Robotic process automation generation method and system based on large model

Abstract

The present invention provides a robot process automation generation method and system based on a large model, which belongs to the field of large model technology, and specifically includes: when determining that the degree of switching influence on the existing process automation robot is difficult to meet the requirements based on the overlapping data of the influencing monitoring ports of different alternative robots, based on the influencing robots of different monitoring ports and the composition data of the influencing monitoring ports of the influencing robots, determining the alternative switching ports in the monitoring ports, obtaining the composition data of the alternative switching ports to be monitored and processed, and combining the overlapping data of the influencing robots between other alternative switching ports to determine the abnormal response strategy for the presence of reading delays in different alternative switching ports, based on the abnormal response strategy and the monitoring ports to be monitored and processed, using the large model to generate and process the process automation robot, thereby improving the efficiency of the generation and processing.

Description

Technical Field

[0001] The present invention belongs to the technical field of large models, and in particular relates to a method and system for automatically generating a robotic process based on a large model. Background Art

[0002] Once an advertisement is published, its operation needs to be monitored, including browsing data, conversion data, exposure data, etc. Existing technical solutions often monitor and process the operation of advertisements through API ports. This makes how to use process automation robots to monitor, analyze and process different API interfaces a technical problem that needs to be solved urgently.

[0003] Existing process automation robots used for advertising monitoring and processing often monitor and process different API ports through manually set rules. However, with the increase in the number of API ports to be monitored and managed, and the changes in advertising types and delivery platforms, the original fixed process automation robots are unable to meet the needs of data monitoring and processing. Therefore, how to use large models to automatically generate and update process automation robots to meet the needs of monitoring and processing has become a technical problem that needs to be solved urgently.

[0004] Therefore, in order to solve the above technical problems, the present application provides a method and system for generating robotic process automation based on a large model. Summary of the Invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] To achieve the above-mentioned purpose of the invention, the present application provides a method for generating a large-scale robotic process automation based on a large model, comprising the following contents:

[0007] S1 determines a candidate robot for an existing process automation robot based on the data type of the monitoring port, and determines an influencing robot for the monitoring port according to the number of candidate robots for different monitoring ports and the port monitoring data of different candidate robots;

[0008] S2 obtains the monitoring ports of the influencing robots of different candidate robots and uses them as the influencing monitoring ports. When it is determined that the degree of influence on the switching of the existing process automation robot cannot meet the requirements based on the overlapping data of the influencing monitoring ports of different candidate robots, the process proceeds to the next step.

[0009] S3: determining a candidate switching port among the monitoring ports based on the influencing robots of different monitoring ports and the constituent data of the influencing robots and the influencing monitoring ports;

[0010] S4 obtains the composition data of the alternative switching port to be monitored and processed, and combines it with the overlapping data of the robot affecting other alternative switching ports to determine the abnormal response strategy for reading delays in different alternative switching ports. Based on the abnormal response strategy and the monitoring port to be monitored and processed, a large model is used to generate and process the process automation robot.

[0011] A further technical solution is that the candidate robot is an existing process automation robot that can read data of the data type of the monitoring port.

[0012] A further technical solution is that the method for determining the influence of the monitoring port on the robot is:

[0013] Determining the number of ports monitored by the candidate robot for the monitoring port based on the port monitoring data of the candidate robot for the monitoring port;

[0014] Whether the candidate robot is an influencing robot is determined according to the number of monitored ports of the candidate robot and the number of candidate robots.

[0015] It should be noted that the influencing robot is a candidate robot with a large number of monitored ports and a small number of candidate robots. Whether the number of monitored ports is large and the number of candidate robots is small can be determined by means of a threshold.

[0016] A further technical solution is to generate and process process automation robots, specifically including:

[0017] The abnormal response strategies of different monitoring ports and the monitoring ports to be monitored are input into the large model;

[0018] Use large models to generate process automation robots.

[0019] In one possible embodiment, the large model is constructed by Deepseek-R2.

[0020] In a second aspect, the present invention provides a computer system comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned large model-based robotic process automation generation method when running the computer program.

[0021] The beneficial effects of the present invention are:

[0022] Based on the composition data of the alternative switching port to be monitored and processed and the overlapping data of the influencing robot with other alternative switching ports, the abnormal response strategy of reading delay of different alternative switching ports is determined. Not only the difference in the degree of impact on the existing process automation robots caused by the number of alternative switching ports is taken into account, but also the difference in the degree of impact on the existing process automation robots caused by the overlap is taken into account. The abnormal response strategy is determined based on the low degree of impact on the existing process automation robots, which ensures the reliability of the reading processing and further reduces the degree of impact on other existing process automation robots.

[0023] Based on the exception response strategy and the monitoring ports to be monitored and processed, the large model is used to generate and process the process automation robot, which further improves the generation and processing efficiency of the process automation robot. By setting differentiated exception response strategies, the complexity of the process automation robot's exception response strategy is reduced, ensuring that the process automation robot can operate reliably.

[0024] Other features and advantages will be described in the following description. The objectives and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0025] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings.

[0027] Figure 1 It is a flowchart of a large model-based robotic process automation generation method;

[0028] Figure 2 is a flow chart of a method for determining an impact robot on a monitoring port;

[0029] Figure 3 It is a flowchart to determine the degree of impact of switching to the existing process automation robot that is difficult to meet the requirements;

[0030] Figure 4 is a flow chart of a method for determining a candidate switching port among monitoring ports;

[0031] Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0032] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this specification without creative work should fall within the scope of protection of this specification.

[0033] The influencing robot is a candidate robot whose number of monitored ports is greater than a preset threshold and whose number of candidate robots is less than 10.

[0034] When the number of influencing robots that do not overlap with the impact monitoring ports of other influencing robots is more than 5, it is determined that the degree of switching impact on the existing process automation robots is difficult to meet the requirements.

[0035] The alternative switching port is a monitoring port whose number of influencing robots is within 10 and the number of influencing monitoring ports of different influencing robots is within 5.

[0036] When the number of candidate switching ports is small, that is, smaller than the pre-selected switching port number threshold, the first strategy is adopted for determining the abnormal response strategy for different candidate switching ports.

[0037] When the number of candidate switching ports is large, that is, not less than the pre-selected switching port number threshold, the second strategy is adopted to determine an abnormal response strategy for the candidate switching ports having a read delay.

[0038] Example 1

[0039] Specifically, such as Figure 1 As shown, a large model-based robotic process automation generation method includes the following contents:

[0040] S1 determines a candidate robot for an existing process automation robot based on the data type of the monitoring port, and determines an influencing robot for the monitoring port according to the number of candidate robots for different monitoring ports and the port monitoring data of different candidate robots;

[0041] Furthermore, the candidate robot is an existing process automation robot that can read data of the data type of the monitoring port.

[0042] Specifically, such as Figure 2 As shown, the method for determining the impact of the monitoring port on the robot is:

[0043] Determining the number of ports monitored by the candidate robot for the monitoring port based on the port monitoring data of the candidate robot for the monitoring port;

[0044] Whether the candidate robot is an influencing robot is determined according to the number of monitored ports of the candidate robot and the number of candidate robots.

[0045] It should be noted that the influencing robot is a candidate robot with a large number of monitored ports and a small number of candidate robots. Whether the number of monitored ports is large and the number of candidate robots is small can be determined by means of a threshold.

[0046] In one embodiment, the method for determining whether the monitoring port affects the robot is:

[0047] The monitoring ports where the number of candidate robots is within a preset range are regarded as potential impact ports;

[0048] Determining the number of ports monitored by the candidate robot that potentially affects the port based on the port monitoring data of the candidate robot that potentially affects the port;

[0049] Whether the candidate robot is an influencing robot is determined according to the number of monitored ports of the candidate robot.

[0050] It can be understood that the potential impact port is a monitoring port with a smaller number of alternative robots, which is specifically determined by a preset number range.

[0051] It should also be noted that, when the number of ports monitored by the candidate robot is large, specifically when the number is greater than a certain threshold, it is determined that the candidate robot monitoring the ports is an influencing robot.

[0052] S2 obtains the monitoring ports of the influencing robots of different candidate robots and uses them as the influencing monitoring ports. When it is determined that the degree of influence on the switching of the existing process automation robot cannot meet the requirements based on the overlapping data of the influencing monitoring ports of different candidate robots, the process proceeds to the next step.

[0053] It is understandable that if Figure 3 As shown in the figure, it is difficult to determine the impact of switching to existing process automation robots to meet the requirements, including:

[0054] Using the overlap data of the impact monitoring ports of different candidate robots, determine the impact monitoring port whose overlap number with other candidate robots is less than a preset overlap number, and use it as an independent impact port;

[0055] Determining a switching-affected robot among the candidate robots according to the number of the independent-affected ports;

[0056] It can be understood that the switching influencing robot is a candidate robot with a larger number of independent influencing ports. Specifically, the candidate robot with the number of independent influencing ports greater than a threshold can be used as the switching influencing robot.

[0057] Based on the number of robots affected by the switch, determine whether the degree of switch impact on existing process automation robots is difficult to meet the requirements.

[0058] Specifically, when the number of robots affected by switching is large, if the number of robots affected by switching is greater than the threshold, the degree of overlap between the affected monitoring port and other alternative robots is low, so the impact on the robot is high. If the number of robots affected by switching is large, the switching impact on the existing process automation robot is high.

[0059] In another possible embodiment, determining that the degree of impact on switching of an existing process automation robot is difficult to meet the requirements specifically includes:

[0060] Determine the number of impact monitoring ports on different candidate robots based on overlapping data of impact monitoring ports on different candidate robots;

[0061] The candidate robot whose number of affected monitoring ports is greater than the preset number of ports is used as the screening-affected robot;

[0062] Based on the number of affected robots, determine whether the impact of switching existing process automation robots is difficult to meet the requirements.

[0063] Specifically, when the number of robots affected by the screening does not meet the requirements, that is, is greater than a preset number threshold, it is determined that the degree of switching impact on the existing process automation robots is difficult to meet the requirements.

[0064] It is understandable that when the degree of impact on the switching of the existing process automation robot meets the requirements, the abnormal response strategy for the existence of read delays on all monitoring ports is set to automatically switch to the alternative robot when the preset time is exceeded.

[0065] In another possible embodiment, determining that the degree of impact on switching of an existing process automation robot is difficult to meet the requirements specifically includes:

[0066] S21 determines, based on the overlap data of the impact monitoring ports of different candidate robots, the impact monitoring ports whose overlap number with other candidate robots is less than a preset overlap number, and uses them as independent impact ports, and determines the switching impact robot among the candidate robots according to the number of independent impact ports;

[0067] In one embodiment, before proceeding to the next step, it is necessary to determine whether the number of alternative robots whose number of influencing monitoring ports does not meet the requirement meets the requirement, whether the number of switching influencing robots meets the requirement, and whether the sum of the number of independent influencing ports of different switching influencing robots meets the requirement. Specifically, whether the requirements are met can be determined by means of a threshold.

[0068] Specifically, if the number of alternative robots that affect the number of monitoring ports is too large, the number of switching-affecting robots is too large, or the sum of the number of independent affecting ports of different switching-affecting robots is too large, the switching impact on the existing process automation robots is relatively high, and therefore the switching impact on the existing process automation robots is difficult to meet the requirements.

[0069] In addition, it should be noted that only when the above conditions are met, it is necessary to determine the number of monitoring ports of different switching-affected robots and determine the degree of switching impact on existing process automation robots.

[0070] S22: obtaining the number of monitoring ports of the robot affected by different switching, and using the number of monitoring ports of the robot affected by different switching as the port impact number;

[0071] In one embodiment, the following factors need to be considered in the above steps:

[0072] If the number of ports affected by different switching robots is small, the specific impact can be determined by the impact quantity interval. On this basis, based on the small number of switching-affected robots, the switching impact on the existing process automation robots meets the requirements;

[0073] In addition, if there are switching-affecting robots with a relatively large number of port impacts, the number of switching-affecting robots with a relatively large number of port impacts is determined. When the number of switching-affecting robots with a relatively large number of port impacts is large, specifically when the number of switching-affecting robots is within the range of the number of robots, the degree of switching impact on the existing process automation robots is difficult to meet the requirements.

[0074] It should also be noted that even if the number of ports affected is not small and the number of switching-affected robots is not large, it is still necessary to determine whether the sum of the number of ports affected by the switching-affected robots meets the requirements. Specifically, if the number is large within a certain range, it is determined that the sum of the number of ports affected by the switching-affected robots does not meet the requirements. At this time, the degree of switching impact on the existing process automation robots is difficult to meet the requirements.

[0075] S23 determines whether the degree of switching impact on the existing process automation robot is difficult to meet the requirements based on the number of ports affected by different switching impact robots and the number of independent ports.

[0076] In one possible embodiment, the influence factors of different switching influencing robots can be determined by multiplying the average value of the number of port influences of different switching influencing robots and the number of independent ports by a preset proportional factor. When the sum of the influence factors of different switching influencing robots is greater than the preset influence factor, it is determined that the degree of switching influence on the existing process automation robot is difficult to meet the requirements.

[0077] S3: determining a candidate switching port among the monitoring ports based on the influencing robots of different monitoring ports and the constituent data of the influencing robots and the influencing monitoring ports;

[0078] Specifically, such as Figure 4 As shown, the method for determining the candidate switching port in the monitoring port is:

[0079] Determining the number of influencing robots of the monitoring port based on the influencing robots of the monitoring port;

[0080] Determining the number of the impact monitoring ports of different impact robots according to the composition data of the impact monitoring ports of different impact robots;

[0081] Based on the number of monitoring ports affected by the influencing robot of the monitoring port, it is determined whether the monitoring port is a candidate switching port.

[0082] Specifically, if the number of robots affecting the monitoring port is within a preset robot number range, that is, the number of robots affecting is not large and the average number of monitoring ports affecting different robots affecting is within 4, then the monitoring port is determined to be an alternative switching port.

[0083] It is understandable that when the monitoring port does not belong to the alternative switching port, when there is a reading delay in the monitoring port, it will be temporarily set as a fault port until the preset time, that is, 5 minutes later, the process automation robot will be used to read the port data.

[0084] In another possible embodiment, the method for determining the candidate switching port among the monitoring ports is:

[0085] S31 determines the number of influencing robots of the monitoring port based on the influencing robots of the monitoring port;

[0086] It can be understood that if a large number of robots are affected in the above steps, the impact on other process automation robots is relatively high. Therefore, it can be directly determined that the monitoring port has a greater impact on the existing robots, so it can be directly determined that it does not belong to the alternative switching port.

[0087] It should also be noted that if the number of robots affected is not large, it is also necessary to determine whether the number of ports affecting the robot's own monitoring meets the requirements. Specifically, if the number of ports affecting the robot's own monitoring is large, specifically if the sum of the number of ports affecting the robot's own monitoring is large and difficult to meet the requirements, it is specifically determined by means of a threshold, and it is determined that it does not belong to the alternative switching port.

[0088] S32 determines the number of the influence monitoring ports of different influencing robots according to the composition data of the influence monitoring ports of different influencing robots, and determines the repeated influencing robots among the influencing robots by using the number of the influence monitoring ports;

[0089] In addition, it can be understood that for the influencing robots that affect a large number of monitoring ports, the number of robots themselves affected by the switching of the monitoring ports is large. Therefore, in the above steps, if there are influencing robots that affect more than 10 monitoring ports, they cannot be used as alternative switching ports at this time, otherwise the degree of impact on the influencing monitoring ports will be higher.

[0090] In another embodiment, if there are no influencing robots with more than 10 influencing monitoring ports, the influencing robots with more than 3 influencing monitoring ports can be regarded as repeated influencing robots. When the number of repeated influencing robots is more than 20, the degree of impact on the existing process automation robots is relatively high, so it can be directly determined that they do not belong to the alternative switching ports.

[0091] It should also be noted that when the number of repeatedly affected robots is not more than 20, if the number of repeatedly affected robots is within a certain range, specifically between 10 and 20, and if the average number of monitoring ports of different overlapping affected robots is more than 70, it can also be determined that it does not belong to the alternative switching port.

[0092] S33 determines whether the monitoring port is a candidate switching port based on the number of robots repeatedly influencing the monitoring port and the number of influencing robots that correspondingly influence the monitoring port.

[0093] It should also be noted that, in a possible embodiment, it can be understood that the port influence values ​​of the influence monitoring ports corresponding to different repeated influencing robots are determined by utilizing the ratio of the number of influencing robots that influence the monitoring ports corresponding to the repeated influencing robots to the preset number, and the influence difference is determined based on the difference between the preset value and the port influence value. When the sum of the influence differences of the influence monitoring ports corresponding to different repeated influencing robots is greater than the preset difference threshold, it means that the number of affected monitoring ports of the overlapping influencing robot is large and has high independence, so it can be directly determined that the monitoring port does not belong to the alternative switching port.

[0094] S4 obtains the composition data of the alternative switching port to be monitored and processed, and combines it with the overlapping data of the robot affecting other alternative switching ports to determine the abnormal response strategy for reading delays in different alternative switching ports. Based on the abnormal response strategy and the monitoring port to be monitored and processed, a large model is used to generate and process the process automation robot.

[0095] Furthermore, the read delay is a state where the time length for reading data is longer than a preset time length and the port does not respond.

[0096] Specifically, the method for determining the abnormal response strategy when the candidate switching port has a read delay is as follows:

[0097] Determining the number of candidate switching ports to be monitored using the composition data of the candidate switching ports to be monitored;

[0098] Determine the number of overlaps between the influencing robots and other candidate switching ports through overlap data of the influencing robots between the other candidate switching ports;

[0099] According to the number of the candidate switching ports and the number of overlaps between different candidate switching ports and other candidate switching ports that affect the robot, an abnormal response strategy for the existence of a read delay in the candidate switching port is determined.

[0100] It is understandable that when the number of candidate switching ports is small, that is, smaller than the pre-set threshold number of candidate switching ports, the first strategy is adopted to determine the abnormal response strategy for different candidate switching ports.

[0101] When the number of alternative switching ports is large, that is, not less than the pre-selected switching port number threshold, the abnormal response strategy of the alternative switching port having a reading delay is determined based on the number of overlaps between the alternative switching port and other alternative switching ports that affect the robot.

[0102] Specifically, when the number of overlapping robots affecting the alternative switching port and other alternative switching ports is greater than the preset overlapping number threshold, and when there is a reading delay in the monitoring port, it will be temporarily set as a fault port until the preset time, that is, 5 minutes later, the process automation robot will be used to read the port data.

[0103] If the number of overlaps between the alternative switching port and other alternative switching ports that affect the robot is not greater than the preset overlap number threshold, determine whether the overlap number is less than the overlap number preset value. If so, use the first strategy to determine the abnormal response strategy. If not, use the second strategy to determine the abnormal response strategy.

[0104] Specifically, the first strategy is to directly switch to the alternative robot for reading processing when there is a reading delay. The second strategy is to determine whether the number of monitoring ports affected by switching to the alternative robot is more than 3 when there is a reading delay. If so, when there is a reading delay on the monitoring port, it is directly set as a fault port temporarily until the preset time, that is, 5 minutes later, the process automation robot is used to read the port data. If not, the alternative robot with the number of monitoring ports affected by switching to the alternative robot being 3 or less will be used as the switching target, and reading processing will be performed after switching.

[0105] Furthermore, the process automation robot is generated and processed, including:

[0106] The abnormal response strategies of different monitoring ports and the monitoring ports to be monitored are input into the large model;

[0107] Use large models to generate process automation robots.

[0108] In one possible embodiment, the large model is constructed by Deepseek-R2.

[0109] Example 2

[0110] Second, as Figure 5 As shown, the present invention provides a computer system, comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned large model-based robotic process automation generation method when running the computer program.

[0111] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0112] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0113] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. A method for generating robotic process automation based on a large model, characterized in that: Specifically include: Based on the data type of the monitoring port, determine the candidate robots of the existing process automation robot, and determine the influencing robot of the monitoring port according to the number of candidate robots of different monitoring ports and the port monitoring data of different candidate robots; Obtain the monitoring ports of the influencing robots of different candidate robots and use them as the influencing monitoring ports. Use the overlapping data of the influencing monitoring ports of different candidate robots to determine whether the switching impact on the existing process automation robot is difficult to meet the requirements, and then proceed to the next step. Determining an alternative switching port among the monitoring ports based on the influencing robots of different monitoring ports and the constituent data of the influencing robots and the influencing monitoring ports; Obtain the composition data of the alternative switching port to be monitored and processed, and combine it with the overlapping data of the robot affecting other alternative switching ports to determine the abnormal response strategy for reading delays in different alternative switching ports. Based on the abnormal response strategy and the monitoring port to be monitored and processed, use the big model to generate and process the process automation robot.

2. The large model-based robotic process automation generation method according to claim 1, characterized in that: The candidate robot is an existing process automation robot that can read data of the data type of the monitoring port.

3. The large model-based robotic process automation generation method according to claim 1, characterized in that: The method for determining the impact of the monitoring port on the robot is: Determining the number of ports monitored by the candidate robot for the monitoring port based on the port monitoring data of the candidate robot for the monitoring port; Whether the candidate robot is an influencing robot is determined according to the number of monitored ports of the candidate robot and the number of candidate robots.

4. The method for generating a large model-based robotic process automation according to claim 1, wherein: Determine the impact of switching to existing process automation robots to meet requirements, including: Using the overlap data of the impact monitoring ports of different candidate robots, determine the impact monitoring port whose overlap number with other candidate robots is less than a preset overlap number, and use it as an independent impact port; Determining a switching-affected robot among the candidate robots according to the number of the independent-affected ports; Based on the number of robots affected by the switch, determine whether the degree of switch impact on existing process automation robots is difficult to meet the requirements.

5. The method for generating a large model-based robotic process automation system according to claim 1, wherein: The method for determining the candidate switching port among the monitoring ports is as follows: Determining the number of influencing robots of the monitoring port based on the influencing robots of the monitoring port; Determining the number of the impact monitoring ports of different impact robots according to the composition data of the impact monitoring ports of different impact robots; Based on the number of monitoring ports affected by the influencing robot of the monitoring port, it is determined whether the monitoring port is a candidate switching port.

6. The method for generating a large model-based robotic process automation according to claim 5, wherein: When the monitoring port does not belong to the alternative switching port, when there is a reading delay on the monitoring port, it is directly set as a fault port temporarily until the preset time period passes and then the process automation robot is used to read the port data.

7. The method for generating a large model-based robotic process automation system according to claim 1, wherein: The read delay refers to a state where the time taken to read data is longer than a preset time and the port does not respond.

8. The method for generating a large model-based robotic process automation according to claim 1, wherein: The method for determining the abnormal response strategy when the candidate switching port has a read delay is as follows: Determining the number of candidate switching ports to be monitored using the composition data of the candidate switching ports to be monitored; Determine the number of overlaps between the influencing robots and other candidate switching ports through overlap data of the influencing robots between the other candidate switching ports; According to the number of the candidate switching ports and the number of overlaps between different candidate switching ports and other candidate switching ports that affect the robot, an abnormal response strategy for the existence of a read delay in the candidate switching port is determined.

9. The method for generating a large model-based robotic process automation system according to claim 1, wherein: Generate and process process automation robots, including: The abnormal response strategies of different monitoring ports and the monitoring ports to be monitored are input into the large model; Use large models to generate process automation robots.

10. A computer system comprising: A memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, characterized in that when the processor runs the computer program, it executes a large model-based robotic process automation generation method as described in any one of claims 1-9.

Images