Task review method and device combining RPA and AI
By using multiple review devices to review tasks in the task review method combined with RPA and AI, multiple review devices are used to review tasks, which solves the problem that the existing technology cannot meet the risk control needs of enterprises, and achieves high accuracy and security of task results. Improve business processing efficiency.
Patent Information
- Application Number
- CN202210110417.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-28
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2042-01-28
Smart Images

Figure CN114490768B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical fields of Robotic Process Automation (RPA) and Artificial Intelligence (AI), and in particular to a task review method and device combining RPA and AI. Background Art
[0002] Robotic Process Automation (RPA), referred to as Robotic Process Automation, uses specific "robot software" to simulate human operations on computers and automatically execute process tasks according to rules.
[0003] Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.
[0004] As the manual operation portal, the Human-Machine Collaboration Center connects the collaborative work between humans and RPA robots to realize manual review and revision of processes. In an RPA automation process, the Human-Machine Collaboration Center can assign tasks that require manual judgment and decision-making to humans. Through operations such as form information input and secondary information verification and confirmation, humans can provide accurate input for RPA robots, thereby creating more and safer automation opportunities.
[0005] In related technologies, the human-machine collaboration center cannot realize multiple reviews of tasks. In many scenarios, such as some important documents, important decisions, and sensitive operations, the human-machine collaboration center needs to review manual input multiple times. If it is only confirmed manually once, it will not meet the needs of internal enterprise risk control. In some scenarios, if manual judgment, calculation, or operation errors are made, it will cause immeasurable serious consequences. Summary of the invention
[0006] The embodiment of the present application provides a task review method and device combining RPA and AI to solve the problems existing in the related technologies. The technical solution is as follows:
[0007] In the first aspect, an embodiment of the present application provides a task review method combining RPA and AI, which is executed by an RPA robot, including: obtaining tasks that need to be reviewed in the RPA robot process, taking the tasks that need to be reviewed as target review tasks, and copying the target review tasks to obtain N target review tasks; selecting N target review devices from a review device cluster, and assigning the N target review tasks to the N target review devices for review, where N is a positive integer greater than or equal to 2; obtaining task review results of the N target review devices; and determining whether the target review task has passed the review based on the N task review results.
[0008] In one embodiment, based on N task review results, determining whether a target review task has passed the review includes: identifying the N task review results; in response to identifying that the N task review results are the same, determining that the target review task has passed the review, and continuing to execute the next task; in response to identifying that the N task review results are different, determining that the target review task has not passed the review, and interrupting the review of the target review task and / or executing the branch task.
[0009] In one embodiment, N target review devices are selected from a review device cluster, including: monitoring a first configuration operation of a target review task, and determining first collaborative information of the target review task based on the first configuration operation, wherein the first collaborative information at least includes device information of the target review device required for the target review task; and determining N target review devices based on the first collaborative information.
[0010] In one embodiment, N target review devices are selected from a review device cluster, including: obtaining a task type for a target review task; obtaining a task label for each candidate review device in the review device cluster, wherein the task label corresponds to the task type; and based on the task type and the task label, selecting N target review devices from the review device cluster for the N target review tasks.
[0011] In one embodiment, before assigning N target review tasks to N target review devices for review, it also includes: monitoring a second configuration operation of the target review task, and determining second collaborative information of the target review task based on the second configuration operation, wherein the second collaborative information indicates the review content of the target review task.
[0012] In one embodiment, after obtaining the task review result of the target review device, it also includes: generating a review record of the target review task based on N task review results; generating a hidden display item based on the review record, using the task identifier of the target review task as a thumbnail display item, and displaying the thumbnail display item on the display interface of the RPA robot, wherein the hidden display item is hidden under the thumbnail display item.
[0013] In one embodiment, after displaying the thumbnail display item on the display interface of the RPA robot, it also includes: in response to monitoring a review result viewing operation for the thumbnail display item, expanding the hidden display item in the detail display area of the display interface to display at least one review record.
[0014] In one embodiment, displaying at least one review record includes: in response to a target review task failing the review, obtaining a failed review record of a failed review from the displayed review records, and highlighting the failed review record, and / or obtaining the review content of the failed review in the failed review record for highlighting.
[0015] On the second aspect, an embodiment of the present application provides a task review device combining RPA and AI, and the device includes: a generation module, which is used to obtain tasks that need to be reviewed in the RPA robot process, take the tasks that need to be reviewed as target review tasks, and copy the target review tasks to obtain N target review tasks; an allocation module, which is used to select N target review devices from the review device cluster, and allocate the N target review tasks to the N target review devices for review, where N is a positive integer greater than or equal to 2; an acquisition module, which is used to obtain task review results of N target review devices; a determination module, which is used to determine whether the target review task has passed the review based on the N task review results.
[0016] In one embodiment, the determination module is also used to: identify the review results of N tasks; in response to identifying that the review results of the N tasks are the same, determine that the target review task has passed the review and continue to execute the next task; in response to identifying that the review results of the N tasks are different, determine that the target review task has not passed the review, and interrupt the review of the target review task and / or execute the branch task.
[0017] In one embodiment, the device also includes a configuration module, which is used to: monitor a first configuration operation of a target review task, and determine first collaborative information of the target review task based on the first configuration operation, wherein the first collaborative information at least includes equipment information of a target review device required for the target review task; and determine N target review devices based on the first collaborative information.
[0018] In one embodiment, the configuration module is also used to: obtain the task type of the target review task; obtain the task label of each candidate review device in the review device cluster, wherein the task label corresponds to the task type; and select N target review devices from the review device cluster for N target review tasks based on the task type and the task label.
[0019] In one embodiment, the configuration module is further used to: monitor a second configuration operation of the target review task, and determine second collaborative information of the target review task based on the second configuration operation, wherein the second collaborative information indicates the review content of the target review task.
[0020] In one embodiment, the device also includes a display module, which is used to: generate a review record for a target review task based on N task review results; generate a hidden display item based on the review record, use the task identifier of the target review task as a thumbnail display item, and display the thumbnail display item on the display interface of the RPA robot, wherein the hidden display item is hidden under the thumbnail display item; in response to monitoring a review result viewing operation for the thumbnail display item, expand the hidden display item in the details display area of the display interface to display at least one review record.
[0021] In one embodiment, the display module is also used to: in response to the target review task failing the review, obtain the failed review record of the failed review from the displayed review record, and highlight the failed review record, and / or obtain the review content of the failed review in the failed review record for highlighting. In a third aspect, an embodiment of the present application provides an electronic device, which includes: a memory and a processor. The memory and the processor communicate with each other through an internal connection path, the memory is used to store instructions, the processor is used to execute the instructions stored in the memory, and when the processor executes the instructions stored in the memory, the processor executes the method in any one of the above-mentioned various embodiments.
[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a computer, the method in any one of the above-mentioned embodiments is executed.
[0023] The advantages or beneficial effects of the above technical solution include at least: the present application supports multiple target review devices to review the target review tasks to be reviewed, and compares the task review results of multiple target review devices, thereby avoiding losses to the company due to a single calculation error or a single operation error, improving the accuracy of the target review task results, and clarifying the differences in target review task processing, thereby improving efficiency for subsequent business correction and processing.
[0024] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present application will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in the present application and should not be regarded as limiting the scope of the present application.
[0026] Figure 1 This is a flowchart of a task review method combining RPA and AI shown in this application.
[0027] Figure 2 This is a schematic diagram of a review based on a target review task to be reviewed shown in the present application.
[0028] Figure 3 This is a flowchart of another task review method combining RPA and AI shown in this application.
[0029] Figure 4 This is a schematic diagram of performing a first configuration operation on a target review task as shown in the present application.
[0030] Figure 5 This is a schematic diagram of performing a second configuration operation on a target review task as shown in the present application.
[0031] Figure 6 A schematic diagram of a task details display interface shown in this application.
[0032] Figure 7 A schematic diagram of the details display area of the display interface of the RPA robot shown in this application.
[0033] Figure 8 This is a flowchart of another task review method combining RPA and AI shown in this application.
[0034] Fig. 9 This is a schematic diagram of a task review device combining RPA and AI shown in the present application.
[0035] Fig.10 This is a schematic diagram of an electronic device shown in this application. DETAILED DESCRIPTION
[0036] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.
[0037] In the description of the present application, the term "plurality" refers to two or more.
[0038] In the description of this application, the term "RPA robot process" refers to RPA automatically processing high-frequency business with clear rules and batches by simulating manual keyboard and mouse operation. It is suitable for operation processes with clear business rules, structured input and output within the enterprise, such as reading emails, reconciliation summary, checking files, generating files and reports, and other boring, repetitive, and standardized work, which can be completed by RPA robots. In the description of this application, the term "target review task" refers to tasks that need to be reviewed multiple times in the RPA robot process.
[0039] In the description of this application, the term "target review device" refers to a device selected from a review device cluster to perform a target review task in an RPA robot process.
[0040] In the description of this application, the term "candidate review device" refers to all devices in the review device cluster corresponding to the RPA robot process.
[0041] In the description of this application, the term "task review result" refers to the task result obtained after each target review device performs the target review task.
[0042] In the description of this application, the term "branch task" refers to other tasks on the same node of the RPA process as the target review task. For example, if the operating cost accounting and the consumables quantity accounting are reviewed on the same node of the RPA process, then the operating cost accounting and the consumables quantity accounting are each other's branch tasks.
[0043] In the description of this application, the term "task type" refers to the task type corresponding to each target review task. Optionally, the task type may include image review type, data collation type, text processing type, cost verification type, etc.
[0044] In the description of this application, the term "task label" refers to labeling the task type that the candidate review device can handle on each candidate review device in the review device cluster as the task label of the candidate review device. For example, if the task types that the candidate review device A can handle include image review type and data sorting type, then the image review type task label and the data sorting type task label are labeled on the candidate review device A.
[0045] In the description of this application, the term "first configuration operation" refers to the basic information configuration of the target review task and the information configuration of the target review device corresponding to the target review task. For example, the first configuration operation may include setting the action name of the target review task, setting whether the target review task needs to be reviewed, setting the number of target review devices corresponding to the target review task, or setting the numbers of N target review devices corresponding to the target review task if the target review task needs to be reviewed.
[0046] In the description of this application, the term "second configuration operation" refers to the configuration of the review content of the target review task. For example, the second configuration operation of the target review task may include the setting of the review capability name, review model, review extraction type and review content of the target review task.
[0047] In the description of the present application, the term "review record" refers to the information of N target review devices and their respective corresponding N task review results obtained after executing the target review task. These and other aspects of the embodiments of the present application will be clear with reference to the following description and drawings. In these descriptions and drawings, some specific implementations in the embodiments of the present application are specifically disclosed to represent some ways of implementing the principles of the embodiments of the present application, but it should be understood that the scope of the embodiments of the present application is not limited thereto. On the contrary, the embodiments of the present application include all changes, modifications and equivalents that fall within the spirit and connotation of the appended claims.
[0048] The following describes the task review method and device combining RPA and AI proposed in this application in conjunction with the accompanying drawings.
[0049] Figure 1 is a flowchart of a task review method combining RPA and AI in one embodiment of the present application, which is executed by an RPA robot. Figure 1 As shown, the method may include the following steps:
[0050] S101, obtaining tasks that need to be reviewed in the RPA robot process, taking the tasks that need to be reviewed as target review tasks, and copying the target review tasks to obtain N target review tasks.
[0051] RPA robots automatically process high-frequency businesses with clear rules and batch processing by simulating manual keyboard and mouse operations. It is suitable for operation processes within the enterprise with clear business rules, structured input and output, such as reading emails, reconciliation and summary, checking files, generating files and reports, and other boring, repetitive, and standardized work, which can all be completed by RPA robots.
[0052] In the RPA robot process, the Human-Machine Collaboration Center serves as the manual operation entrance, connecting the collaborative work of humans and robots to realize manual review and revision of the process. In an automated process, the Human-Machine Collaboration Center can assign tasks that require human judgment and decision-making to humans. Humans provide accurate input for robots through operations such as form information input and secondary information verification, thereby creating more and safer automation opportunities.
[0053] In certain scenarios, such as scenarios where payments can only be made when the financial and accounting calculations are consistent, scenarios where core processes require approval from multiple people, and scenarios where sensitive information in the financial field needs to be reconfirmed, there is a high possibility of error if only one manual confirmation is performed. In order to avoid losses caused by errors, tasks that need to be reviewed in the RPA robot process are reviewed multiple times as target review tasks.
[0054] Figure 2 This is a schematic diagram of reviewing based on the target review tasks to be reviewed, such as Figure 2 As shown, the target review task to be reviewed is obtained, and the target review task is copied to obtain N target review tasks. Exemplarily, if the target review task is target review task A, target review task A is copied to generate N target review tasks A.
[0055] S102, selecting N target review devices from the review device cluster, and assigning N target review tasks to the N target review devices for review, where N is a positive integer greater than or equal to 2.
[0056] The review device cluster includes all candidate review devices that can process the review task. Among all the candidate review devices, N target review devices corresponding to the target review task are selected, and the N target review tasks are assigned to the selected N target review devices for review. Wherein, N is a positive integer greater than or equal to 2, for example, N can be a positive integer such as 5 or 10.
[0057] Optionally, when selecting N target review devices, the N target review devices may be determined based on the target review device information set by the operator at the beginning of the RPA process, for example, based on the target review device numbers set in advance.
[0058] Optionally, when selecting N target review devices, the RPA robot process can automatically determine the N target review devices to be assigned for the target review task based on the classification of the target review task.
[0059] For example, Figure 2As shown, N target review tasks A are assigned to N target review devices for review, and the N target review devices are target review device A, target review device B, target review device C...target review device N.
[0060] S103, obtaining task review results of N target review devices.
[0061] After N target review devices complete the target review task, the task review results corresponding to each of the N target review devices are obtained.
[0062] For example, Figure 2 As shown, after the target review device A completes the target review task, it generates a task review result A; after the target review device B completes the target review task, it generates a task review result B; after the target review device C completes the target review task, it generates a task review result C... After the target review device N completes the target review task, it generates a task review result N.
[0063] S104: Based on the N task review results, determine whether the target review task has passed the review.
[0064] According to the N task review results obtained above, the N task review results are analyzed to determine whether the target review task has passed the review.
[0065] For example, Figure 2 As shown, if the review results of N tasks are the same, it is considered that the target review task A has passed the review.
[0066] For example, Figure 2 As shown, if there are differences in the review results of N tasks, for example, when N is equal to 10, there is a task review result that is different from the review results of the other 9 tasks, then it is considered that the target review task A has not passed the review.
[0067] The embodiment of the present application proposes a task review method that combines RPA and AI, by obtaining the tasks that need to be reviewed in the RPA robot process, taking the tasks that need to be reviewed as target review tasks, and copying the target review tasks to obtain N target review tasks; selecting N target review devices from the review device cluster, and assigning the N target review tasks to the N target review devices for review, where N is a positive integer greater than or equal to 2; obtaining the task review results of the target review devices; based on the N task review results, determining whether the target review task has passed the review. The present application supports multiple target review devices to review the target review tasks to be reviewed, and compares the task review results of multiple target review devices, avoiding losses to the company due to a single calculation error or a single operation error, improving the accuracy of the target review task results, and clarifying the differences in target review task processing, so as to improve the efficiency of subsequent business correction and processing.
[0068] Figure 3 is a flowchart of a task review method combining RPA and AI in one embodiment of the present application, which is executed by an RPA robot. Figure 3 As shown, the method may include the following steps:
[0069] S301, obtaining tasks that need to be reviewed in the RPA robot process, taking the tasks that need to be reviewed as target review tasks, and copying the target review tasks to obtain N target review tasks.
[0070] Regarding the implementation method of step S301, reference may be made to the implementation methods in the various embodiments of the present application, and no further details will be given here.
[0071] S302, monitoring a first configuration operation of a target review task, and determining first coordination information of the target review task according to the first configuration operation, wherein the first coordination information at least includes equipment information of a target review equipment required for the target review task.
[0072] In order to determine the N target review devices for the target review task, the RPA robot needs to monitor the first configuration operation of the target review task, wherein the first configuration operation includes the information configuration of the target review task and the device information configuration of the target review device corresponding to the target review task. For example, the device information of the configured target review device may include information such as the number of devices, the device number, and the device identification.
[0073] For example, Figure 4 This is a schematic diagram of performing the first configuration operation on the target review task, such as Figure 4As shown, the operator performs a first configuration operation on the target review task, wherein the first configuration operation may include setting the action name of the target review task, setting whether the target review task needs to be reviewed, setting the number of target review devices corresponding to the target review task, or setting the numbers of N target review devices corresponding to the target review task if a review is required.
[0074] The various configuration information of the target review task set by the first configuration operation is used as the first collaborative information of the target review task, wherein the first collaborative information should at least include the equipment information of the target review equipment required for the target review task. Exemplarily, the first collaborative information may indicate the equipment information of the target review equipment required for the target review task, wherein the equipment information may be the number of target review equipment, the serial number of the target review equipment, etc.
[0075] S303: Determine N target review devices according to the first collaborative information.
[0076] According to the first coordination information determined above, N target review devices are determined from all candidate review devices in the review device cluster as target review devices corresponding to the target review task.
[0077] For example, if the first collaborative information indicates that there are three target review devices to be reviewed, and the first collaborative information indicates that the target review devices to be reviewed are candidate review devices numbered 12, 16, and 27 in the review device cluster, then based on the first collaborative information, the candidate review devices numbered 12, 16, and 27 are determined from the review device cluster as the three target review devices corresponding to the target review task.
[0078] S304, monitoring a second configuration operation of the target review task, and determining second coordination information of the target review task based on the second configuration operation, wherein the second coordination information indicates a review content of the target review task.
[0079] After determining the N target review devices corresponding to the target review task as mentioned above, it is also necessary to determine the review content corresponding to the target review task. When determining the review content corresponding to the target review task, it is necessary to monitor the second configuration operation of the target review task. The second configuration operation of the target review task is the configuration of the review content of the target review task, and based on the second configuration operation, the second collaborative information of the target review task is determined, wherein the second collaborative information includes the review content corresponding to the target review task.
[0080] For example, Figure 5 This is a schematic diagram of performing the second configuration operation on the target review task, such as Figure 5As shown, the second configuration operation of the target review task may include setting the review capability name, review model, review extraction type and review content of the target review task, and using the set review capability name, review model, review extraction type and review content of the target review task as the second collaborative information of the target review task. Figure 5 As shown, the review capability name of the target review task is general multi-invoice recognition, the review model of the target review task is model 1, the review extraction type of the target review task is special value-added tax invoice, and the review content of the target review task includes invoice number, purchaser name, seller taxpayer identification number, etc.
[0081] S305, assigning N target review tasks to N target review devices for review.
[0082] The N target review tasks generated based on the target review tasks are respectively assigned to the N target review devices determined above for review.
[0083] S306, obtaining task review results of N target review devices.
[0084] After N target review devices complete the target review task, the task review results corresponding to each of the N target review devices are obtained.
[0085] S307: Generate a review record of the target review task based on the N task review results.
[0086] In order to facilitate the review record and review result of the target review task to be viewed in the task chain after the target review task is completed, the review record and review result of the target review task are generated according to the task review results corresponding to each of the N target review devices. Optionally, the review record of the target review task may include the numbers of the N target review devices and their corresponding task review results.
[0087] For example, if the target review task is cost accounting, corresponding to the three target review equipment, the review record can be generated as: target review equipment 1-task review result 100,000 yuan; target review equipment 2-task review result 100,000 yuan, target review equipment 3-task review result 100,000 yuan.
[0088] S308, generating a hidden display item based on the review record, using the task identifier of the target review task as a thumbnail display item, and displaying the thumbnail display item on the display interface of the RPA robot, wherein the hidden display item is hidden under the thumbnail display item.
[0089] In the RPA robot process, humans can view the results of each step of the RPA robot process. To facilitate manual viewing, hidden display items are generated based on the review records, and the task identifier of the target review task is displayed as a thumbnail display item on the display interface of the RPA robot. The hidden display item is hidden under the thumbnail display item. When the thumbnail display item is clicked, the review record corresponding to the hidden display item is displayed on the display interface.
[0090] Figure 6 This is a schematic diagram of a task details display interface shown in an embodiment of the present application, such as Figure 6 As shown, the task details display interface may include the task identification of the target review task, the basic information of the target review task, the acceptance target of the target review task, the functional description of the target review task and the processing result of the target review task.
[0091] S309: In response to monitoring a review result viewing operation for a thumbnail display item, a hidden display item is expanded in a detail display area of the display interface to display at least one review record.
[0092] To facilitate manual review of the results of each task in the RPA robot process, the RPA robot continuously monitors the review results of the target review task. If the RPA robot monitors the review result review operation for the target review task, the review record of the target review task is displayed in the details display area of the RPA robot display interface. The details display area of the display interface can display the review record of one target review task or multiple target review tasks.
[0093] Figure 7 This is a schematic diagram of the details display area of the display interface of the RPA robot shown in the embodiment of the present application, such as Figure 7 As shown, the details display area of the display interface of the RPA robot may include the number of the target review task, the related tasks of the target review task, the creation time of the target review task, the difference comparison of the target review task, the review results of multiple tasks of the target review task, the name of the review employee corresponding to the target review task, etc.
[0094] If the target review task fails the review, the failed review records of the failed review are obtained from the displayed review records, and the failed review records are highlighted. For example, the inconsistent task review results can be marked with a red frame or yellow to display them prominently.
[0095] S310 , in response to the N task review results being the same, determining that the target review task has passed the review, and continuing to execute the next task.
[0096] The N task review results are identified. If the N task review results corresponding to the N target review devices are the same, for example, when N is equal to 10, if the 10 task review results are the same, then it is considered that the target review task has passed the review, and the next task of the RPA robot process can be executed.
[0097] S311, in response to the N task review results being different, it is determined that the target review task has not passed the review, and the review of the target review task is interrupted and / or the branch task is executed.
[0098] The N task review results are identified. If the N task review results corresponding to the N target review devices are different, for example, when N is equal to 10, there is one task review result that is different from the other nine task review results, then it is considered that the target review task has not passed the review.
[0099] Optionally, if the target review task fails the review, and there are other branch tasks of the target review task, the review of the target review task is interrupted, and other branch tasks of the target review task can be executed first. Branch tasks refer to other tasks on the same node of the RPA process as the target review task. For example, if the operating cost accounting and the consumables quantity accounting are reviewed on the same node of the RPA process, the operating cost accounting and the consumables quantity accounting are each other's branch tasks.
[0100] Optionally, when the target review task fails the review, if there are no other branch tasks for the target review task, the review of the target review task is directly interrupted, that is, the RPA robot process is interrupted at the target review task.
[0101] The embodiment of the present application supports multiple target review devices to review the target review tasks to be reviewed, and compares the task review results of the multiple target review devices. When the review results of N tasks are different, it is determined to interrupt the review of the target review task and / or execute the branch task, which is beneficial to improving the risk control capability of the robot process, and the comparison results are displayed in the details display area of the display interface for manual viewing, thereby improving the efficiency of subsequent business correction and processing.
[0102] The above-mentioned embodiment requires manual setting of the target review device for performing the target review task review before the RPA robot process is carried out. In order to improve the intelligence of the RPA robot, the following introduces an implementation method in which the RPA robot can automatically assign multiple target review devices to the target review task.
[0103] Figure 8 is a flowchart of a task review method combining RPA and AI in one embodiment of the present application, which is executed by an RPA robot. Figure 8As shown, the method may include the following steps:
[0104] S801, obtaining tasks that need to be reviewed in the RPA robot process, taking the tasks that need to be reviewed as target review tasks, and copying the target review tasks to obtain N target review tasks.
[0105] Regarding the implementation method of step S801, reference may be made to the implementation methods in the various embodiments of the present application, and no further details will be given here.
[0106] S802, obtaining the task type of the target review task.
[0107] Each target review task has its corresponding task type. Optionally, the task type may include image review type, data sorting type, text processing type, cost verification type, etc. In order to improve the intelligence of the RPA robot and enable the RPA robot to automatically assign multiple target review devices to the target review task, it is necessary to obtain the task type of the target review task.
[0108] S803, obtaining a task label of each candidate review device in the review device cluster, wherein the task label corresponds to the task type.
[0109] On each candidate review device in the review device cluster, the task type that the candidate review device can handle is marked as the task label of the candidate review device. For example, if the task types that the candidate review device A can handle include image review type and data sorting type, then the image review type task label and the data sorting type task label are marked on the candidate review device A.
[0110] S804 , based on the task type and the task tag, select N target review devices from the review device cluster for the N target review tasks.
[0111] After determining the task type of the target review task, based on the task type of the target review task, find N candidate review devices from the review device cluster that carry task tags consistent with the task type of the target review task, and use the selected N candidate review devices as the N target review devices for executing the target review task. The value of N can be set in advance in the RPA process. For example, if the task type of the target review task C is a cost verification type, if N is set to 5, then find 5 candidate review devices with a cost verification type task tag from all candidate review devices, and use these 5 selected candidate review devices as the target review devices corresponding to the target review task.
[0112] S805, assigning N target review tasks to N target review devices for review.
[0113] Regarding the implementation method of step S805, reference may be made to the implementation methods in the various embodiments of the present application, and no further details will be given here.
[0114] S806, obtaining task review results of N target review devices.
[0115] Regarding the implementation method of step S806, reference may be made to the implementation methods in the various embodiments of the present application, and no further details will be given here.
[0116] S807, based on the N task review results, determine whether the target review task has passed the review.
[0117] Regarding the implementation method of step S807, reference may be made to the implementation methods in the various embodiments of the present application, and no further details will be given here.
[0118] The embodiment of the present application automatically allocates multiple target review devices to the target review task according to the task type of the target review task and the task label of the candidate review device. This is more convenient and efficient than manually setting up multiple target review devices. Multiple target review devices review the target review tasks to be reviewed, thereby avoiding losses to the company due to a single calculation error or a single operation error, improving the accuracy of the target review task results, and clarifying the differences in target review task processing, thereby improving efficiency for subsequent business correction and processing.
[0119] Fig. 9 is a schematic diagram of a task review device combining RPA and AI according to an embodiment of the present application. Fig. 9 As shown, the task review device 900 combining RPA and AI includes a generation module 91, an allocation module 92, an acquisition module 93 and a determination module 94, wherein:
[0120] The generation module 91 is used to obtain the tasks that need to be reviewed in the RPA robot process, take the tasks that need to be reviewed as target review tasks, and copy the target review tasks to obtain N target review tasks.
[0121] The allocation module 92 is used to select N target review devices from the review device cluster and allocate N target review tasks to the N target review devices for review, where N is a positive integer greater than or equal to 2.
[0122] The acquisition module 93 is used to obtain N task review results of the target review equipment.
[0123] The determination module 94 is used to determine whether the target review task has passed the review based on the N task review results.
[0124] Furthermore, the determination module 94 is also used to: identify the review results of N tasks; in response to identifying that the review results of the N tasks are the same, determine that the target review task has passed the review and continue to execute the next task; in response to identifying that the review results of the N tasks are different, determine that the target review task has not passed the review, and interrupt the review of the target review task and / or execute the branch task.
[0125] Furthermore, the task review device 900 combining RPA and AI also includes a configuration module 95, which is used to: monitor the first configuration operation of the target review task, and determine the first collaborative information of the target review task based on the first configuration operation, wherein the first collaborative information at least includes the equipment information of the target review equipment required for the target review task; determine N target review equipment based on the first collaborative information.
[0126] Furthermore, configuration module 95 is also used to: obtain the task type of the target review task; obtain the task label of each candidate review device in the review device cluster, wherein the task label corresponds to the task type; and based on the task type and the task label, select N target review devices from the review device cluster for N target review tasks.
[0127] Furthermore, the configuration module 95 is also used to: monitor the second configuration operation of the target review task, and determine the second coordination information of the target review task based on the second configuration operation, wherein the second coordination information indicates the review content of the target review task.
[0128] Furthermore, the task review device 900 combining RPA and AI also includes a display module 96, which is used to: generate a review record for a target review task based on N task review results; generate a hidden display item based on the review record, use the task identifier of the target review task as a thumbnail display item, and display the thumbnail display item on the display interface of the RPA robot, wherein the hidden display item is hidden under the thumbnail display item; in response to monitoring a review result viewing operation for the thumbnail display item, expand the hidden display item in the details display area of the display interface to display at least one review record.
[0129] Furthermore, the display module 96 is also used to: in response to the target review task failing the review, obtain the failed review record from the displayed review record, and highlight the failed review record, and / or obtain the review content of the failed review in the failed review record for highlighting.
[0130] Fig.10 FIG. 1 is a block diagram showing a structure of an electronic device according to an embodiment of the present application. Fig.10As shown, the electronic device includes: a memory 1010 and a processor 1020, wherein the memory 1010 stores a computer program that can be run on the processor 1020. When the processor 1020 executes the computer program, the task review method combining RPA and AI in the above embodiment is implemented. The number of the memory 1010 and the processor 1020 can be one or more.
[0131] The electronic device also includes:
[0132] The communication interface 1030 is used to communicate with external devices and perform data exchange transmission.
[0133] If the memory 1010, the processor 1020 and the communication interface 1030 are implemented independently, the memory 1010, the processor 1020 and the communication interface 1030 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.10 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0134] Optionally, in a specific implementation, if the memory 1010, the processor 1020 and the communication interface 1030 are integrated on a chip, the memory 1010, the processor 1020 and the communication interface 1030 can communicate with each other through an internal interface.
[0135] An embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements a task review method combining RPA and AI provided in an embodiment of the present application.
[0136] An embodiment of the present application also provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present application.
[0137] An embodiment of the present application also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided in the embodiment of the application.
[0138] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced RISC machines (ARM) architecture.
[0139] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM).
[0140] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
[0141] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.
[0142] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.
[0143] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.
[0144] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.
[0145] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.
[0146] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.
[0147] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A task review method combining robotic process automation (RPA) and artificial intelligence (AI). It is characterized in that Executed by an RPA robot, the method includes: Obtain tasks that need to be reviewed in the RPA robot process, use the tasks that need to be reviewed as target review tasks, and copy the target review tasks to obtain N target review tasks; Select N target review devices from the review device cluster, and assign the N target review tasks to the N target review devices for review, where N is a positive integer greater than or equal to 2; Obtaining task review results of N target review devices; Based on the N task review results, determine whether the target review task has passed the review.
2. The method according to claim 1, It is characterized in that The determining whether the target review task has passed the review based on the N task review results includes: Identifying N of the task review results; In response to identifying that the N task review results are all the same, determining that the target review task has passed the review, and continuing to execute the next task; In response to identifying that the review results of the N tasks are different, it is determined that the target review task has not passed the review, and the review of the target review task is interrupted and / or a branch task is executed.
3. The method according to claim 1, It is characterized in that The step of selecting N target review devices from the review device cluster includes: Monitoring a first configuration operation of the target review task, and determining first coordination information of the target review task according to the first configuration operation, wherein the first coordination information at least includes equipment information of the target review equipment required for the target review task; According to the first collaborative information, N target review devices are determined.
4. The method according to claim 1, It is characterized in that The step of selecting N target review devices from the review device cluster includes: Obtaining the task type of the target review task; Obtaining a task label of each candidate review device in the review device cluster, wherein the task label corresponds to a task type; Based on the task type and the task label, N target review devices are selected from the review device cluster for the N target review tasks.
5. The method according to claim 1, It is characterized in that Before allocating the N target review tasks to the N target review devices for review, the method further includes: A second configuration operation of the target review task is monitored, and based on the second configuration operation, second coordination information of the target review task is determined, wherein the second coordination information indicates a review content including the target review task.
6. The method according to claim 1, It is characterized in that After obtaining the task review result of the target review device, the method further includes: Based on the N task review results, generating a review record for the target review task; A hidden display item is generated based on the review record, and the task identifier of the target review task is used as a thumbnail display item. The thumbnail display item is displayed on the display interface of the RPA robot, wherein the hidden display item is hidden under the thumbnail display item.
7. The method according to claim 6, It is characterized in that After displaying the thumbnail display item on the display interface of the RPA robot, the method further includes: In response to monitoring a review result viewing operation for the thumbnail display item, the hidden display item is expanded in the detail display area of the display interface to display at least one of the review records.
8. The method according to claim 7, It is characterized in that The presenting of at least one of the review records includes: In response to the target review task failing the review, a failed review record of the failed review is obtained from the displayed review records, and the failed review record is highlighted, and / or the review content of the failed review record of the failed review is obtained and highlighted.
9. A task review device combining robotic process automation (RPA) and artificial intelligence (AI). It is characterized in that The device comprises: A generation module is used to obtain tasks that need to be reviewed in the RPA robot process, take the tasks that need to be reviewed as target review tasks, and copy the target review tasks to obtain N target review tasks; An allocation module, used for selecting N target review devices from the review device cluster, and allocating the N target review tasks to the N target review devices for review, wherein N is a positive integer greater than or equal to 2; An acquisition module, used for acquiring task review results of N target review devices; A determination module is used to determine whether the target review task has passed the review based on the N task review results.
10. The device according to claim 9, It is characterized in that The determining module is further used for: Identifying N of the task review results; In response to identifying that the N task review results are all the same, determining that the target review task has passed the review, and continuing to execute the next task; In response to identifying that the review results of the N tasks are different, the target review task fails the review, and it is determined to interrupt the review of the target review task and / or execute a branch task.
11. The device according to claim 9, It is characterized in that The device further includes a configuration module, wherein the configuration module is configured to: Monitoring a first configuration operation of the target review task, and determining first coordination information of the target review task according to the first configuration operation, wherein the first coordination information at least includes equipment information of the target review equipment required for the target review task; According to the first collaborative information, N target review devices are determined.
12. The device according to claim 11, It is characterized in that The configuration module is also used for: Obtaining the task type of the target review task; Obtaining a task label of each candidate review device in the review device cluster, wherein the task label corresponds to a task type; Based on the task type and the task label, N target review devices are selected from the review device cluster for the N target review tasks.
13. The device according to claim 11, It is characterized in that The configuration module is also used for: A second configuration operation of the target review task is monitored, and based on the second configuration operation, second coordination information of the target review task is determined, wherein the second coordination information indicates a review content including the target review task.
14. The device according to claim 9, It is characterized in that The device further comprises a display module, wherein the display module is used to: Based on the N task review results, generating a review record for the target review task; generating a hidden display item based on the review record, using the task identifier of the target review task as a thumbnail display item, and displaying the thumbnail display item on the display interface of the RPA robot, wherein the hidden display item is hidden under the thumbnail display item; In response to monitoring a review result viewing operation for the thumbnail display item, the hidden display item is expanded in the detail display area of the display interface to display at least one of the review records.
15. An electronic device, It is characterized in that include: A processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the method according to any one of claims 1 to 8.
16. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.
