Business processing method, apparatus and device based on ai, rpa and ai agent

Abstract

The application provides a business processing method, device and equipment based on AI, RPA and AI Agent, and relates to the field of AI, RPA and AI Agent. The method comprises the following steps: calling an LLM to perform intent recognition on scene generation requirements associated with a target business scene, obtaining a target intent, and generating an information-based business process adapted to the target intent; performing elementization processing on a plurality of hierarchical process nodes in the information-based business process to obtain a plurality of process elements; performing structured processing on the information-based business process according to the categories to which the plurality of process elements belong to obtain a structured business process; and building process elements in the structured business process to create process entities of the process elements and generate execution sequences of the process entities. Therefore, the technical threshold and application threshold can be reduced, and the efficiency of business process generation and building can be improved. In addition, the accuracy of business process generation and building can be improved based on AI, RPA and AI Agent technology.

Description

Technical Field

[0001] This application relates to the fields of Artificial Intelligence (AI), Robotic Process Automation (RPA), and Artificial Intelligence Agent (AI Agent) for digital workforce platforms, and particularly to a business processing method, apparatus, and device based on AI, RPA, and AI Agent. Background Technology

[0002] Robotic Process Automation (RPA) uses specific "robot software" to simulate human operations on a computer 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] The Artificial Intelligence Agent (AI Agent) on the digital workforce platform can perceive its environment, make decisions, and execute actions. Unlike traditional artificial intelligence, it possesses the ability to think and act independently, and can utilize tools to achieve given goals. Based on Large Language Models (LLMs) as its core computing engine, the AI ​​Agent can engage in dialogue, perform tasks, reason, and exhibit a degree of autonomy. It has the ability to autonomously understand, perceive, plan, remember, and use tools, enabling it to automate complex tasks. Specifically, the AI ​​Agent, driven by LLM and integrating various AI capabilities, can interact with employees using natural language, understand their instructions and needs, and provide feedback and responses; it can acquire domain-specific knowledge relevant to the business to complete complex professional tasks; it can break down complex tasks into several executable tasks and use data and tools to complete them; it can also collaborate with employees, and AI Agents can collaborate with each other to complete complex tasks, enabling digital employees to leap from automation to intelligence, helping employees complete their work more efficiently, and fully realizing human-machine collaboration.

[0005] In related technologies, business processes are mainly restructured in the following ways when using internal business systems: business personnel understand and become familiar with the original business system, and information-based business processes are designed and developed using process design tools.

[0006] However, the above restructuring methods not only require a lot of human resources to understand and learn the business, but also suffer from low accuracy and efficiency in business process restructuring due to limitations in human experience. Summary of the Invention

[0007] This application provides a business processing method, apparatus, and device based on AI, RPA, and AI Agent to solve one of the technical problems existing in related technologies. The technical solution is as follows:

[0008] In a first aspect, embodiments of this application provide a business processing method based on AI, RPA, and AI Agent, including:

[0009] The large language model is invoked to perform intent recognition on the scene generation requirements associated with the target business scenario, obtain the target intent, and generate an information business process adapted to the target intent; wherein, the information business process includes multiple levels of process nodes.

[0010] The process nodes at multiple levels are processed into elements to obtain multiple process elements;

[0011] Based on the categories to which the multiple process elements belong, the information-based business process is structured to obtain a structured business process.

[0012] At least some process elements in the structured business process are constructed to create process entities of the at least some process elements, and the execution order of each process entity is generated; wherein each process entity is used to process the business under the target business scenario.

[0013] Secondly, embodiments of this application provide a business processing apparatus based on AI, RPA, and AI Agent, including:

[0014] The first invocation module is used to invoke a large language model to perform intent recognition on the scene generation requirements associated with the target business scenario, obtain the target intent, and generate an information business process adapted to the target intent; wherein, the information business process includes multiple levels of process nodes.

[0015] The first processing module is used to perform element-based processing on the process nodes at multiple levels to obtain multiple process elements;

[0016] The second processing module is used to perform structured processing on the information business process according to the category to which the multiple process elements belong, so as to obtain a structured business process.

[0017] A construction module is used to construct at least some of the process elements in the structured business process, to create process entities of the at least some process elements, and to generate the execution order of each process entity; wherein each process entity is used to process the business under the target business scenario.

[0018] Thirdly, embodiments of this application provide an electronic device comprising a memory and a processor. The memory and the processor communicate with each other via an internal connection path. The memory stores instructions, and the processor executes the instructions stored in the memory. When the processor executes the instructions stored in the memory, it causes the processor to perform the method described in any of the above embodiments.

[0019] Fourthly, embodiments of this application provide a computer-readable storage medium that stores a computer program, wherein when the computer program is run on a computer, the methods in any of the above-described embodiments are executed.

[0020] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the methods in any of the above-described embodiments.

[0021] The advantages or beneficial effects of the above technical solutions include at least the following:

[0022] Users only need to provide the scenario generation requirements for their target business scenario, and the system can automatically generate information-based business processes by calling a large language model. Based on these information-based business processes, a structured business process is then generated. On the one hand, users do not need to spend considerable time and resources familiarizing themselves with and organizing the business process content, thus lowering the technical and application barriers. On the other hand, it also improves the efficiency and accuracy of business process generation. Furthermore, the system automatically builds the process elements within the structured business process. This eliminates the need for users to spend time building the business process system itself, allowing them to focus their time and energy on more valuable creative work. It also significantly saves time and costs associated with building traditional business process systems, improving the accuracy and efficiency of business process system construction. In addition, AI, RPA, and AI Agent technologies can be used to further enhance the accuracy of business process generation and construction.

[0023] The above overview 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 this application will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0024] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in this application and should not be construed as limiting the scope of this application.

[0025] Figure 1 This is a flowchart of a business processing method based on AI, RPA, and AI Agent provided in one embodiment of this application;

[0026] Figure 2 This is a flowchart of a business processing method based on AI, RPA, and AI Agent provided in another embodiment of this application;

[0027] Figure 3 This is a flowchart of a business processing method based on AI, RPA, and AI Agent provided in another embodiment of this application;

[0028] Figure 4 This is a flowchart of a business processing method based on AI, RPA, and AI Agent provided in another embodiment of this application;

[0029] Figure 5 These are schematic diagrams of reference examples provided in the embodiments of this application;

[0030] Figure 6 This is a flowchart of a business processing method based on AI, RPA, and AI Agent provided in another embodiment of this application;

[0031] Figure 7 This is a schematic diagram illustrating the implementation principle of an embodiment of this application;

[0032] Figure 8 This is a structural diagram of a business processing apparatus based on AI, RPA, and AI Agent provided in one embodiment of this application;

[0033] Figure 9 A structural block diagram of an electronic device according to an embodiment of this application is shown. Detailed Implementation

[0034] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0035] With the popularization and application of artificial intelligence (AI) and automation technologies, the construction and management of enterprise internal information systems are still based on the design of information business processes according to existing procedures, without applying AI and automation technologies to optimize and improve the efficiency of the original information business processes.

[0036] If you want to optimize the information-based business processes of existing businesses, the IT personnel need to understand and learn about the existing businesses and conduct a systematic review. This requires the IT personnel to have strong business understanding and experience.

[0037] In addition, IT personnel need to have a good understanding of the application of new AI technologies and need to combine the capabilities of artificial intelligence with the characteristics of business processes to optimize or even restructure them. At the same time, business processes will also change with business development and changes in the external environment, requiring significant time to adapt to and adjust to these changes.

[0038] In other words, the design and construction of business processes in related technologies involves manually designing and building business processes according to business requirements. On the one hand, for ordinary users, it is necessary to understand and learn the specific process of the business process, and users need to have certain business knowledge and experience. On the other hand, it is necessary to transform the business process into an information-based business process, which also requires users to have relative information technology capabilities.

[0039] To address these challenges and enable business processes to be optimized in tandem with the development of AI technology, thereby improving the work efficiency of business personnel, in any embodiment of this application, AI technology can be used to understand and analyze business processes, allowing AI technology to automatically optimize and reconstruct business processes, and return the optimization results to an intelligent and automated business process building platform to quickly achieve business process optimization and reconstruction.

[0040] In other words, to address at least one of the problems existing in related technologies, embodiments of this application propose a business processing method, apparatus, and device based on Artificial Intelligence (AI), Robotic Process Automation (RPA), and an Artificial Intelligence Agent (AI Agent) for a digital workforce platform. These and other aspects of the embodiments of this application will become clear with reference to the following description and accompanying drawings. In these descriptions and drawings, some specific implementations of the embodiments of this application are specifically disclosed to illustrate some ways of carrying out the principles of the embodiments of this application; however, it should be understood that the scope of the embodiments of this application is not limited thereto. Rather, the embodiments of this application include all variations, modifications, and equivalents falling within the spirit and scope of the appended claims.

[0041] Before describing the specific embodiments of this application, for ease of understanding, commonly used technical terms will first be introduced:

[0042] In the description of this application, the term "multiple" means two or more.

[0043] In the description of this application, the term "large language model" refers to a class of natural language processing models based on deep learning. Its main characteristics are a large number of model parameters and a complex neural network structure, which enable it to have powerful language understanding, context awareness and language generation capabilities. It can automatically learn useful feature representations from input data and generate relevant text.

[0044] In the description of this application, the term "target business scenario" refers to the business scenario to which the information business process to be created belongs, which can be determined by the user based on business needs.

[0045] In the description of this application, the term "scenario generation requirements" is used to indicate the user's scenario description, specification, or requirements for the target business scenario.

[0046] In the description of this application, the term "process node" refers to a node in an information-based business process, including but not limited to: a first-level business stage (referred to as a stage), a second-level business link (referred to as a link), and a third-level execution step (referred to as a step).

[0047] In the description of this application, the term "process element" refers to the basic unit or basic element obtained by elementalizing the node content of a process node, including but not limited to elements such as "stage", "link", and "step".

[0048] In the description of this application, the term "process entity" refers to the entity module (a module containing business logic) of a process element, which is used to implement the business logic of the process element.

[0049] In the description of this application, the term "specified technical field" refers to a pre-specified technical field, including but not limited to the following technical fields: automation, AI, AI processing, etc.

[0050] In the description of this application, the term "first prompt template" refers to a prompt template pre-configured for a target business scenario, used to instruct the large language model to perform information generation tasks in the workflow. It should be understood that in practical applications, the first prompt template can also be dynamically maintained and updated based on dynamic business needs under the target business scenario, and the embodiments of this application do not impose any limitations on this.

[0051] In the description of this application, the term "second prompt template" refers to a prompt template pre-configured for business process optimization tasks. It should be understood that in practical applications, the second prompt template can also be dynamically maintained and updated based on dynamic business needs in the target business scenario, and the embodiments of this application do not impose any limitations on this.

[0052] These and other aspects of the embodiments of this application will become clear from the following description and accompanying drawings. In these descriptions and drawings, some specific implementations of the embodiments of this application are specifically disclosed to illustrate some ways of carrying out the principles of the embodiments of this application; however, it should be understood that the scope of the embodiments of this application is not limited thereto. Rather, the embodiments of this application include all variations, modifications, and equivalents falling within the spirit and scope of the appended claims.

[0053] The following describes, with reference to the accompanying drawings, a business processing method, apparatus, and device based on AI, RPA, and AI Agent according to embodiments of this application.

[0054] Figure 1 This is a flowchart of a business processing method based on AI, RPA, and AI Agent provided in one embodiment of this application.

[0055] In one possible implementation provided in this application, the application exemplifies that the business processing method based on AI, RPA, and AI Agent is configured in a business processing device based on AI, RPA, and AI Agent. This business processing device can be applied to any electronic device with computing capabilities.

[0056] The electronic device can be a personal computer, a mobile terminal, a server (or a server), etc. The mobile terminal can be a mobile phone, a tablet computer, a personal digital assistant, or other hardware device with various operating systems.

[0057] In another possible implementation of this application embodiment, the business processing method based on AI, RPA and AI Agent can be applied to an AI Agent, wherein the AI ​​Agent can run on any electronic device with computing capabilities.

[0058] In another possible implementation of this application embodiment, the business processing method based on AI, RPA, and AI Agent can be applied to an intelligent automation platform. This intelligent automation platform can seamlessly integrate multiple capabilities such as RPA, Intelligent Document Processing (IDP), Conversational AI (CoAI), and Process Mining. It possesses five major functional categories: "business understanding," "process creation," "anywhere operation," "centralized management and control," and "human-machine collaboration." This enables enterprises to achieve end-to-end intelligent automation of business processes, replacing manual operations, further improving business efficiency, and accelerating digital transformation.

[0059] Intelligent Document Processing (IDP) is one of the core capabilities of the intelligent automation platform. IDP utilizes AI technologies such as Optical Character Recognition (OCR), Computer Vision (CV), Natural Language Processing (NLP), and Knowledge Graph (KG) to perform tasks such as identification, classification, element extraction, verification, comparison, and error correction on various types of documents, helping enterprises achieve intelligent and automated document processing.

[0060] like Figure 1 As shown, the business processing method based on AI, RPA, and AI Agent may include the following steps S101 to S104:

[0061] Step S101: Call the large language model to perform intent recognition on the scenario generation requirements associated with the target business scenario, obtain the target intent, and generate an information business process that matches the target intent; wherein, the information business process includes multiple levels of process nodes.

[0062] In this embodiment, firstly, the user-inputted scenario generation requirements associated with the target business scenario can be obtained; wherein, the input methods for the scenario generation requirements include, but are not limited to, touch input (such as swiping, clicking, etc.), keyboard input, voice input, etc. Then, a large language model can be invoked to perform business-oriented understanding of the scenario generation requirements, obtaining the user's actual intent (referred to as the target intent in this application), and generating an information-based business process adapted to the target intent, wherein the information-based business process includes multiple levels of process nodes.

[0063] As an example, an information-based business process may include multiple first-level business stages, each business stage may include at least one second-level business link, and each business link may include multiple third-level execution steps.

[0064] Step S102: Perform elementization processing on process nodes at multiple levels to obtain multiple process elements.

[0065] In this embodiment of the application, the node content (or process content) of process nodes at multiple levels can be classified to obtain the category to which each process node belongs (such as "stage", "link", "step"). Based on the categories to which the process nodes at multiple levels belong, the process nodes at multiple levels can be categorized to obtain process elements under multiple categories.

[0066] Step S103: Based on the categories to which multiple process elements belong, perform structured processing on the information business process to obtain a structured business process.

[0067] In this embodiment of the application, the information business process can be structured according to the category to which multiple process elements belong, so as to obtain a structured business process.

[0068] Among them, structured business processes can be used to indicate the correspondence between multiple process elements and their execution order.

[0069] Step S104: Construct at least some of the process elements in the structured business process to create process entities of at least some of the process elements, and generate the execution order of each process entity; wherein, each process entity is used to handle business under the target business scenario.

[0070] At least some of the process elements can be selected by the user from multiple process elements in the structured business process.

[0071] In the embodiments of this application, at least some process elements in a structured business process can be constructed to create process entities of the at least some process elements and generate the execution order of each process entity. Thus, during the business processing stage, each process entity can be executed sequentially based on the execution order of each process entity, ensuring that the business is executed in the correct order and improving the accuracy of business execution.

[0072] The business processing method based on AI, RPA, and AI Agent in this application embodiment allows users to automatically generate information-based business processes by simply providing the scenario generation requirements for the target business scenario and calling a large language model. This automatically generates structured business processes based on these information-based processes. On the one hand, users do not need to spend significant time and resources familiarizing themselves with and organizing the business process content, reducing both the technical and application barriers. On the other hand, it improves the efficiency and accuracy of business process generation. Furthermore, the automatic construction of process elements within the structured business process eliminates the need for users to spend time building the business process system, allowing them to focus their time and energy on more valuable creative work. This significantly saves time and costs associated with building traditional business process systems, improving the accuracy and efficiency of business process system construction. Moreover, the accuracy of business process generation and construction can be further enhanced by leveraging AI, RPA, and AI Agent technologies.

[0073] To clearly illustrate how the information-based business process is structured according to the categories to which multiple process elements belong in any embodiment of this application, resulting in a structured business process, this application also proposes a business processing method based on AI, RPA, and AIAgent.

[0074] Figure 2 This is a flowchart of a business processing method based on AI, RPA, and AI Agent provided in another embodiment of this application.

[0075] It should be noted that the business processing method based on AI, RPA and AI Agent can be executed alone, or it can be executed together with any embodiment or possible implementation in the embodiment of this application, or it can be executed together with any technical solution in related technologies. The embodiments of this application do not limit this.

[0076] like Figure 2 As shown, the business processing method based on AI, RPA, and AI Agent may include the following steps S201 to S205:

[0077] Step S201: Call the large language model to perform intent recognition on the scenario generation requirements associated with the target business scenario, obtain the target intent, and generate an information business process that matches the target intent; wherein, the information business process includes multiple levels of process nodes.

[0078] Step S202: Elementize the process nodes at multiple levels to obtain multiple process elements.

[0079] The explanation of steps S201 to S202 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0080] Step S203: Generate execution sequence numbers corresponding to multiple process elements based on the categories to which they belong and their positions in the information business process.

[0081] The smaller the execution sequence number of a process element, the earlier the corresponding business logic is executed; conversely, the larger the execution sequence number of a process element, the later the corresponding business logic is executed.

[0082] In this embodiment, execution sequence numbers corresponding to multiple process elements can be generated based on the category to which they belong and their position in the information-based business process. The earlier a process element appears in the sequence, the smaller its execution sequence number.

[0083] As an example, the execution sequence number of a process element with the category "stage" can be a single digit. For instance, the execution sequence number of the first process element with the category "stage" can be 1, the second process element with the category "stage" can be 2, ..., and the execution sequence number of the Nth (N is a positive integer) process element with the category "stage" can be N.

[0084] The execution sequence number of a process element with the category "Step" can be a 2-digit number, and its display format is, for example, "xx". For example, for a process element located between the process element with execution sequence number 1 (marked as element 1) and the process element with execution sequence number 2 (marked as element 2), its execution sequence number can be "1.x". For instance, for the first process element with the category "Step" that is arranged after element 1 and before element 2, its execution sequence number can be "1.1", and for the second process element with the category "Step" that is arranged after element 1 and before element 2, its execution sequence number can be "1.2".

[0085] The execution sequence number of a process element with the category "Step" can be a 3-digit number, and its display format is, for example, "xxx". For example, for a process element located between the process element with execution sequence number 1.1 (marked as element 3) and the process element with execution sequence number 1.2 (marked as element 4), its execution sequence number can be "1.1.x". For example, for the first process element with the category "Step" that is arranged after element 3 and before element 4, its execution sequence number can be "1.1.1", and for the second process element with the category "Step" that is arranged after element 3 and before element 4, its execution sequence number can be "1.1.2".

[0086] Step S204: Generate a structured business process based on multiple process elements and their corresponding execution sequence numbers.

[0087] In this embodiment of the application, a structured business process can be generated based on multiple process elements and the execution sequence numbers corresponding to the multiple process elements.

[0088] In any embodiment of this application, the structured business process can be generated using the following steps A to B:

[0089] Step A: For any one of the multiple process elements, if the process element contains a specified technical field, you can add tag information to the process element based on the technical type to which the specified technical field belongs.

[0090] The types of technologies include, but are not limited to, automation and AI processing.

[0091] As an example, the technology type of a specified technology field contained in a process element can be used as the label information for that process element.

[0092] Step B: Generate a structured business process based on multiple process elements, their corresponding execution sequence numbers, and tag information.

[0093] That is, a structured business process, used to indicate the correspondence between process elements and execution sequence numbers and tag information.

[0094] In summary, structured business processes include not only the correspondence between process elements and execution sequence numbers, but also the correspondence between process elements and tag information. This allows for the orderly execution of the business logic of each process entity in subsequent business processing stages, based on both the execution sequence number and tag information, thereby improving the targeting, accuracy, and reliability of business execution.

[0095] Step S205: Construct at least some of the process elements in the structured business process to create process entities of at least some of the process elements, and generate the execution order of each process entity; wherein, each process entity is used to process the business under the target business scenario.

[0096] The explanation of step S205 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0097] The business processing method based on AI, RPA, and AI Agent in this application embodiment can accurately and effectively determine the execution sequence number corresponding to multiple process elements based on the category to which multiple process elements belong and the arrangement position of multiple process elements in the information business process. Thus, a structured business process can be generated effectively and accurately based on multiple process elements and their corresponding execution sequence numbers.

[0098] To clearly illustrate how at least some process elements in a structured business process are constructed in any embodiment of this application, this application also proposes a business processing method based on AI, RPA, and AI Agent.

[0099] Figure 3 This is a flowchart of a business processing method based on AI, RPA, and AI Agent provided in another embodiment of this application.

[0100] It should be noted that the business processing method based on AI, RPA and AI Agent can be executed alone, or it can be executed together with any embodiment or possible implementation in the embodiment of this application, or it can be executed together with any technical solution in related technologies. The embodiments of this application do not limit this.

[0101] like Figure 3 As shown, the business processing method based on AI, RPA, and AI Agent may include the following steps S301 to S307:

[0102] Step S301: Call the large language model to perform intent recognition on the scenario generation requirements associated with the target business scenario, obtain the target intent, and generate an information business process that matches the target intent; wherein, the information business process includes multiple levels of process nodes.

[0103] Step S302: Elementize the process nodes at multiple levels to obtain multiple process elements.

[0104] Step S303: Based on the categories to which multiple process elements belong, the information-based business process is structured to obtain a structured business process.

[0105] The explanation of steps S301 to S303 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0106] Step S304: For any process element among at least some process elements in the structured business process, determine the target API that matches the category to which any process element belongs from multiple application programming interfaces (APIs) of the business process building platform.

[0107] At least some of the process elements can be selected by the user from multiple process elements in the structured business process.

[0108] The API is used to create process entities (or process entity modules) corresponding to process elements. The process entities are used to implement the business logic of the process elements.

[0109] In this embodiment of the application, when constructing any one of the process elements in at least a portion of the process elements in a structured business process, a target API matching the category to which the process element belongs can be determined from multiple APIs of the business process construction platform. The matching relationship between the API and the category is pre-established.

[0110] Step S305: Call the target API to create a process entity for any process element.

[0111] Among them, a process entity refers to an entity module that contains business logic and is used to implement the business logic of process elements.

[0112] In this embodiment of the application, the target API can be called to create the process entity of the above-mentioned process element.

[0113] Step S306: Generate the attribute information of the process entity based on the tag information of any process element.

[0114] In this embodiment of the application, attribute information of the corresponding process entity can be generated based on the tag information of the process element.

[0115] As an example, when the label information of a process element includes automation, the attribute information of the process entity of that process element includes automation technology; when the label information of a process element includes AI processing, the attribute information of the process entity of that process element includes AI technology.

[0116] Step S307: Generate the execution order of each process entity based on the execution sequence number of each process element, so as to execute each process entity in sequence based on the execution order, thereby realizing the business processing under the target business scenario.

[0117] Among them, the execution sequence number is positively correlated with the execution order, that is, the smaller the execution sequence number, the earlier the execution order, and vice versa.

[0118] In this embodiment, the execution order of each process entity can be generated based on the execution sequence number of each process element, so that in the subsequent business processing stage, each process entity can be executed sequentially based on the execution order of each process entity to realize the business processing under the target business scenario.

[0119] In any embodiment of this application, the business processing method under the target business scenario may include, for example, the following steps C to F:

[0120] Step C: In response to the business processing time when the target business scenario arrives, execute each process entity sequentially according to the execution order of each entity element.

[0121] Among them, the business processing time is the time that is pre-configured for the target business scenario.

[0122] Step D: Query the attribute information of the currently executing process entity.

[0123] Step E: If the attribute information is automation technology, then call the RPA robot to execute the currently executing process entity.

[0124] Step F: If the attribute information is AI technology, then call the pre-configured AI algorithm to execute the currently executing process entity.

[0125] In summary, it can achieve automatic and orderly processing of business in the target business scenario, improving the timeliness and accuracy of business processing.

[0126] The business processing method based on AI, RPA, and AI Agent in this application embodiment can connect the generation of large language models with the construction of business process systems, analyze and identify the generated process content, transform it into structured process elements for business process construction, and connect to the API of the business process construction platform to realize the automated construction of business process systems. This can greatly save the time and cost of traditional business process system construction, and the automated identification and construction method also improves the accuracy and efficiency of business process system construction.

[0127] To clearly illustrate how the large language model generates an information-based business process adapted to the target intent in any embodiment of this application, this application also proposes a business processing method based on AI, RPA, and AI Agent.

[0128] Figure 4This is a flowchart of a business processing method based on AI, RPA, and AI Agent provided in another embodiment of this application.

[0129] It should be noted that the business processing method based on AI, RPA and AI Agent can be executed alone, or it can be executed together with any embodiment or possible implementation in the embodiment of this application, or it can be executed together with any technical solution in related technologies. The embodiments of this application do not limit this.

[0130] like Figure 4 As shown, the business processing method based on AI, RPA, and AI Agent may include the following steps S401 to S406:

[0131] Step S401: Obtain the scene generation requirements associated with the target business scenario, and obtain the first prompt template adapted to the target business scenario.

[0132] The first prompt template is used to instruct the large language model to perform information generation tasks in the execution process.

[0133] In this application embodiment, the first prompt template is a prompt template pre-configured for the target business scenario. In this application, stored data or configuration information can be queried to obtain the first prompt template adapted to the target business scenario.

[0134] In any embodiment of this application, in order to improve the prediction accuracy of the large language model, the first prompt template may also include a reference example, wherein the reference example is used to indicate a reference business process in a reference business scenario, and the reference business process includes multiple levels of reference process nodes.

[0135] The reference business scenario and the target business scenario may be the same business scenario or different business scenarios. This application embodiment does not impose any restrictions on this.

[0136] As an example, a reference example may be as follows: Figure 5 As shown, this includes a reference business process in a financial audit scenario.

[0137] Therefore, introducing reference examples for large language models can help reduce errors in the prediction and generation processes, and improve the accuracy, robustness and generalization ability of large language models.

[0138] Step S402: Use the scene generation requirements as execution parameters, and use the execution parameters to update the first prompt template to obtain the first prompt information.

[0139] In this embodiment of the application, the scene generation requirements under the target business scenario can be used as execution parameters, and the first prompt template can be filled using the execution parameters to obtain the first prompt information.

[0140] Step S403: The large language model is invoked to process the first prompt information, so as to identify the target intent to which the scene generation requirement belongs through the large language model, and generate an information business process that matches the target intent.

[0141] In this embodiment of the application, a large language model can be invoked to process the first prompt information, so as to identify the target intent to which the scenario generation requirement belongs based on the first prompt information, and generate an information business process that is adapted to the target intent; wherein, the information business process includes multiple levels of process nodes.

[0142] Step S404: Elementize the process nodes at multiple levels to obtain multiple process elements.

[0143] Step S405: Based on the categories to which multiple process elements belong, the information-based business process is structured to obtain a structured business process.

[0144] Step S406: Construct at least some of the process elements in the structured business process to create process entities of at least some of the process elements, and generate the execution order of each process entity; wherein, each process entity is used to process the business under the target business scenario.

[0145] The explanation of steps S404 to S406 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0146] The business processing method based on AI, RPA, and AI Agent in this application embodiment uses first prompt information as prior information to indicate the task information to be executed by the large language model, which can improve the prediction accuracy of the large language model, that is, improve the accuracy of information business process generation.

[0147] To clearly illustrate any embodiment of this application, this application also proposes a business processing method based on AI, RPA, and AI Agent.

[0148] Figure 6 This is a flowchart of a business processing method based on AI, RPA, and AI Agent provided in another embodiment of this application.

[0149] It should be noted that the business processing method based on AI, RPA and AI Agent can be executed alone, or it can be executed together with any embodiment or possible implementation in the embodiment of this application, or it can be executed together with any technical solution in related technologies. The embodiments of this application do not limit this.

[0150] like Figure 6 As shown, the business processing method based on AI, RPA, and AI Agent may include the following steps S601 to S608:

[0151] Step S601: Call the large language model to perform intent recognition on the scenario generation requirements associated with the target business scenario, obtain the target intent, and generate an information business process that matches the target intent.

[0152] The information-based business process includes multiple levels of process nodes.

[0153] The explanation of step S601 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0154] Step S602: Receive a business process optimization instruction; wherein, the business process optimization instruction is used to indicate the process optimization parameters of at least one process node in the information business process.

[0155] The process optimization parameters include, but are not limited to, "automation" parameters and "AI technology" parameters.

[0156] It should be noted that if the node content (or process content) of at least one process node in the automated business process generated by the large language model does not meet the business expectations or business requirements, the user can issue a business process optimization instruction (or intelligent optimization process instruction).

[0157] For example, if the node content (or process content) of a certain process node does not contain the fields of "automation" or "AI processing", the user can issue a business process optimization instruction, which is used to instruct that the process node be regenerated using AI technology and / or automation technology.

[0158] It should be understood that if the node content (or process content) of a certain process node does not meet business expectations or business needs, the business process optimization instruction can also be used to instruct: to regenerate the entire information business process. This application embodiment does not limit this.

[0159] Step S603: Obtain the second prompt template; wherein, the second prompt template is used to prompt the large language model to perform business process optimization tasks.

[0160] In this application embodiment, the second prompt template is a prompt template pre-configured for the target business scenario. In this application, the second prompt template can be obtained by querying stored data or configuration information.

[0161] Step S604: Update the second prompt template using the information business process and the process optimization parameters of at least one process node to obtain the second prompt information.

[0162] In this embodiment of the application, the second prompt template can be filled with information-based business processes and process optimization parameters of at least one process node to obtain the second prompt information.

[0163] Step S605: Call the large language model to process the second prompt information to obtain the optimized information-based business process.

[0164] In this embodiment of the application, a large language model can be invoked to process the second prompt information, so as to optimize at least one process node in the information business process based on the process optimization parameters of at least one process node through the large language model, and obtain the optimized information business process.

[0165] Step S606: Elementize the process nodes at multiple levels in the optimized information-based business process to obtain multiple process elements.

[0166] Step S607: Based on the categories to which multiple process elements belong, the optimized information-based business process is structured to obtain a structured business process.

[0167] Step S608: Construct at least some of the process elements in the structured business process to create process entities of at least some of the process elements, and generate the execution order of each process entity; wherein, each process entity is used to process the business under the target business scenario.

[0168] The explanation of steps S606 to S608 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0169] The business processing method based on AI, RPA, and AI Agent in this application embodiment utilizes a large language model to intelligently optimize the process content of the information business process, thereby improving the quality of the final generated information business process and meeting actual business needs.

[0170] In any embodiment of this application, a technology for intelligent optimization and construction of business processes is proposed, mainly including the following parts: generating information-based business processes, optimizing information-based business processes, elementizing process content, and automating process construction. Its implementation principle is mainly as follows: Figure 7As shown, the platform utilizes a large language model to understand business scenarios and generate information-based business processes, transforming users' business processes into information-based processes. Simultaneously, AI technology is used to intelligently analyze the generated information-based business processes, moving beyond simple information-based processes to intelligently process the steps using AI and automation technologies, optimizing cumbersome processes. The optimized information-based business processes are then processed into structured data to obtain structured business processes. These structured business processes are matched with elements and links of the business process construction platform, and a business process system is automatically created and generated via API, completing the intelligent optimization and implementation process from business process to business system.

[0171] The first part involves generating information-based business processes.

[0172] The system obtains the scenario description (referred to as the scenario generation requirement in this application) of the target business scenario input by the user, calls the intent understander of the large language model to perform business-oriented understanding of the scenario generation requirement input by the user, and then calls the content generator of the large language model to generate the information business process steps.

[0173] Based on the user's instruction to generate an information-based business process and the characteristics of the information-based business process, the process is generated according to the hierarchy of "stages", "links" and "steps", matching the information-based process prompt, and using the scenario generation requirements as execution parameters to generate high-level instructions for the large language model. The request is sent to the large language model to execute the command for generating the information-based process, and the information-based business process generated and returned by the large language model is obtained.

[0174] The second part focuses on intelligent optimization of information-based business processes.

[0175] For the content of the already generated information-based business processes, it is necessary to be able to identify the processes that can be replaced and optimized using automation and AI technologies during the execution of the business processes.

[0176] For example, based on the user's instruction to intelligently optimize the business process and the process content of the currently input information business process (or the step content of each step), the "automation" parameter and "AI technology" parameter of the process optimization can be passed in, the prompt for optimizing the process execution content can be matched, and a high-level instruction for execution by the large language model can be generated. After generating the prompt, the command for optimizing the business process can be requested from the large language model.

[0177] Based on the generated results returned by the large language model, the information structure for business process construction is then streamlined.

[0178] Part Three: Elementizing the Process Content.

[0179] For information-based business processes that generate and optimize large language models, it is not possible to directly build a business process system. In this case, it is necessary to first sort out the elements of the information-based business process and generate a structured business process based on the process content.

[0180] First, the category selector of the large language model is invoked to classify the process content of the information business process, identify the "stage", "link", "step" and other content of the process, and process them into basic process elements such as "stage", "link" and "step".

[0181] Identify the "automation" and "AI processing" content in the information process elements, and mark the process elements as the corresponding "automation" and "AI processing" content.

[0182] Simultaneously, based on the identified content, an execution sequence is generated for the "stage", "link", and "step" content in the order of generation. The sequence number of the "stage" in the execution sequence (referred to as the execution sequence number in this application) is a 1-digit number, the sequence number of the "link" in the execution sequence is "xx" (2 digits), and the sequence number of the "step" in the execution sequence is "xxx" (3 digits).

[0183] Each process element and its corresponding execution sequence number in the generated information-based business process are stored in a structured data format to obtain a structured business process.

[0184] Part Four: Automated Construction of Structured Business Processes.

[0185] Using a business process building platform (or business process system building platform), based on the process elements selected by the user to build the business system, it supports the generation and building of individual steps or links, as well as the generation and building of structured business processes for the entire process.

[0186] The processed information process elements are matched with the API of the business process building platform. Based on the category of the process element, the API of the different business process building platform is called to create the process entity of the information process element. The tag information of the process element is used as the attribute information of the created process entity. For process entities with the attribute information of "automation technology", they can be completed through automation technology such as RPA. For process entities with the attribute information of "AI processing" or "AI technology", they can be completed through configuring AI capabilities.

[0187] Then, based on the execution sequence number of each process element, the process element relationship API can be called to automatically generate the execution order of the process entities, thus completing the construction of the structured business process.

[0188] In summary, the technical solution provided in this application has at least the following advantages:

[0189] 1. By using intelligent business process optimization and construction technology, users do not need to spend a lot of cost and time to familiarize themselves with and sort out the business process content, nor do they need to spend time to carry out the business process system construction process. This allows users to focus their time and energy on more valuable business creation work.

[0190] 2. By utilizing the large language model platform, the content of information-based business processes can be intelligently optimized. For process entities of process elements, intelligent identification can use "automation" and "AI processing" technologies to optimize execution. It is no longer a simple matter of moving offline business processes online, but rather using large language model technology to achieve intelligent processing of business processes.

[0191] 3. Integrate the large language model generation with the business process system construction, analyze and identify the generated process content, transform it into structured process elements for business process construction, and connect to the API of the business process construction platform to realize the automated construction of the business process system. This can greatly save the time and cost of traditional business process system construction, and the automated identification and construction method also improves the accuracy and efficiency of business process system construction.

[0192] To implement the above embodiments, this application also provides a business processing device based on AI, RPA, and AI Agent.

[0193] Figure 8 This is a structural diagram of a business processing apparatus based on AI, RPA, and AI Agent provided in one embodiment of this application.

[0194] like Figure 8 As shown, the business processing device 800 based on AI, RPA and AI Agent includes: a first invocation module 810, a first processing module 820, a second processing module 830 and a setup module 840.

[0195] The first calling module 810 is used to call the large language model to perform intent recognition on the scene generation requirements associated with the target business scenario, obtain the target intent, and generate an information business process that matches the target intent; the information business process includes multiple levels of process nodes.

[0196] The first processing module 820 is used to perform element-based processing on process nodes at multiple levels to obtain multiple process elements;

[0197] The second processing module 830 is used to perform structured processing on the information business process according to the categories to which multiple process elements belong, so as to obtain a structured business process.

[0198] The module 840 is used to build at least some of the process elements in a structured business process, to create process entities of at least some of the process elements, and to generate the execution order of each process entity; wherein each process entity is used to handle business under the target business scenario.

[0199] In any embodiment of this application, the second processing module 830 is configured to: generate execution sequence numbers corresponding to multiple process elements according to the categories to which multiple process elements belong and according to the arrangement positions of multiple process elements in the information business process; and generate a structured business process according to the multiple process elements and their corresponding execution sequence numbers.

[0200] In any embodiment of this application, the second processing module 830 is configured to: add tag information to any process element based on the technology type to which the specified technology field belongs when any process element contains a specified technical field; and generate a structured business process based on multiple process elements, corresponding execution sequence numbers and tag information.

[0201] In any embodiment of this application, the construction module 840 is configured to: for any process element among at least some process elements, determine a target API from multiple application programming interfaces (APIs) of the business process construction platform that matches the category to which any process element belongs; call the target API to create a process entity for any process element; generate attribute information of the process entity based on the tag information of any process element; and generate the execution order of each process entity based on the execution sequence number of each process element.

[0202] In any embodiment of this application, the business processing apparatus 800 based on AI, RPA, and AI Agent further includes:

[0203] The execution module responds to the business processing time when the target business scenario arrives, and executes each process entity sequentially according to the execution order of each entity element;

[0204] The query module is used to query the attribute information of the currently executing process entity;

[0205] The second calling module is used to call the RPA robot to execute the currently executing process entity if the attribute information is automation technology.

[0206] In any embodiment of this application, the business processing apparatus 800 based on AI, RPA, and AI Agent further includes:

[0207] The third calling module is used to call the pre-configured AI algorithm and execute the currently executing process entity if the attribute information is AI technology.

[0208] In any embodiment of this application, the first invocation module 810 is used to: obtain a first prompt template adapted to the target business scenario; wherein the first prompt template is used to instruct the large language model to execute the information generation task of the process; take the scenario generation requirements as execution parameters, and update the first prompt template using the execution parameters to obtain the first prompt information; call the large language model to process the first prompt information, so as to identify the target intent to which the scenario generation requirements belong through the large language model, and generate an information business process adapted to the target intent.

[0209] In any embodiment of this application, the first prompt template also includes a reference example, wherein the reference example is used to indicate a reference business process in a reference business scenario, and the reference business process includes multiple levels of reference process nodes.

[0210] In any embodiment of this application, the business processing apparatus 800 based on AI, RPA, and AI Agent further includes:

[0211] The receiving module is used to receive business process optimization instructions; wherein, the business process optimization instructions are used to indicate the process optimization parameters of at least one process node in the information business process;

[0212] The acquisition module is used to acquire the second prompt template; the second prompt template is used to prompt the large language model to perform business process optimization tasks.

[0213] The update module is used to update the second prompt template using information-based business processes and process optimization parameters of at least one process node, so as to obtain the second prompt information.

[0214] The optimization module is used to call the large language model to process the second prompt information and obtain the optimized information business process.

[0215] It should be noted that the business processing apparatus based on AI, RPA and AI Agent provided in this application embodiment can implement all the method steps implemented in any of the above method embodiments and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiments and the beneficial effects will not be described in detail.

[0216] Figure 9 A structural block diagram of an electronic device according to an embodiment of this application is shown. Figure 9As shown, the electronic device includes a memory 910 and a processor 920. The memory 910 stores a computer program that can run on the processor 920. When the processor 920 executes the computer program, it implements the business processing methods based on AI, RPA, and AI Agent in the above embodiments. The number of memories 910 and processors 920 can be one or more.

[0217] The electronic device also includes:

[0218] The communication interface 930 is used to communicate with external devices and exchange and transmit data.

[0219] If the memory 910, processor 920, and communication interface 930 are implemented independently, they can be interconnected via a bus to communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 9 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0220] Optionally, in a specific implementation, if the memory 910, processor 920, and communication interface 930 are integrated on a single chip, then the memory 910, processor 920, and communication interface 930 can communicate with each other through an internal interface.

[0221] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the business processing methods based on AI, RPA, and AI Agent provided in any embodiment of this application.

[0222] This application also provides a chip, which includes a processor for calling and executing instructions stored in a memory, causing a communication device equipped with the chip to execute the business processing methods based on AI, RPA, and AI Agent provided in any embodiment of this application.

[0223] This application also provides a chip, including: an input interface, an output interface, a processor, and a memory. The input interface, output interface, processor, and memory are connected through an internal connection path. The processor is used to execute code in the memory. When the code is executed, the processor is used to execute the business processing method based on AI, RPA, and AIAgent provided in any embodiment of the application.

[0224] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting Advanced Reduced Instruction Set Computing (RISC) machines (ARM) architecture.

[0225] Further, optionally, the aforementioned memory may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory may be volatile or non-volatile, or may include both. 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. Volatile memory may include random access memory (RAM), which serves as an external cache. Many forms of RAM are available by way of example, but not limitation. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0226] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as 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, all or part of the flow or function according to this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0227] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0228] 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 indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0229] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process. Furthermore, the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functionality involved.

[0230] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can 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 processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0231] It should be understood that various parts of this application 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 memory and executed by a suitable instruction execution system. All or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware, the program being stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiments.

[0232] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. This storage medium can be a read-only memory, a disk, or an optical disk, etc.

[0233] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A business processing method based on artificial intelligence (AI), robotic process automation (RPA), and a digital workforce platform intelligent assistant (AIAgent), characterized in that: include: The large language model is invoked to perform intent recognition on the scene generation requirements associated with the target business scenario, obtain the target intent, and generate an information business process adapted to the target intent; wherein, the information business process includes multiple levels of process nodes. The process nodes at multiple levels are processed into elements to obtain multiple process elements; Based on the categories to which the multiple process elements belong, the information-based business process is structured to obtain a structured business process. Construct at least some process elements in the structured business process to create process entities of the at least some process elements, and generate the execution order of each process entity; wherein each process entity is used to process business under the target business scenario, including: For any one of the at least some process elements, determine the target API that matches the category to which the process element belongs from multiple application programming interface (API) APIs of the business process building platform. Call the target API to create a process entity for any of the process elements; Generate the attribute information of the process entity based on the tag information of any process element; The execution order of each process entity is generated based on the execution sequence number of each process element. In response to the arrival of the business processing time in the target business scenario, each process entity is executed sequentially according to its execution order. Query the attribute information of the currently executing process entity; If the attribute information is related to automation technology, then the RPA robot is invoked to execute the currently executing process entity; If the attribute information is AI technology, then the pre-configured AI algorithm is invoked to execute the currently executing process entity.

2. The method according to claim 1, characterized in that, The step of structuring the information-based business process according to the categories to which the multiple process elements belong, to obtain a structured business process, includes: Based on the category to which the multiple process elements belong and their arrangement position in the information business process, an execution sequence number corresponding to the multiple process elements is generated. The structured business process is generated based on the multiple process elements and their corresponding execution sequence numbers.

3. The method according to claim 2, characterized in that, The step of generating the structured business process based on the multiple process elements and their corresponding execution sequence numbers includes: If any process element contains a specified technical field, add tag information to the process element based on the technical type to which the specified technical field belongs; The structured business process is generated based on the multiple process elements, their corresponding execution sequence numbers, and tag information.

4. The method according to claim 1, characterized in that, The process of calling a large language model to perform intent recognition on the scenario generation requirements associated with the target business scenario, obtaining the target intent, and generating an information-based business process adapted to the target intent includes: Obtain a first prompt template adapted to the target business scenario; wherein, the first prompt template is used to instruct the large language model to perform an information generation task in the execution process; The scene generation requirements are used as execution parameters, and the first prompt template is updated using the execution parameters to obtain the first prompt information; The large language model is invoked to process the first prompt information in order to identify the target intent to which the scenario generation requirement belongs through the large language model, and to generate the information business process that is adapted to the target intent.

5. The method according to claim 4, characterized in that, The first prompt template also includes a reference example, wherein the reference example is used to indicate a reference business process in a reference business scenario, and the reference business process includes multiple levels of reference process nodes.

6. The method according to claim 4, characterized in that, After generating the information-based business process adapted to the target intent, the method further includes: Receive a business process optimization instruction; wherein the business process optimization instruction is used to indicate the process optimization parameters of at least one process node in the information business process; Obtain a second prompt template; wherein the second prompt template is used to prompt the large language model to perform a business process optimization task; The second prompt template is updated using the information-based business process and the process optimization parameters of at least one process node to obtain the second prompt information; The large language model is invoked to process the second prompt information, resulting in the optimized information-based business process.

7. A business processing device based on AI, RPA, and AI Agent, characterized in that, include: The first invocation module is used to invoke a large language model to perform intent recognition on the scene generation requirements associated with the target business scenario, obtain the target intent, and generate an information business process adapted to the target intent; wherein, the information business process includes multiple levels of process nodes. The first processing module is used to perform element-based processing on the process nodes at multiple levels to obtain multiple process elements; The second processing module is used to perform structured processing on the information business process according to the category to which the multiple process elements belong, so as to obtain a structured business process. A construction module is used to construct at least some of the process elements in the structured business process, to create process entities of the at least some process elements, and to generate the execution order of each process entity; wherein, each process entity is used to process the business under the target business scenario; The execution module responds to the business processing time when the target business scenario arrives, and executes each process entity sequentially according to the execution order of each process entity; The building module is also used for: For any one of the at least some process elements, determine the target API that matches the category to which the process element belongs from multiple application programming interface (API) APIs of the business process building platform. Call the target API to create a process entity for any of the process elements; Generate the attribute information of the process entity based on the tag information of any process element; The execution order of each process entity is generated based on the execution sequence number of each process element. The query module is used to query the attribute information of the currently executing process entity; The second calling module is used to call the RPA robot to execute the currently executing process entity if the attribute information is automation technology; The third calling module is used to call the pre-configured AI algorithm and execute the currently executing process entity if the attribute information is AI technology.

8. The apparatus according to claim 7, characterized in that, The second processing module is used for: Based on the category to which the multiple process elements belong and their arrangement position in the information business process, an execution sequence number corresponding to the multiple process elements is generated. The structured business process is generated based on the multiple process elements and their corresponding execution sequence numbers.

9. The apparatus according to claim 8, characterized in that, The second processing module is used for: If any process element contains a specified technical field, add tag information to the process element based on the technical type to which the specified technical field belongs; The structured business process is generated based on the multiple process elements, their corresponding execution sequence numbers, and tag information.

10. An electronic device, characterized in that, include: A processor and a memory, wherein instructions are stored in the memory and loaded and executed by the processor to implement the method as described in any one of claims 1 to 6.

11. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method as described in any one of claims 1-6.

Images