Method and device for realizing robot operation status of IA based on RPA and AI

Abstract

The present disclosure proposes a method for realizing the robot running status of IA based on RPA and AI. The method includes: after the RPA robot obtains the current business node to be executed, it calls the natural language processing NLP service to process the current business node to be executed to determine the type of the current business node to be executed. In the case that the type of the current business node to be executed is a screenshot business, a screenshot of the business node corresponding to the screenshot business can be obtained. After that, the screenshot of the business node can be sent to the RPA robot console so that the RPA robot console determines the running status of the RPA robot according to the screenshot. Thus, the type of the business node is determined to be a screenshot business through the NLP service, and then the running status of the RPA robot can be automatically determined according to the obtained screenshot of the business node, thereby realizing the robot running status of IA, realizing automatic monitoring of the running status of the RPA robot, and improving the operating efficiency of the equipment.

Description

Technical Field

[0001] The present disclosure relates to the field of automation technology, and more particularly to a method and device for realizing the robot operation status of IA based on RPA and AI. Background Art

[0002] Robotic Process Automation (RPA) 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] Intelligent Automation (IA) is a general term for a range of technologies from robotic process automation to artificial intelligence. It combines RPA with multiple AI technologies, including optical character recognition (OCR), intelligent character recognition (ICR), process mining, deep learning (DL), machine learning (ML), natural language processing (NLP), automatic speech recognition (ASR), text to speech (TTS), and computer vision (CV), to create end-to-end business processes that can think, learn, and adapt. This covers the entire process from process discovery and automation to automatic and continuous data collection, understanding the meaning of data, and using data to manage and optimize business processes.

[0005] With the continuous development of automation technology, RPA robots have been widely used. However, during the operation of RPA robots, manual monitoring of their operating status is required, which wastes manpower time and places high demands on the monitoring personnel. Summary of the Invention

[0006] The present disclosure provides a method for implementing the robot operating status of an IA based on RPA and AI to solve the problem of low equipment operating efficiency. The technical solution is as follows:

[0007] In a first aspect, embodiments of the present disclosure provide a method for implementing an IA robot operating state based on RPA and AI, including:

[0008] The RPA robot obtains the business node to be executed;

[0009] Call the Natural Language Processing (NLP) service to process the business node to be executed to determine the type of the business node to be executed.

[0010] In response to the current service node to be executed being a screenshot service, obtaining a screenshot of the service node corresponding to the screenshot service;

[0011] Send the business node screenshot to the RPA robot console so that the RPA robot console can determine the running status of the RPA robot based on the screenshot.

[0012] In one embodiment, obtaining a screenshot of a service node corresponding to a screenshot service includes:

[0013] Determine the size and / or position of the screenshot frame corresponding to the screenshot service;

[0014] According to the size and / or position of the screenshot frame, a screenshot of the service node corresponding to the screenshot service is obtained.

[0015] In one embodiment, sending a screenshot of a service node to an RPA robot console includes:

[0016] Call the optical character recognition (OCR) service to recognize the business node screenshot to obtain the characters contained in the business node screenshot;

[0017] Determine the degree of match between the character and the sensitive words in the preset sensitive dictionary;

[0018] When the matching degree between any character and any sensitive word is greater than a threshold, any character is masked to obtain a screenshot of the masked business node;

[0019] Send the masked business node screenshot to the RPA robot console.

[0020] In one embodiment, sending a screenshot of a service node to an RPA robot console includes:

[0021] Send the business node screenshot and the corresponding business node ID to the RPA robot console.

[0022] In a second aspect, embodiments of the present disclosure provide a method for implementing the robot operating status of IA based on RPA and AI, including:

[0023] Receive business node screenshots sent by the RPA robot;

[0024] Obtain reference screenshots corresponding to the RPA robot;

[0025] Determine the running status of the RPA robot based on the matching degree between the business node screenshot and the reference screenshot.

[0026] In one embodiment, obtaining a reference screenshot corresponding to the RPA robot includes:

[0027] Obtain the reference screenshots of the RPA robot based on the target business process of the RPA robot.

[0028] In one embodiment, obtaining a reference screenshot corresponding to the RPA robot includes:

[0029] Determine the business node ID associated with the business node screenshot;

[0030] Obtain a reference screenshot set for the RPA robot based on the target business process.

[0031] From the reference screenshot set, obtain a reference screenshot corresponding to the business node identifier.

[0032] In one embodiment, determining the operating status of the RPA robot based on the matching degree between the service node screenshot and the reference screenshot includes:

[0033] Call the optical character recognition (OCR) service to recognize the screenshot and obtain the characters contained in the screenshot;

[0034] Determine the degree of match between the character and the sensitive words in the preset sensitive dictionary;

[0035] When the matching degree between any character and any sensitive word is greater than a threshold, any character is masked to obtain a screenshot of the masked business node;

[0036] The running status of the RPA robot is determined based on the matching degree between the masked business node screenshot and the reference screenshot.

[0037] In one embodiment, before determining the matching degree between the character and the sensitive word in the preset sensitive dictionary, it also includes: obtaining the preset sensitive dictionary according to the target business process corresponding to the RPA robot.

[0038] In a third aspect, an embodiment of the present disclosure provides a device for implementing the robot operating status of IA based on RPA and AI, including:

[0039] The acquisition module is used by the RPA robot to obtain the business node to be executed;

[0040] The determination module is used to call the natural language processing (NLP) service to process the business node to be executed to determine the type of the business node to be executed;

[0041] A screenshot module, configured to obtain a screenshot of the service node corresponding to the screenshot service in response to the current service node to be executed being the screenshot service;

[0042] The sending module is used to send the business node screenshot to the RPA robot console so that the RPA robot console can determine the running status of the RPA robot based on the screenshot.

[0043] In one embodiment, the screenshot module is specifically used to:

[0044] Determine the size and / or position of the screenshot frame corresponding to the screenshot service;

[0045] According to the size and / or position of the screenshot frame, a screenshot of the service node corresponding to the screenshot service is obtained.

[0046] In one embodiment, the sending module is specifically configured to:

[0047] Call the optical character recognition (OCR) service to recognize the business node screenshot to obtain the characters contained in the business node screenshot;

[0048] Determine the degree of match between the character and the sensitive words in the preset sensitive dictionary;

[0049] When the matching degree between any character and any sensitive word is greater than a threshold, any character is masked to obtain a screenshot of the masked business node;

[0050] Send the masked business node screenshot to the RPA robot console.

[0051] In one embodiment, the sending module is specifically configured to:

[0052] Send the business node screenshot and the corresponding business node ID to the RPA robot console.

[0053] In a fourth aspect, an embodiment of the present disclosure provides a device for implementing the robot operating status of IA based on RPA and AI, including:

[0054] The receiving module is used to receive business node screenshots sent by the RPA robot;

[0055] The acquisition module is used to obtain reference screenshots corresponding to the RPA robot;

[0056] The determination module is used to determine the operating status of the RPA robot based on the matching degree between the business node screenshot and the reference screenshot.

[0057] In one embodiment, the acquisition module is specifically configured to:

[0058] Obtain the reference screenshots of the RPA robot based on the target business process of the RPA robot.

[0059] In one embodiment, the acquisition module is specifically configured to:

[0060] Determine the business node ID associated with the business node screenshot;

[0061] Obtain a reference screenshot set for the RPA robot based on the target business process.

[0062] From the reference screenshot set, obtain a reference screenshot corresponding to the business node identifier.

[0063] In one embodiment, the determination module is specifically configured to:

[0064] Call the optical character recognition (OCR) service to recognize the screenshot and obtain the characters contained in the screenshot;

[0065] Determine the degree of match between the character and the sensitive words in the preset sensitive dictionary;

[0066] When the matching degree between any character and any sensitive word is greater than a threshold, any character is masked to obtain a screenshot of the masked business node;

[0067] The running status of the RPA robot is determined based on the matching degree between the masked business node screenshot and the reference screenshot.

[0068] In one embodiment, the acquisition module is further configured to acquire a preset sensitive dictionary according to a target business process corresponding to the RPA robot.

[0069] In a fifth aspect, embodiments of the present disclosure provide a device for implementing the robot operating state of IA based on RPA and AI, the device comprising: a memory and a processor. The memory and the processor communicate with each other via an internal connection path, the memory is configured to store instructions, and the processor is configured to execute the instructions stored in the memory. When the processor executes the instructions stored in the memory, the processor executes the method described in any of the aforementioned embodiments.

[0070] In a sixth aspect, an embodiment of the present disclosure 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.

[0071] The advantages or beneficial effects of the above technical solution include at least the following: after the RPA robot obtains the current business node to be executed, it calls the natural language processing (NLP) service to process the current business node to be executed to determine the type of the current business node to be executed. If the type of the current business node to be executed is a screenshot business, a screenshot of the business node corresponding to the screenshot business can be obtained. Afterwards, the screenshot of the business node can be sent to the RPA robot console so that the RPA robot console determines the operating status of the RPA robot based on the screenshot. Thus, by determining that the type of the business node is a screenshot business through the NLP service, the operating status of the RPA robot can be automatically determined based on the obtained screenshot of the business node, thereby realizing the operating status of the IA robot, realizing automatic monitoring of the operating status of the RPA robot, and improving the operating efficiency of the equipment.

[0072] 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 disclosure will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments provided in accordance with the present disclosure and should not be regarded as limiting the scope of the present disclosure.

[0074] Figure 1 A flowchart of a method for implementing the robot operation status of IA based on RPA and AI provided in an embodiment of the present disclosure;

[0075] Figure 2 A flowchart of another method for implementing the robot operating status of IA based on RPA and AI provided in an embodiment of the present disclosure;

[0076] Figure 3 A flowchart of another method for implementing the robot operating status of IA based on RPA and AI provided in an embodiment of the present disclosure;

[0077] Figure 4 A schematic diagram of a service node screenshot provided in an embodiment of the present disclosure;

[0078] Figure 5 A schematic diagram of a service node screenshot provided in an embodiment of the present disclosure;

[0079] Figure 6A flowchart of another method for implementing the robot operating status of IA based on RPA and AI provided in an embodiment of the present disclosure;

[0080] Figure 7 A flowchart of another method for implementing the robot operating status of IA based on RPA and AI provided in an embodiment of the present disclosure;

[0081] Figure 8 A flowchart of another method for implementing the robot operating status of IA based on RPA and AI provided in an embodiment of the present disclosure;

[0082] Figure 9 A schematic diagram of viewing a screenshot of a service node provided in an embodiment of the present disclosure;

[0083] Figure 10 A schematic diagram of enabling the screenshot coding function provided in an embodiment of the present disclosure;

[0084] Figure 11 A schematic diagram of the structure of a device for implementing the robot operation status of IA based on RPA and AI provided in an embodiment of the present disclosure;

[0085] Figure 12 A schematic diagram of the structure of another device for implementing the robot operation status of IA based on RPA and AI provided in an embodiment of the present disclosure;

[0086] Figure 13 A block diagram of a computer device that implements the robot operating state of IA based on RPA and AI provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0087] The following describes in detail embodiments of the present disclosure, examples of which 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 intended only to explain the present disclosure and are not to be construed as limiting the present disclosure.

[0088] In the description of the present disclosure, the term "plurality" refers to two or more.

[0089] In this disclosure, the term "RPA robot" refers to any robot that can invoke RPA programs to implement corresponding services or functions. It can be manually started as needed or automatically started when specific trigger conditions are met. Tasks can be orchestrated, and processes can be backtracked.

[0090] In this disclosure, the term "console" refers to a platform for unified management of multiple process robots within an enterprise. It allows for rapid batch dispatch of tasks and provides the process robots with the data, credentials, and files they need for runtime. It also allows for real-time monitoring of the process robots' operational status and review of their historical records.

[0091] In this disclosure, the term "RPA process" refers to a series of activities related to customer value creation. It is an automated work process consisting of orderly process nodes and execution methods. This process may include specific steps such as interface automation, AI recognition, and data reading and writing.

[0092] In the description of this disclosure, the term "business node" refers to any process node during the operation of an RPA robot.

[0093] In the description of this disclosure, the term "screenshot service" refers to a service that triggers an RPA robot to capture the current screen.

[0094] In the description of this disclosure, the term "business node screenshot" is a screenshot of the device operation interface when the RPA robot runs on the business node.

[0095] In the description of this disclosure, the term "sensitive dictionary" refers to a dictionary containing sensitive words in various fields, or it may also be a dictionary containing sensitive words related to the business process executed by RPA.

[0096] In the description of this disclosure, the term "service node identifier" refers to any information that can uniquely identify a service node, such as a service node number corresponding to a service node.

[0097] In the description of this disclosure, the term "reference screenshot" is a screenshot of the device operation interface of the RPA robot in normal operation.

[0098] These and other aspects of the embodiments of the present disclosure will become apparent with reference to the following description and accompanying drawings. In these descriptions and accompanying drawings, some specific implementations of the embodiments of the present disclosure are disclosed to illustrate some ways of implementing the principles of the embodiments of the present disclosure, but it should be understood that the scope of the embodiments of the present disclosure is not limited thereby. On the contrary, the embodiments of the present disclosure include all changes, modifications, and equivalents that fall within the spirit and scope of the appended claims.

[0099] Typically, during the operation of an RPA robot, anomalies may occur, requiring timely human monitoring and handling, resulting in low equipment operating efficiency. In this disclosure, by matching screenshots of the RPA robot's interface during operation with screenshots of the RPA robot's interface in normal operation, the RPA robot's status can be determined, thereby achieving automatic monitoring of the RPA robot's operating status and improving the equipment's operating efficiency.

[0100] The following describes a method for implementing a robot operating state of intelligent automation (IA) based on process automation (Robotic Process Automation, RPA) and artificial intelligence (Artificial Intelligence, AI) according to an embodiment of the present disclosure in conjunction with the accompanying drawings.

[0101] Figure 1 This is a flowchart of a method for implementing the robot operation status of IA based on RPA and AI according to an embodiment of the present disclosure. The method is executed by an RPA robot, such as Figure 1 As shown, the method may include the following steps:

[0102] Step S101: The RPA robot obtains the business node to be executed.

[0103] A business node can be any process node during the RPA robot's operation. Furthermore, because RPA robots execute the business processes corresponding to each business during actual operation, a business process can contain multiple business nodes, and the RPA robot can execute the corresponding business process based on the order of the business nodes in each business process.

[0104] In this disclosure, users can set the execution order of each business node when editing a business process. As a result, the RPA robot can determine the current business node to be executed based on the execution order of each business node in the current business process.

[0105] Step S102: calling a natural language processing (NLP) service to process the current service node to be executed, so as to determine the type of the current service node to be executed.

[0106] The types of business nodes may include screenshot business types and non-screenshot business types, and the screenshot business may be a business that triggers the RPA robot to capture the current screen.

[0107] In the present disclosure, the RPA robot can call the natural language processing (NLP) service to process the information of the current business node to be executed to determine the type of the current business node to be executed. The information of the business node may include information used to determine the type of the business node.

[0108] For example, an RPA robot can call a natural language processing (NLP) service to process the name of a business node and determine that the business node is a screenshot business. The business node name includes the character "Screenshot" to indicate that the business node is a screenshot business.

[0109] Step S103: In response to the current service node to be executed being the screenshot service, a service node screenshot corresponding to the screenshot service is obtained.

[0110] In the present disclosure, in order to monitor the operating status of the RPA robot, a business node for instructing the RPA robot to take screenshots can be added to the business process corresponding to the RPA, so that when the RPA robot executes its corresponding business process and executes the screenshot business node, it can trigger the acquisition of the current screenshot of the device screen where it is located.

[0111] In this disclosure, due to the characteristics of each business node in the business process, only some business nodes have a higher probability of abnormalities. In order to reduce the resource consumption of monitoring the operating status of the RPA robot, only the business nodes with a higher probability of abnormalities can be monitored.

[0112] When editing a business process, you can set a screenshot business node for the business node you want to monitor. This allows the RPA robot to capture a screenshot of the business node when it reaches that node during execution of the business process. The screenshot can be a screenshot of the device's operating interface when the RPA robot is running at that business node.

[0113] It should be noted that the RPA robot business process may include one screenshot business node or multiple screenshot business nodes, which is not limited in this disclosure.

[0114] Step S104: Send the screenshot of the business node to the RPA robot console, so that the RPA robot console determines the operating status of the RPA robot based on the screenshot.

[0115] In the present disclosure, after obtaining a screenshot of a business node, the RPA robot can send the screenshot of the business node to the RPA robot console. Thus, the RPA robot console can determine the operating status of the RPA robot based on the screenshot of the business node.

[0116] For example, the RPA robot console may include a sequence of screenshots of the RPA robot in its normal operating state. The RPA robot can then determine whether it is in a normal operating state based on the order of the screenshots returned by the RPA robot during the authorization process and the match between the screenshot sequence. Alternatively, the RPA robot console may also include reference screenshots of the normal operating state corresponding to each RPA robot. The RPA robot's operating state can then be determined based on the match between the actual screenshots returned by the RPA robot and the reference screenshots. This disclosure is not limited to this.

[0117] In the present disclosure, after the RPA robot obtains the current business node to be executed, it can call the natural language processing (NLP) service to process the current business node to be executed to determine the type of the current business node to be executed. In the case that the current business node to be executed is a screenshot business, a screenshot of the business node corresponding to the screenshot business can be obtained. After that, the screenshot of the business node can be sent to the RPA robot console so that the RPA robot console can determine the operating status of the RPA robot based on the screenshot. Thus, the type of the business node is determined to be a screenshot business through the NLP service, and then the operating status of the RPA robot can be automatically determined based on the obtained screenshot of the business node, thereby realizing automatic monitoring of the operating status of the RPA robot and improving the operating efficiency of the equipment.

[0118] Figure 2 This is a flowchart of a method for implementing the robot operation status of IA based on RPA and AI according to an embodiment of the present disclosure. The method is executed by an RPA robot, such as Figure 2 As shown, the method may include the following steps:

[0119] Step S201: The RPA robot obtains the business node to be executed.

[0120] Step S202: calling a natural language processing (NLP) service to process the current service node to be executed, so as to determine the type of the current service node to be executed.

[0121] In the present disclosure, the specific implementation process of step S201-step S202 can be found in the detailed description of any embodiment of the present disclosure, and will not be repeated here.

[0122] Step S203: In response to the current service node to be executed being a screenshot service, determining a size and / or position of a screenshot frame corresponding to the screenshot service.

[0123] The screenshot service can trigger an RPA robot to capture the current screen.

[0124] In the present disclosure, different business nodes may correspond to different information for determining the operating status of the RPA robot, or the information used to determine the operating status of the RPA robot may be located at different positions on the operating interface. Therefore, according to the actual page layout of different screenshot businesses, different screenshot box sizes or positions can be set for each screenshot business in the RPA process, thereby reducing the amount of information in the screenshot and avoiding resource consumption.

[0125] In the present disclosure, when the service node to be currently executed is a screenshot service, the size and / or position of the screenshot frame corresponding to the screenshot service can be determined through query.

[0126] Step S204: obtaining a screenshot of a service node corresponding to the screenshot service according to the size and / or position of the screenshot frame.

[0127] Step S205: Send the screenshot of the business node to the RPA robot console, so that the RPA robot console determines the operating status of the RPA robot based on the screenshot.

[0128] In the present disclosure, the specific implementation process of step S205 can be found in the detailed description of any embodiment of the present disclosure, and will not be repeated here.

[0129] In the present disclosure, after the RPA robot obtains the current business node to be executed, if the current business node to be executed is a screenshot business, it can determine the size and / or position of the screenshot frame corresponding to the screenshot business. After that, it can obtain a screenshot of the business node corresponding to the screenshot business based on the size and / or position of the screenshot frame. Then, the screenshot of the business node can be sent to the RPA robot console so that the RPA robot console can determine the operating status of the RPA robot based on the screenshot. Thus, by adding a screenshot business node to the business process of the RPA robot, the operating status of the RPA robot can be automatically determined based on the obtained screenshot of the business node, thereby realizing automatic monitoring of the operating status of the RPA robot and improving the operating efficiency of the equipment.

[0130] Figure 3 This is a flowchart of a method for implementing the robot operation status of IA based on RPA and AI according to an embodiment of the present disclosure. The method is executed by an RPA robot, such as Figure 3 As shown, the method may include the following steps:

[0131] Step S301: The RPA robot obtains the business node to be executed.

[0132] Step S302: calling the natural language processing (NLP) service to process the current service node to be executed to determine the type of the current service node to be executed.

[0133] Step S303: In response to the current service node to be executed being the screenshot service, a service node screenshot corresponding to the screenshot service is obtained.

[0134] In the present disclosure, the specific implementation process of steps S301-S303 can be found in the detailed description of any embodiment of the present disclosure, and will not be repeated here.

[0135] Step S304: calling an optical character recognition (OCR) service to recognize the service node screenshot to obtain characters contained in the service node screenshot.

[0136] In this disclosure, business node screenshots may contain some sensitive information. For example, in the RPA process, when downloading a user's credit report, the obtained business node screenshots may contain the user's ID card information, family information, etc. Therefore, the sensitive information in the business node screenshots can be masked and then uploaded to the console, thereby avoiding the leakage of sensitive information and ensuring information security.

[0137] Step S305: Determine the matching degree between the character and the sensitive words in the preset sensitive dictionary.

[0138] In the present disclosure, the sensitive dictionary may include sensitive words in various fields, or may also include sensitive words related to the business process executed by the RPA. Thus, the RPA robot can determine the degree of match between each character and each sensitive word in the preset sensitive dictionary by calculating the distance between the vector corresponding to each character identified from the business node screenshot and the vector corresponding to each sensitive word in the preset sensitive dictionary, thereby determining whether the information contained in the business node screenshot is sensitive information. The greater the distance between the vector corresponding to the character and the vector corresponding to the sensitive word, the smaller the corresponding degree of match.

[0139] Step S306: When the matching degree between any character and any sensitive word is greater than a threshold, masking is performed on any character to obtain a screenshot of the service node after masking.

[0140] In the present disclosure, when the degree of match between a certain character and any sensitive word is greater than a threshold, it indicates that the character is sensitive information. Afterwards, the character and the specific information corresponding to the character can be masked in the business node screenshot, and the masked business node screenshot can be obtained.

[0141] For example, Figure 4 As shown, Figure 4 Names, phone numbers, ID numbers, gender and other characters are all sensitive words. Therefore, names, phone numbers, ID numbers, gender and other characters and the corresponding information can be masked.

[0142] It should be noted that 4 in the figure can be any business-related information on the page, which is not limited here.

[0143] Optionally, the type of each character may be determined. If any character is a numeric type, mask processing is performed on the character to obtain a masked screenshot of the service node.

[0144] In this disclosure, the user's private data mostly exists in the form of numbers, such as ID number, social security number, bank card number, mobile phone number, etc. Therefore, the digital characters in the business node screenshot can be masked to avoid the leakage of sensitive information.

[0145] For example, Figure 5 As shown, Figure 5 The mobile phone number in a is sensitive information. After using the OCR service to identify the numeric characters in the image, the numeric characters can be masked to obtain a screenshot of the masked business node, such as Figure 5 b. In addition, Figure 5 The letters A, B, C, D, X, and Y are used to represent mobile phone numbers.

[0146] Step S307: Send the masked screenshot of the business node to the RPA robot console.

[0147] In the present disclosure, the RPA robot can send the masked business node screenshot to the RPA robot console, so that the RPA robot console can determine the operating status of the RPA robot based on the screenshot.

[0148] Optionally, you can also send a screenshot of the business node and the corresponding business node ID to the RPA robot console. The business node ID can be any information that can uniquely identify the business node, such as the business node number corresponding to the business node.

[0149] In this disclosure, when executing a screenshot service, an RPA robot can obtain screenshots of corresponding business nodes at preset time intervals. Therefore, a business node may collect multiple business node screenshots. When uploading a business node screenshot, the RPA robot can also upload the business node identifier corresponding to the business node screenshot to the RPA robot console. The RPA robot console can then obtain the corresponding reference screenshot based on the business node identifier. The reference screenshot is a screenshot of the RPA robot interface in normal operation.

[0150] In the present disclosure, after the RPA robot obtains the current business node to be executed, if the current business node to be executed is a screenshot business, it can obtain a screenshot of the business node corresponding to the screenshot business. After that, it can call the optical character recognition (OCR) service to identify the business node screenshot to obtain the characters contained in the business node screenshot and determine the matching degree between the characters and the sensitive words in the preset sensitive dictionary. When the matching degree between any character and any sensitive word is greater than a threshold, any character can be masked to obtain a screenshot of the business node after masking, and then the screenshot of the business node after masking is sent to the RPA robot console. Thus, by masking the sensitive information in the business node screenshot and sending the masked business node screenshot to the RPA robot console, the RPA robot console can determine the operating status of the RPA robot through the screenshot of the business node corresponding to the screenshot business, thereby realizing automatic monitoring of the operating status of the RPA robot while ensuring information security and improving the operating efficiency of the equipment.

[0151] Figure 6 This is a flowchart of a method for implementing the robot operation status of IA based on RPA and AI according to an embodiment of the present disclosure. The method is executed by the RPA robot console, such as Figure 6 As shown, the method may include the following steps:

[0152] Step S601: Receive a screenshot of a business node sent by an RPA robot.

[0153] A business node can be any process node during the RPA robot's operation. Furthermore, because RPA robots execute the business processes corresponding to each business during actual operation, a business process can contain multiple business nodes, and RPA robots can execute each business process based on the order of the business nodes within the process.

[0154] In the present disclosure, in order to monitor the operating status of the RPA robot, a business node for instructing the RPA robot to take screenshots can be added to the business process corresponding to the RPA, so that when the RPA robot executes its corresponding business process and executes the screenshot business node, it can trigger the acquisition of the current screenshot of the device screen where it is located.

[0155] In this disclosure, when editing a business process, you can set a screenshot business node on the business node that needs to be monitored. As a result, when the RPA robot executes the business process, it can obtain a screenshot of the corresponding business node when executing the node. The business node screenshot can be a screenshot of the device operation interface when the RPA robot is running at the business node.

[0156] Step S602: Obtain a reference screenshot corresponding to the RPA robot.

[0157] The reference screenshot is a screenshot of the device operation interface of the RPA robot in normal operation.

[0158] In the present disclosure, when editing a business process, the user can set a corresponding reference screenshot for each screenshot business to determine the operating status of the RPA robot. Afterwards, when the RPA robot executes the business process, it can send the reference screenshots corresponding to each screenshot business in the business process to the RPA robot console. In this way, the RPA robot console can obtain the reference screenshots corresponding to the RPA robot.

[0159] Optionally, you can pre-set reference screenshots for each business process in the RPA robot console. You can then retrieve the reference screenshots for the RPA robot based on the target business process for the RPA robot. The target business process can be the business process currently being executed by the RPA robot.

[0160] Step S603: Determine the running status of the RPA robot based on the matching degree between the business node screenshot and the reference screenshot.

[0161] In the present disclosure, the RPA robot console can determine the degree of matching between each business node screenshot and each reference screenshot by calculating the distance between the vector corresponding to the business node screenshot and the vector corresponding to the reference screenshot. Afterwards, when the degree of matching between the business node screenshot and the reference screenshot is greater than a threshold, it can be determined that the business node screenshot is similar to the reference screenshot, and therefore, it can be determined that the operating state of the RPA robot is normal. When the degree of matching between the business node screenshot and the reference screenshot is less than a threshold, it can be determined that the business node screenshot is different from the reference screenshot, and therefore, it can be determined that the operating state of the RPA robot is abnormal. Among them, the smaller the distance between the vector corresponding to the business node screenshot and the vector corresponding to the reference screenshot, the greater the corresponding degree of matching.

[0162] Optionally, the RPA robot console may include a sequence of screenshots of the RPA robot in normal operation. Then, whether the RPA robot is in normal operation can be determined based on the matching between the order of the screenshots returned by the RPA robot during the permission process and the screenshot sequence.

[0163] In this disclosure, after receiving the business node screenshot sent by the RPA robot, the RPA robot console can obtain the reference screenshot corresponding to the RPA robot and determine the running status of the RPA robot based on the matching degree between the business node screenshot and the reference screenshot. Thus, the running status of the RPA robot can be automatically determined by the obtained business node screenshot, thereby realizing automatic monitoring of the running status of the RPA robot and improving the operating efficiency of the equipment.

[0164] Figure 7 This is a flowchart of a method for implementing the robot operation status of IA based on RPA and AI according to an embodiment of the present disclosure. The method is executed by the RPA robot console, such as Figure 7 As shown, the method may include the following steps:

[0165] Step S701: Receive a screenshot of a business node sent by an RPA robot.

[0166] In the present disclosure, the specific implementation process of step S701 can be found in the detailed description of any embodiment of the present disclosure, and will not be repeated here.

[0167] Step S702: Determine the business node identifier associated with the business node screenshot.

[0168] The service node identifier may be any information that can uniquely identify the service node, such as a service node number corresponding to the service node.

[0169] In the present disclosure, when the RPA robot performs the screenshot business, it can obtain the corresponding business node screenshots at preset time intervals. Therefore, a business node may collect multiple screenshots. Then, when uploading the business node screenshot, the RPA robot can upload the business node identifier corresponding to the business node screenshot to the RPA robot console, so that the RPA robot console can determine the business node identifier associated with the business node screenshot.

[0170] Step S703: According to the target business process corresponding to the RPA robot, obtain a reference screenshot set corresponding to the RPA robot.

[0171] In the present disclosure, the specific implementation process of step S703 can be found in the detailed description of any embodiment of the present disclosure and will not be repeated here.

[0172] Step S704: Obtain a reference screenshot corresponding to the service node identifier from the reference screenshot set.

[0173] In the present disclosure, the reference screenshot set corresponding to the RPA robot may include reference screenshots corresponding to each screenshot business in the target business process. Therefore, the RPA robot console can obtain the reference screenshot corresponding to the business node identifier from the reference screenshot set based on the business node identifier.

[0174] Step S705: Determine the running status of the RPA robot based on the matching degree between the business node screenshot and the reference screenshot.

[0175] In the present disclosure, the specific implementation process of step S705 can be found in the detailed description of any embodiment of the present disclosure, and will not be repeated here.

[0176] In the present disclosure, after receiving a business node screenshot sent by the RPA robot, the RPA robot console can determine the business node identifier associated with the business node screenshot. Subsequently, based on the target business process corresponding to the RPA robot, a reference screenshot set corresponding to the RPA robot can be obtained. From the reference screenshot set, a reference screenshot corresponding to the business node identifier can be obtained. The RPA robot's operating status can then be determined based on the degree of match between the business node screenshot and the reference screenshot. Thus, the RPA robot's operating status can be automatically determined using the obtained business node screenshot, thereby achieving automatic monitoring of the RPA robot's operating status and improving the device's operating efficiency.

[0177] Figure 8 This is a flowchart of a method for implementing the robot operation status of IA based on RPA and AI according to an embodiment of the present disclosure. The method is executed by the RPA robot console, such as Figure 8 As shown, the method may include the following steps:

[0178] Step S801: Receive a screenshot of a business node sent by an RPA robot.

[0179] Step S802: Obtain a reference screenshot corresponding to the RPA robot.

[0180] In the present disclosure, the specific implementation process of steps S801 to S802 can be found in the detailed description of any embodiment in the present disclosure, and will not be repeated here.

[0181] Step S803: calling the optical character recognition (OCR) service to recognize the screenshot to obtain characters contained in the screenshot.

[0182] In this disclosure, after receiving the business node screenshot, the RPA robot console can view it on the RPA robot console interface, such as Figure 9 As shown, you can click the task number corresponding to each business process in the task bar to display a list of business node screenshots obtained during the execution of the business process on the page. Then, by clicking the view button corresponding to each business node screenshot in the operation bar of the business node screenshot list, you can view each business node screenshot to determine the running status of the corresponding RPA robot.

[0183] However, business node screenshots may contain some sensitive information. For example, in the RPA process, when downloading a user's credit report, the obtained business node screenshot may contain the user's ID card information, family information, etc. Therefore, to avoid the leakage of sensitive information and ensure information security, the sensitive information in the business node screenshot can be masked, and then the masked business node screenshot can be saved and displayed.

[0184] like Figure 10 As shown, you can set Figure 10 The switch control corresponding to "Enable screenshot masking" is turned on, allowing the RPA robot console to mask sensitive information in received business node screenshots.

[0185] Step S804: Obtain a preset sensitive dictionary based on the target business process corresponding to the RPA robot.

[0186] The sensitive dictionary may include sensitive words in various fields, or may also include sensitive words related to the business process executed by the RPA.

[0187] In this disclosure, due to the different business scenarios corresponding to business processes, the sensitive information contained in the screenshots of each business node corresponding to the business process may be different. Therefore, sensitive dictionaries corresponding to different business processes can be preset in the RPA robot console. After that, the sensitive dictionary corresponding to the target business process can be obtained through query.

[0188] Step S805: Determine the matching degree between the character and the sensitive words in the preset sensitive dictionary.

[0189] Step S806: When the matching degree between any character and any sensitive word is greater than a threshold, mask processing is performed on any character to obtain a screenshot of the service node after mask processing.

[0190] Step S807: Determine the operating status of the RPA robot based on the matching degree between the masked business node screenshot and the reference screenshot.

[0191] In the present disclosure, the specific implementation process of steps S805 to S807 can be found in the detailed description of any embodiment in the present disclosure, and will not be repeated here.

[0192] In the present disclosure, after the RPA robot console receives the business node screenshot sent by the RPA robot, it can obtain a reference screenshot corresponding to the RPA robot. After that, the optical character recognition (OCR) service can be called to identify the screenshot to obtain the characters contained in the screenshot. Then, according to the target business process corresponding to the RPA robot, the preset sensitive dictionary is obtained, and the matching degree between the characters and the sensitive words in the preset sensitive dictionary is determined. When the matching degree between any character and any sensitive word is greater than a threshold, any character is masked to obtain a masked business node screenshot, and the running status of the RPA robot is determined based on the matching degree between the masked business node screenshot and the reference screenshot. Thus, by masking the sensitive information in the business node screenshot and matching the business node screenshot corresponding to the screenshot business with the reference screenshot to determine the running status of the RPA robot, while ensuring information security, automatic monitoring of the running status of the RPA robot is achieved, thereby improving the operating efficiency of the equipment.

[0193] In order to implement the above embodiment, the embodiment of the present disclosure also proposes a device for realizing the robot operation status of IA based on RPA and AI. Figure 11 A schematic diagram of the structure of a device for implementing the robot operation status of IA based on RPA and AI provided in an embodiment of the present disclosure.

[0194] like Figure 11 As shown, the device 1100 for implementing the robot operation status of IA based on RPA and AI includes: an acquisition module 1110, a screenshot module 1120, and a sending module 1130.

[0195] Acquisition module 1110 is used by the RPA robot to obtain the business node to be executed currently;

[0196] A determination module 1120 is configured to call a natural language processing (NLP) service to process the current service node to be executed to determine the type of the current service node to be executed;

[0197] A screenshot module 1130 is configured to obtain a screenshot of the service node corresponding to the screenshot service in response to the service node to be currently executed being the screenshot service;

[0198] The sending module 1140 is used to send the business node screenshot to the RPA robot console, so that the RPA robot console determines the operating status of the RPA robot based on the screenshot.

[0199] Optionally, the screenshot module 1120 is specifically configured to:

[0200] Determine the size and / or position of the screenshot frame corresponding to the screenshot service;

[0201] According to the size and / or position of the screenshot frame, a screenshot of the service node corresponding to the screenshot service is obtained.

[0202] Optionally, the sending module 1130 is specifically configured to:

[0203] Call the optical character recognition (OCR) service to recognize the business node screenshot to obtain the characters contained in the business node screenshot;

[0204] Determine the degree of match between the character and the sensitive words in the preset sensitive dictionary;

[0205] When the matching degree between any character and any sensitive word is greater than a threshold, any character is masked to obtain a screenshot of the masked business node;

[0206] Send the masked business node screenshot to the RPA robot console.

[0207] Optionally, the sending module 1130 is specifically configured to:

[0208] Send the business node screenshot and the corresponding business node ID to the RPA robot console.

[0209] In the present disclosure, after the RPA robot obtains the current business node to be executed, it can call the natural language processing (NLP) service to process the current business node to be executed to determine the type of the current business node to be executed. In the case that the current business node to be executed is a screenshot business, a screenshot of the business node corresponding to the screenshot business can be obtained. After that, the screenshot of the business node can be sent to the RPA robot console so that the RPA robot console can determine the operating status of the RPA robot based on the screenshot. Thus, the type of the business node is determined to be a screenshot business through the NLP service, and then the operating status of the RPA robot can be automatically determined based on the obtained screenshot of the business node, thereby realizing automatic monitoring of the operating status of the RPA robot and improving the operating efficiency of the equipment.

[0210] The functions of each module in each device of the embodiment of the present disclosure can be found in the corresponding description of the above method and will not be repeated here.

[0211] In order to implement the above embodiment, the embodiment of the present disclosure also proposes another device for realizing the robot operation status of IA based on RPA and AI. Figure 12 A schematic diagram of the structure of a device for implementing the robot operation status of IA based on RPA and AI provided in an embodiment of the present disclosure.

[0212] like Figure 12As shown, the device 1200 for implementing the robot operation status of IA based on RPA and AI includes: a receiving module 1210, an acquisition module 1220, and a determination module 1230.

[0213] Receiving module 1210, configured to receive a screenshot of a business node sent by an RPA robot;

[0214] An acquisition module 1220 is configured to acquire a reference screenshot corresponding to the RPA robot;

[0215] The determination module 1230 is used to determine the operating status of the RPA robot based on the matching degree between the business node screenshot and the reference screenshot.

[0216] Optionally, the acquisition module 1220 is specifically configured to:

[0217] Obtain the reference screenshots of the RPA robot based on the target business process of the RPA robot.

[0218] Optionally, the acquisition module 1220 is specifically configured to:

[0219] Determine the business node ID associated with the business node screenshot;

[0220] Obtain a reference screenshot set for the RPA robot based on the target business process.

[0221] From the reference screenshot set, obtain a reference screenshot corresponding to the business node identifier.

[0222] Optionally, the determining module 1230 is specifically configured to:

[0223] Call the optical character recognition (OCR) service to recognize the screenshot and obtain the characters contained in the screenshot;

[0224] Determine the degree of match between the character and the sensitive words in the preset sensitive dictionary;

[0225] When the matching degree between any character and any sensitive word is greater than a threshold, any character is masked to obtain a screenshot of the masked business node;

[0226] The running status of the RPA robot is determined based on the matching degree between the masked business node screenshot and the reference screenshot.

[0227] Optionally, the acquisition module 1220 is further configured to: acquire a preset sensitive dictionary according to a target business process corresponding to the RPA robot.

[0228] In this disclosure, after receiving a business node screenshot sent by the RPA robot, the RPA robot console can obtain a reference screenshot corresponding to the RPA robot and determine the RPA robot's operating status based on the degree of match between the business node screenshot and the reference screenshot. Thus, the RPA robot's operating status can be automatically determined based on the obtained business node screenshot, thereby achieving automatic monitoring of the RPA robot's operating status and improving the device's operating efficiency.

[0229] The functions of each module in each device of the embodiment of the present disclosure can be found in the corresponding description of the above method and will not be repeated here.

[0230] Figure 13 The following is a block diagram showing the structure of the device / terminal / server for implementing the robot running state of IA based on RPA and AI according to an embodiment of the present disclosure. Figure 13 As shown, the device / terminal / server for implementing the robot operating state of IA based on RPA and AI includes: a memory 1310 and a processor 1320. The memory 1310 stores a computer program executable on the processor 1320. When the processor 1320 executes the computer program, the method for implementing the robot operating state of IA based on RPA and AI in the above embodiment is implemented. The number of memory 1310 and processor 1320 can be one or more.

[0231] The devices / terminals / servers that implement IA based on RPA and AI also include:

[0232] The communication interface 1330 is used to communicate with external devices and perform data exchange transmission.

[0233] If the memory 1310, the processor 1320, and the communication interface 1330 are implemented independently, the memory 1310, the processor 1320, and the communication interface 1330 can be connected to each other via 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, Figure 13 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0234] Optionally, in a specific implementation, if the memory 1310, the processor 1320 and the communication interface 1330 are integrated on a chip, the memory 1310, the processor 1320 and the communication interface 1330 can communicate with each other through an internal interface.

[0235] An embodiment of the present disclosure provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present disclosure when the program is executed by a processor.

[0236] An embodiment of the present disclosure further provides a chip, which includes a processor for calling and executing instructions stored in a memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present disclosure.

[0237] An embodiment of the present disclosure also provides a chip, including: an input interface, an output interface, a processor and a memory. The input interface, the output interface, the processor and the memory are connected through an internal connection path. 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.

[0238] 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 that supports the advanced reduced instruction set machine (ARM) architecture.

[0239] Furthermore, optionally, the above-mentioned memory may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. The volatile memory may include 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).

[0240] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present disclosure are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0241] In the description of this specification, reference to the terms "one embodiment," "some embodiments," "examples," "specific examples," 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 disclosure. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and integrate different embodiments or examples described in this specification, as well as features of different embodiments or examples, unless they are mutually inconsistent.

[0242] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the present disclosure, "plurality" means two or more, unless otherwise specifically defined.

[0243] Any process or method description described in a flowchart or otherwise herein can be understood to represent a module, segment, or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process. The scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may be performed in a different order than shown or discussed, including in a substantially simultaneous manner or in a reverse order depending on the functions involved.

[0244] The logic and / or steps represented in the flowchart or otherwise described herein may be considered, for example, as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device).

[0245] It should be understood that various parts of the present disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using 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. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0246] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the aforementioned integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic disk, or an optical disk, etc.

[0247] The above description is merely a specific embodiment of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any person skilled in the art can easily conceive of various modifications or substitutions within the technical scope disclosed in the present disclosure, and such modifications or substitutions should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A method for realizing the robot operation status of IA based on RPA and AI, characterized in that: Adding a screenshot business node to a business node prone to exceptions in the business process of the RPA robot includes: The RPA robot obtains the business node to be executed; Invoking a natural language processing (NLP) service to process the service node to be executed to determine the type of the service node to be executed; In response to the type of the currently to-be-executed service node being a screenshot service, obtaining a screenshot of the service node corresponding to the screenshot service at a preset time interval; The matching degree between the characters of the business node screenshot and the sensitive words in the preset sensitive dictionary is calculated. When the matching degree between any character and any sensitive word is greater than a threshold, the any character is masked to obtain a masked business node screenshot, and the masked business node screenshot and the business node identifier corresponding to the business node screenshot are sent to the RPA robot console, so that the RPA robot console obtains the corresponding masked business node screenshot according to the business node identifier; according to the target business process corresponding to the RPA robot, a reference screenshot set corresponding to the RPA robot is obtained, and a reference screenshot corresponding to the business node identifier is obtained from the reference screenshot set; the operating status of the RPA robot is determined based on the masked business node screenshot corresponding to the business node identifier and the reference screenshot; wherein, the reference screenshot is a screenshot of the device operation interface of the RPA robot under normal operating state.

2. The method according to claim 1, wherein The obtaining of a screenshot of a service node corresponding to the screenshot service includes: Determining a screenshot frame size and / or position corresponding to the screenshot service; A service node screenshot corresponding to the screenshot service is obtained according to the size and / or position of the screenshot frame.

3. The method according to claim 1, wherein The matching degree between the characters in the screenshot of the business node and the sensitive words in the preset sensitive dictionary includes: Invoke an optical character recognition (OCR) service to recognize the service node screenshot to obtain characters contained in the service node screenshot; Determine the degree of match between the character and a sensitive word in a preset sensitive dictionary.

4. The method according to claim 3, wherein Before determining the matching degree between the character and the sensitive word in the preset sensitive dictionary, the method further includes: According to the target business process corresponding to the RPA robot, the preset sensitive dictionary is obtained.

5. A device for realizing the robot operation status of IA based on RPA and AI, characterized in that: A screenshot service node is added to a service node in the business process of the RPA robot where anomalies are likely to occur. The device includes: The acquisition module is used by the RPA robot to obtain the business node to be executed; A determination module, configured to call a natural language processing (NLP) service to process the currently executed service node to determine a type of the currently executed service node; A screenshot module, configured to obtain a screenshot of the service node corresponding to the screenshot service in response to the service node to be currently executed being the screenshot service; A sending module is used to match the characters of the business node screenshot with the sensitive words in a preset sensitive dictionary. When the matching degree between any character and any sensitive word is greater than a threshold, the any character is masked to obtain a masked business node screenshot, and the masked business node screenshot and the business node identifier corresponding to the business node screenshot are sent to the RPA robot console, so that the RPA robot console obtains the corresponding masked business node screenshot according to the business node identifier; according to the target business process corresponding to the RPA robot, a reference screenshot set corresponding to the RPA robot is obtained, and a reference screenshot corresponding to the business node identifier is obtained from the reference screenshot set; the operating status of the RPA robot is determined based on the masked business node screenshot corresponding to the business node identifier and the reference screenshot; wherein, the reference screenshot is a screenshot of the device operation interface of the RPA robot under normal operating state.

6. A computer device, 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 4.

7. 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 4 is implemented.

Images