RPA knowledge base updating method of AI agent

Abstract

The invention discloses an RPA knowledge base updating method of an AI agent, and relates to the field of robot process automation, and the method comprises the steps: generating a process description by using an LLM of the AI agent; the flow description is converted into a flow chart # imgabs0 #; an RPA knowledge base of the AI agent is constructed, the RPA knowledge base comprises executable process knowledge and abstract process knowledge, and each piece of abstract process knowledge corresponds to a plurality of pieces of executable process knowledge; calculating the similarity between the flow chart # imgabs 1 # and the abstract flow knowledge, and finding the most similar abstract flow knowledge # imgabs 2 #; performing similarity measurement on executable flow knowledge corresponding to the flow charts # imgabs3 # and # imgabs4 #; fusing the executable process knowledge of which the similarity is greater than a threshold value with the flow chart # imgabs5 # to obtain a new executable process knowledge set; new abstract process knowledge is summarized through a large language model, and an RPA knowledge base of the AI agent is updated. According to the method, the process can be automatically updated and optimized according to the new task.

Description

Technical Field

[0001] The present invention relates to the field of robotic process automation, and in particular to a method for updating an RPA knowledge base of an AI agent. Background Art

[0002] Robotic Process Automation (RPA) is also known as software robots. With RPA technology, you can configure RPA scripts to allow robots to simulate human user operations, interact with various software in the operating system, and perform repetitive or error-prone business process tasks, such as processing transactions and replying to emails. RPA technology can quickly and accurately process a large number of repetitive process tasks, improve the efficiency of process execution, and also reduce the probability of errors during process execution.

[0003] Large Language Model (LLM) has shown excellent performance in natural language text generation and code generation tasks due to its powerful semantic understanding ability on natural corpus. However, in the field of robotic process automation, the numerous process commands bring various paths for the completion of process tasks. At the same time, each process command has a unique configuration syntax, which brings challenges to the automatic generation of process commands, making it impossible to rely solely on large language models to automatically generate process commands. An adaptive architecture is needed to apply the powerful semantic understanding ability of large language models to the field of robotic process automation and promote the wider application and implementation of RPA technology. AI agent refers to an intelligent agent that can perceive the environment, understand it autonomously, make decisions and perform actions. Thanks to the powerful language understanding ability of LLM, AI agent based on LLM has powerful reasoning, planning and interaction capabilities. Traditional robotic process automation commands rely on predefined rules and processes, and it is difficult to cope with process changes or abnormal situations. Combining the intelligent decision-making ability of AI agent with the efficient execution ability of RPA can make up for the shortcomings of traditional RPA and realize a more intelligent automation system. The knowledge base plays an important role in the technology of AI agent intelligently generating RPA commands. The knowledge base contains historical records and experience, which can help AI agents quickly respond to complex problems. However, as the amount of tasks increases, a large amount of redundant and low-quality process information may accumulate in the AI ​​agent's knowledge base, resulting in reduced query efficiency and may even interfere with the AIagent's generation of RPA commands. Therefore, in order to prevent too much redundant information in the knowledge base, the information in the knowledge base also needs to have an update mechanism. A robotic process automation knowledge base that can continuously update itself can help AI agents generate RPA commands by providing useful information, thereby promoting the further development of RPA technology. Summary of the invention

[0004] The purpose of the present invention is to solve the problem that a large amount of redundant process information is accumulated in the knowledge base update of robotic process automation, and to propose an RPA knowledge base update method of an AI agent, comprising the following steps: S1. Use the AI ​​agent’s large language model to summarize the current tasks and processes, remove redundant information, and generate a process description; S2. Convert the process description into a flowchart through the flowchart construction module ; S3. Build the RPA knowledge base of the AI ​​agent, including executable process knowledge and abstract process knowledge. Abstract process knowledge is a summary of several executable process knowledge with similarity greater than a set value, and each abstract process knowledge corresponds to several executable process knowledge. S4. Calculation flow chart Similarity with abstract process knowledge, find the most similar abstract process knowledge , and abstract process knowledge Corresponding executable process knowledge set ; S5. Flowchart and executable process knowledge set Perform similarity measurement; S6. Neutralization Flowchart Executable process knowledge and flowcharts with similarity greater than a threshold The new executable process knowledge set is integrated to obtain a new set of executable process knowledge. Based on the new set of executable process knowledge, new abstract process knowledge is summarized through the large language model of the AI ​​agent, and the RPA knowledge base of the AI ​​agent is updated.

[0005] Furthermore, the calculation flow chart The similarity with abstract process knowledge is expressed as: ; in, express and The graph similarity of Represents abstract process knowledge, Represents the editing cost.

[0006] Further, ; Where n represents the number of edit operations, represents the cost of the i-th editing operation; ; in, Representation process and The semantic similarity of z represents a constant, the process and Belong to the node and , the i-th editing operation represents Modified to ; ; in, express A real vector of , express A real vector of , It means to find the magnitude of a vector.

[0007] Furthermore, according to the editing cost Get the final editing cost , using the final editing cost Calculation flow chart Similarity to abstract process knowledge: , based on editing costs Get the final editing cost The process is: Setting cost thresholds ,when When and Mapping, update status ;when , stop mapping, threshold as the current editing cost; for Map the unmapped nodes in For each active node that is not matched in the , we continue to find the mapping with the minimum editing cost and update the state ,until All nodes in Matching, output the final editing cost is .

[0008] Further, Neutralization Flowchart Executable process knowledge and flowcharts with similarity greater than a threshold The specific process of fusion is as follows: by The process with the least number of nodes As the basis, express Neutralization Flowchart The executable process knowledge with similarity greater than the threshold will be and Modify the cost The nodes are merged into one node. Indicates a set threshold; when modifying the cost ,Will Appeared in Nodes and control flows not in the .

[0009] Furthermore, if Neutralization Flowchart The executable process knowledge with similarity greater than the threshold is an empty set, and the executable process set corresponding to the most similar abstract process knowledge is updated to ,in, represents the set of executable processes corresponding to the most similar abstract process knowledge, Indicates updated .

[0010] The present invention also proposes an RPA knowledge base update system for an AI agent, comprising: The process description generation module is used to summarize the current tasks and processes using the AI ​​agent's large language model, remove redundant information, and generate a process description; Flowchart generation module, used to convert process description into flowchart through flowchart construction module ; The knowledge base construction module is used to build the RPA knowledge base of the AI ​​agent, including executable process knowledge and abstract process knowledge. Abstract process knowledge is a summary of several executable process knowledge with similarity greater than a set value, and each abstract process knowledge corresponds to several executable process knowledge. The first similarity calculation module is used to calculate the flow chart Similarity with abstract process knowledge, find the most similar abstract process knowledge , and abstract process knowledge Corresponding executable process knowledge set ; The second similarity calculation module is used to convert the flowchart and executable process knowledge set Perform similarity measurement; Knowledge base update module, used to update Neutralization Flowchart Executable process knowledge and flowcharts with similarity greater than a threshold The new executable process knowledge set is integrated to obtain a new set of executable process knowledge. Based on the new set of executable process knowledge, new abstract process knowledge is summarized through the large language model of the AI ​​agent, and the RPA knowledge base of the AI ​​agent is updated.

[0011] The present invention also proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned RPA knowledge base update method of the AI ​​agent.

[0012] The present invention also proposes an electronic device, comprising a processor and a memory, wherein the processor and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises computer-readable instructions, and the processor is configured to call the computer-readable instructions to execute the above-mentioned AI agent's RPA knowledge base update method.

[0013] The beneficial effects brought by the technical solution provided by the present invention are: The present invention uses a large language model to summarize the current task and process; converts the process into a flowchart through a flowchart construction module; compares the abstract knowledge of the knowledge base with the current process knowledge and the abstract process knowledge set to find the most similar abstract process knowledge; measures the similarity of the process knowledge associated with the flowchart and the executable process knowledge, selects the executable process knowledge with a similarity greater than a threshold, and merges it with the current flowchart; and summarizes the current process knowledge set using LLM. The present invention reduces the number of similarity comparisons and improves the efficiency of queries by storing knowledge of different granularities; generates a more adaptable general process through a large language model, which can be applied to similar tasks in different scenarios, thereby improving the reuse rate of the process and reducing the time and cost of task processing; reduces the redundant process information accumulated in the knowledge base update through knowledge base fusion; combines the large language model and similarity search to enable the system to automatically update and optimize the process according to the new task, thereby enhancing the system's self-learning ability and adaptability to environmental changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a flow chart of a method for updating an RPA knowledge base of an AI agent according to an embodiment of the present invention; Figure 2 This is the process knowledge fusion process of the embodiment of the present invention; Figure 3 It is a block diagram of an electronic device in an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0015] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0016] The RPA knowledge base of the AI ​​agent is a knowledge management system that combines the AI ​​agent and RPA technology. The knowledge base is a system used to store and manage process knowledge, providing decision support for the AI ​​agent and improving its execution efficiency. When the AIagent is running, if a new requirement is proposed, the AI ​​agent will first query the knowledge base, and the knowledge base will output the historical process knowledge that meets the new requirement to the AI ​​agent. Finally, the AI ​​agent generates new process knowledge that meets the new requirement based on the historical process knowledge, and then generates RPA commands.

[0017] Example 1: A flowchart of a method for updating an RPA knowledge base of an AI agent according to an embodiment of the present invention is as follows Figure 1 , specifically including the following steps: S1. Use the AI ​​agent’s large language model to summarize the current tasks and processes, remove redundant information, and generate a process description.

[0018] When the process is successfully executed, you can get the current task and the resulting process Through the large language model Abstract each process step in the process and finally generate the corresponding process description ,Right now .

[0019] S2. Convert the process description into a flowchart through the flowchart construction module .

[0020] The flowchart construction module is specifically used to describe the text of the process. Converted into a flow chart component. This module is parsed Each action in the graph is mapped to a node in the graph. Using a large language model, we can identify and analyze the order relationship and control structure between actions, and then establish directed edges between nodes. , and finally build a complete flowchart .

[0021] S3. Build the RPA knowledge base of the AI ​​agent. The knowledge base consists of two kinds of knowledge with different granularity, namely executable process knowledge and abstract process knowledge. Abstract process knowledge is a summary of several related executable process knowledge with similarity greater than a set value. Each abstract process knowledge corresponds to several executable process knowledge. Executable process knowledge refers to process knowledge that has been used in practice and can be correctly executed. All knowledge is saved in the form of flowcharts, and the abstract knowledge set , for some abstract process knowledge The corresponding associated executable process set is When searching, the most similar abstract process knowledge can be searched first, and then the executable process knowledge set associated with the abstract process knowledge can be searched, which can improve efficiency.

[0022] S4. Calculation flow chart Similarity with abstract process knowledge, find the most similar abstract process knowledge , and abstract process knowledge Corresponding executable process knowledge set .

[0023] The flowchart Sequentially and Each abstract process knowledge in The similarity calculation module of the input graph returns the calculation result. .

[0024] The graph similarity calculation module is implemented based on the edit distance of the graph. The specific implementation process is as follows: First, establish a node mapping from one graph to another. The current state Indicates from arrive Partial matching of function Indicates the editing cost. Set the cost threshold ,when When , we continue to find the mapping with the minimum editing cost , update the state s; when , then stop mapping, threshold As the current cost. Not yet mapped nodes, try to map them to Each active node w that is not matched in . As before, we continue to find the mapping with the minimum editing cost , update the state s until All nodes in the If matched, the final editing cost is output as .at last, and Similarity ,when hour, Minimum.

[0025] Edit Operation It includes five operations: adding nodes, deleting nodes, modifying nodes, adding edges, and deleting edges. The editing costs of adding nodes, deleting nodes, adding edges, and deleting edges are constants, and the cost of modifying nodes is obtained by calculating the vector similarity between the processes in the nodes. For example, for the node and , which include processes and , using word vector models (such as Word2Vec) to transform the process and Mapping to real vector and real vector , calculation process and The semantic similarity of ,Will Modified to The cost of (i.e., the cost of the i-th editing operation) is , is a constant. Mapping Contains a series of editing operations , editing cost , n is the number of editing operations.

[0026] Compare all similarity calculation results and get the smallest result , returns the most similar abstract process knowledge , and abstract process knowledge Corresponding executable process knowledge set .

[0027] S5. Flowchart and executable process knowledge set Perform similarity measurement.

[0028] The graph similarity calculation module is used to calculate Respectively The similarity of each executable flowchart in is selected, and the similarity is greater than the threshold Executable process knowledge .

[0029] S6. Neutralization Flowchart Executable process knowledge and flowcharts with similarity greater than a threshold The new executable process knowledge set is integrated to obtain a new set of executable process knowledge. Based on the new set of executable process knowledge, new abstract process knowledge is summarized through the large language model of the AI ​​agent, and the RPA knowledge base of the AI ​​agent is updated.

[0030] if In order to reduce storage space, and Fusion, get .also, Corresponding executable process set Updated to .

[0031] The fusion process is as follows: The process with the least number of nodes Based on the other processes Make changes. and Process For example, first change the process and Process Modify the cost If there are obvious divergence nodes, that is, the modification cost between the two nodes When middle Nodes and control flows not in the , where control flow is used to describe the logical order between nodes. Finally, check the comparison and The control flow of Add the control flow that was not added to , and finally get .

[0032] if , The corresponding executable process set is updated to Based on the new executable process knowledge set, new abstract process knowledge is summarized through the large language model, that is, . Update the RPA knowledge base of AIagent.

[0033] Based on the technical solution of the present invention, the implementation process of the present invention in practical application is described with the following embodiments.

[0034] Assume the current task Yes: You need to copy the content in the document origin.docx to the document res.docx.

[0035] Successfully executed process yes: 1. Open the document origin.docx; 2. Open the document res.docx; 3. Select all the contents in the document origin.docx; 4. Copy the contents of the document origin.docx; 5. Paste the copied content into res.docx; 6. Save the document res.docx; 7. Close the document origin.docx; 8. Close the document res.docx.

[0036] The task Passed to the large language model, the large language model is used for the task Abstract and get the task The content of document A is copied to document B. Then the large language model is used to Analyze and summarize, generate processes : Open document A; Open document B; Select all the contents in document A; Copy the contents of document A; Paste the copied content into B; Save document B; Close document A; Close document B.

[0037] The process Convert to Flowchart , the structure is as shown in the attached figure Figure 2 As shown. The most similar abstract process knowledge is found in the input to the abstract process knowledge comparison module For example, "Copy content --> Paste content". Then search through the executable process knowledge comparison module The associated executable process knowledge set that meets the conditions, such as a flowchart , the process knowledge included is The process knowledge fusion process of the embodiment of the present invention is as follows: Figure 2 As shown. and Fusion, get Figure 2 In . as follows: Get the text of the first page in pdf file A; Open document B; Paste the obtained text into B; Save document B; Close document B.

[0038] Finally, the abstract process knowledge and executable process set are updated.

[0039] Embodiment 2: The present invention also proposes an RPA knowledge base update system for an AI agent, comprising: The process description generation module is used to summarize the current tasks and processes using the AI ​​agent's large language model, remove redundant information, and generate a process description; Flowchart generation module, used to convert process description into flowchart through flowchart construction module ; The knowledge base construction module is used to build the RPA knowledge base of the AI ​​agent, including executable process knowledge and abstract process knowledge. Abstract process knowledge is a summary of several executable process knowledge with similarity greater than a set value, and each abstract process knowledge corresponds to several executable process knowledge. The first similarity calculation module is used to calculate the flow chart Similarity with abstract process knowledge, find the most similar abstract process knowledge , and abstract process knowledge Corresponding executable process knowledge set ; The second similarity calculation module is used to convert the flowchart and executable process knowledge set Perform similarity measurement; Knowledge base update module, used to update Neutralization Flowchart Executable process knowledge and flowcharts with similarity greater than a threshold The new executable process knowledge set is integrated to obtain a new set of executable process knowledge. Based on the new set of executable process knowledge, new abstract process knowledge is summarized through the large language model of the AI ​​agent, and the RPA knowledge base of the AI ​​agent is updated.

[0040] Embodiment 3: In an exemplary embodiment, a computer-readable storage medium is included, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned RPA knowledge base update method of the AI ​​agent is implemented.

[0041] Example 4: Please refer to Figure 3 In an exemplary embodiment, an electronic device is also included, including at least one processor, at least one memory, and at least one communication bus.

[0042] Among them, a computer program is stored in the memory, and the computer program includes computer-readable instructions. The processor calls the computer-readable instructions stored in the memory through the communication bus to execute the above-mentioned RPA knowledge base update method of the AI ​​agent.

[0043] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for updating an RPA knowledge base of an AI agent, characterized in that: The following steps are involved: S1. Use the AI ​​agent’s large language model to summarize the current tasks and processes, remove redundant information, and generate a process description; S2. Convert the process description into a flowchart through the flowchart construction module ; S3. Build the RPA knowledge base of the AI ​​agent, including executable process knowledge and abstract process knowledge. Abstract process knowledge is a summary of several executable process knowledge with similarity greater than a set value, and each abstract process knowledge corresponds to several executable process knowledge. S4. Calculation flow chart Similarity with abstract process knowledge, find the most similar abstract process knowledge , and abstract process knowledge Corresponding executable process knowledge set ; S5. Flowchart and executable process knowledge set Perform similarity measurement; S6. Neutralization Flowchart Executable process knowledge and flowcharts with similarity greater than a threshold The new executable process knowledge set is integrated to obtain a new set of executable process knowledge. Based on the new set of executable process knowledge, new abstract process knowledge is summarized through the large language model of the AI ​​agent, and the RPA knowledge base of the AI ​​agent is updated.

2. The method according to claim 1, characterized in that Calculation flow chart The similarity with abstract process knowledge is expressed as: ； in, express and The graph similarity of Represents abstract process knowledge, Represents the editing cost.

3. The method according to claim 2, characterized in that ； Where n represents the number of edit operations, represents the cost of the i-th editing operation; ； in, Representation process and The semantic similarity of z represents a constant, the process and Belong to the node and , the i-th editing operation represents Modified to ; ； in, express A real vector of , express A real vector of , It means to find the magnitude of a vector.

4. The method according to claim 3, characterized in that According to editing costs Get the final editing cost , using the final editing cost Calculation flow chart Similarity to abstract process knowledge: , based on editing costs Get the final editing cost The process is: Setting cost thresholds ,when When and Mapping, update status ;when , stop mapping, threshold as the current editing cost; for Map the unmapped nodes in For each active node that is not matched in the , we continue to find the mapping with the minimum editing cost and update the state ,until All nodes in Matching, output the final editing cost is .

5. The method according to claim 1, characterized in that Will Neutralization Flowchart Executable process knowledge and flowcharts with similarity greater than a threshold The specific process of fusion is as follows: by The process with the least number of nodes As the basis, express Neutralization Flowchart The executable process knowledge with similarity greater than the threshold will be and Modify the cost The nodes are merged into one node. Indicates a set threshold; when modifying the cost ,Will Appeared in Nodes and control flows not in the .

6. The method according to claim 5, characterized in that if Neutralization Flowchart The executable process knowledge with similarity greater than the threshold is an empty set, and the executable process set corresponding to the most similar abstract process knowledge is updated to ,in, represents the set of executable processes corresponding to the most similar abstract process knowledge, Indicates updated .

7. An AI agent RPA knowledge base update system, characterized in that: include: The process description generation module is used to summarize the current tasks and processes using the AI ​​agent's large language model, remove redundant information, and generate a process description; Flowchart generation module, used to convert process description into flowchart through flowchart construction module ; The knowledge base construction module is used to build the RPA knowledge base of the AI ​​agent, including executable process knowledge and abstract process knowledge. Abstract process knowledge is a summary of several executable process knowledge with similarity greater than a set value, and each abstract process knowledge corresponds to several executable process knowledge. The first similarity calculation module is used to calculate the flow chart Similarity with abstract process knowledge, find the most similar abstract process knowledge , and abstract process knowledge Corresponding executable process knowledge set ; The second similarity calculation module is used to convert the flowchart and executable process knowledge set Perform similarity measurement; Knowledge base update module, used to update Neutralization Flowchart Executable process knowledge and flowcharts with similarity greater than a threshold The new executable process knowledge set is integrated to obtain a new set of executable process knowledge. Based on the new set of executable process knowledge, new abstract process knowledge is summarized through the large language model of AI agent, and the RPA knowledge base of AI agent is updated.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the processor and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises computer-readable instructions, and the processor is configured to call the computer-readable instructions to execute the method according to any one of claims 1 to 6.

Images