the preset operation database, data marking processing is performed on multiple second recommended data to obtain second target data until an operation completion instruction is received, thereby ending the determination of the operation process. The second target data is determined through the first operation path. The step of performing data labeling processing on multiple first recommended data sets based on the real-time operation data and a preset operation database to obtain the first target data includes: The real-time operation data is matched in the preset operation database to obtain a first matching result. If, based on the first matching result, it is determined that there is no first operation path containing the real-time operation data in the preset operation database, data marking processing is performed from multiple first recommended data according to preset operation rules to obtain the first target data.

2. The method according to claim 1, characterized in that, Before performing data decision processing based on the acquired real-time operational data to obtain multiple first recommendation data, the method further includes: Obtain historical operation data and operation success data corresponding to each of the operation scenarios; wherein, the operation success data is operation data that enables the corresponding operation scenario to be executed successfully; Based on the historical operation data and the successful operation data, a path recognition process is performed using a reinforcement learning algorithm to obtain the first operation path corresponding to each operation scenario. Then, a dataset is constructed based on the first operation path to obtain a path dataset. Obtain the first process data corresponding to each of the operation scenarios, and perform flowchart construction processing based on the first process data to obtain a flowchart dataset; wherein, the first process data includes flowcharts of all the operation paths corresponding to each of the operation scenarios. The preset operation database is obtained by performing database construction processing based on the preset operation rules, the path dataset, and the flowchart dataset.

3. The method according to claim 2, characterized in that, After performing matching processing on the preset operation database based on the real-time operation data to obtain a first matching result, the method further includes: If, based on the first matching result, it is determined that there exists a first operation path containing the real-time operation data in the preset operation database, the first operation path containing the real-time operation data is determined as the first target path. Based on the first target path, data matching processing is performed from multiple first recommended data to obtain first data to be labeled; wherein, the first data to be labeled is the first recommended data located in the first target path; The flowchart data corresponding to the first data to be marked is marked according to the preset operation database to obtain the first target data.

4. The method according to claim 2, characterized in that, Before performing data decision processing based on the acquired real-time operational data to obtain multiple first recommendation data, the method further includes: Determine whether the process information of the operation flow in which the real-time operation data is located has been obtained; If the process information is not obtained, data decision processing is performed based on the obtained real-time operation data to obtain multiple first recommendation data.

5. The method according to claim 4, characterized in that, After determining whether the process information of the operation flow in which the real-time operation data is located has been obtained, the method further includes: If the process information is obtained, a path selection process is performed in the preset operation database based on the process information and the real-time operation data to obtain a second operation path; wherein, the second operation path is a first operation path that includes the real-time operation data. Based on the second operation path, flowchart data matching processing is performed in the preset operation database to obtain the target flowchart data corresponding to the second operation path; wherein, the flowchart dataset includes flowchart data corresponding to all operation paths; The target operation process is determined based on the target flowchart data, wherein the target operation process includes at least target operation data, which is the next operation data adjacent to the real-time operation data in the second operation path.

6. The method according to claim 1, characterized in that, Before performing data decision processing based on the acquired second operational data to obtain multiple second recommendation data, the method further includes: The second operation data is subjected to data detection processing to obtain data detection results; If the data detection results indicate that the second operation data is an non-compliant operation, a pop-up window will display a preset warning message and a preset suggestion message.

7. The method according to claim 6, characterized in that, The data detection processing of the second operation data to obtain the data detection result includes: The second operation data is matched in a preset path library to obtain a second matching result; wherein, the preset path library contains all operation paths; If, based on the second matching result, it is determined that there is no operation path containing the second operation data in the preset path library, the second operation data is determined to be an non-compliant operation; and / or, The operation frequency of the second operation data is obtained. If the operation frequency is less than a preset frequency threshold, the second operation data is determined to be an non-compliant operation. The operation frequency is the number of times the second operation data appears in all operation paths.

8. A device for determining an operation process, characterized in that, include: The first decision unit is used to perform data decision processing based on the acquired real-time operation data to obtain multiple first recommended data; wherein, the first recommended data is the next operation data adjacent to the real-time operation data in the operation path containing the real-time operation data; The first labeling unit is used to perform data labeling processing on multiple first recommended data according to the real-time operation data and the preset operation database to obtain first target data; wherein, the preset operation database includes multiple first operation paths, the first operation paths are target operation paths corresponding to different operation scenarios obtained through reinforcement learning, and the first target data is determined by the first operation paths. The second decision unit is used to perform data decision processing based on the acquired second operation data to obtain multiple second recommended data; wherein, the second operation data is the next operation data acquired after the real-time operation data is acquired, and the second recommended data is the next operation data adjacent to the second operation data in the operation path containing the second operation data; The second marking unit is used to perform data marking processing on multiple second recommended data according to the second operation data and the preset operation database to obtain the second target data until the operation completion instruction is responded to, thereby ending the determination of the operation process, wherein the second target data is determined through the first operation path; The first marking unit includes: The first matching module is used to perform matching processing on the preset operation database based on the real-time operation data to obtain a first matching result; The tagging module is used to perform data tagging processing on multiple first recommended data according to preset operation rules to obtain the first target data when it is determined from the preset operation database that there is no first operation path containing the real-time operation data based on the first matching result.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

Images