Business process processing methods, devices, electronic equipment and storage media

Abstract

This disclosure relates to a business process processing method, apparatus, electronic device, and storage medium, comprising: determining a business process to be processed; the business process to be processed includes multiple process nodes, each process node corresponding to a subtask; generating at least one business intelligence agent required to execute the business process, and constructing the process intelligence agent; during the execution of the business process, determining the target business intelligence agent for each call through the process intelligence agent, obtaining the historical execution information and corresponding subtask task information required by the target business intelligence agent; filtering the historical execution information from the execution information of previous business intelligence agents; inputting the historical execution information and the corresponding subtask task information into the target business intelligence agent for processing to obtain the task execution result. This method enables the business intelligence agent to trace back the context and coordinate interdependent process nodes when executing tasks, improving the accuracy of task processing.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a business process processing method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] With the development of Large Language Model (LLM) technology, most tasks can be completed using agents. However, many tasks are quite complex, involving multiple business processes with interconnected nodes. For example, a business release task involves several key process nodes such as "pre-filling of release form," "submission of release form," and "approval of release form."

[0003] In related technologies, each subtask of a business process node is typically processed by a separate agent. That is, at each business process node, the user inputs the subtask, and the agent processes it and outputs the result. While the individual business process nodes are independent, this processing method loses contextual information between related business process nodes, thus affecting the accurate execution of tasks. Summary of the Invention

[0004] This disclosure provides a business process processing method, apparatus, electronic device, storage medium, and program product to at least solve the problem in related technologies where context information is lost, thereby affecting the accurate execution of tasks. The technical solution of this disclosure is as follows:

[0005] According to a first aspect of the present disclosure, a business process processing method is provided, including:

[0006] Determine the business process to be processed; the business process to be processed includes multiple process nodes, and each process node corresponds to a subtask.

[0007] Generate at least one business agent required to execute the business process, and construct a process agent; the process agent is used to schedule the various business agents under the business process.

[0008] During the execution of the business process, the process agent determines the target business agent for each call, and obtains the historical execution information and corresponding subtask information required by the target business agent; the historical execution information is filtered from the execution information of the business agents preceding the target business agent.

[0009] The historical execution information and the corresponding subtask task information are input into the target business agent for processing to obtain the task execution result.

[0010] In one exemplary embodiment, generating at least one business agent required to execute the business process includes:

[0011] Determine the business capabilities required to execute the business process;

[0012] Based on the model context protocol, the business capabilities are standardized and encapsulated to generate a set of tools that can be called by a large language model.

[0013] Based on the aforementioned toolset and large language model, at least one business agent required to execute the aforementioned business process is generated.

[0014] In one exemplary embodiment, the construction process agent includes:

[0015] Build a process management module, a process prompt word module, a process recording module, and a process decision module;

[0016] The business information corresponding to the business process is entered into the process management module; and the prompt information corresponding to the business process is constructed and entered into the process prompt word module.

[0017] The process intelligent agent is obtained by integrating the process management module for inputting the business information, the process prompt word module for inputting the prompt information, the process recording module, and the process decision module.

[0018] In an exemplary embodiment, the process intelligence agent is used for scheduling business intelligence agents under multiple business processes; wherein, for each processing of any business process, a process instance is created to record the process execution progress;

[0019] The step of determining the target business agent for each call through the process agent includes:

[0020] Based on the business identifier of the business process and the version identifier of this processing, query the process instance created for this processing of the business process, and determine the current process node and the corresponding process status information.

[0021] Based on the current process node and process status information, the target business intelligence agent to be invoked is determined.

[0022] In one exemplary embodiment, the method further includes:

[0023] During the execution of the business process, if the target business agent called is the first business agent of the business process, then the task information of the subtask corresponding to the target business agent is obtained and input into the target business agent;

[0024] If the target business agent being invoked is not the first business agent in the business process, then the historical execution information and corresponding subtask task information required by the target business agent are obtained and input into the target business agent.

[0025] In one exemplary embodiment, the method further includes:

[0026] Obtain the prompt information required by the target business intelligent agent;

[0027] If the target business agent invoked is the first business agent in the business process, then the prompt information and the task information are input into the target business agent for processing to obtain the task execution result;

[0028] If the target business agent being invoked is not the first business agent in the business process, then the prompt information, the historical execution information, and the task information are input into the target business agent for processing to obtain the task execution result.

[0029] In one exemplary embodiment, the process intelligence agent includes a process management module, a process prompt word module, a process decision module, and a process recording module; the method further includes:

[0030] The process decision module determines the target business intelligence agent for each call.

[0031] The process prompting module determines the prompting information required by the target business intelligent agent;

[0032] The process management module determines the historical execution information and corresponding sub-task information required by the target business intelligent agent.

[0033] The process recording module records the task execution results of the target business intelligence agent.

[0034] The process decision module extracts the execution process of the target business agent for each call based on the business scenario of the business process, and obtains the execution information.

[0035] According to a second aspect of the present disclosure, a business process processing apparatus is provided, comprising:

[0036] The business determination unit is configured to execute a determined business process to be processed; the business process to be processed includes multiple process nodes, and each process node corresponds to a subtask.

[0037] An agent generation unit is configured to generate at least one business agent required to execute the business process, and to construct a process agent; the process agent is used to schedule the various business agents under the business process.

[0038] The agent scheduling unit is configured to, during the execution of the business process, determine the target business agent for each call through the process agent, and obtain the historical execution information and corresponding subtask task information required by the target business agent; the historical execution information is filtered from the execution information of business agents preceding the target business agent.

[0039] The task execution unit is configured to input the historical execution information and the task information of the corresponding subtasks into the target business intelligence agent for processing, and obtain the task execution result.

[0040] In one exemplary embodiment, the agent generation unit is further configured to: determine the business capabilities required to execute the business process; standardize and encapsulate the business capabilities based on a model context protocol to generate a set of tools that can be called by a large language model; and generate at least one business agent required to execute the business process based on the set of tools and the large language model.

[0041] In an exemplary embodiment, the intelligent agent generation unit is further configured to execute a process management module, a process prompt word module, a process recording module, and a process decision module; input the business information corresponding to the business process into the process management module; and construct prompt information corresponding to the business process and input it into the process prompt word module; integrate the process management module that inputs the business information, the process prompt word module that inputs the prompt information, the process recording module, and the process decision module to obtain the process intelligent agent.

[0042] In an exemplary embodiment, the process intelligence agent is used for scheduling business intelligence agents under multiple business processes; wherein, for each processing of any business process, a process instance is created to record the process execution progress; the intelligence agent scheduling unit is further configured to query the process instance created for the current processing of the business process based on the business identifier of the business process and the version identifier of the current processing, determine the current process node and the corresponding process status information; and determine the target business intelligence agent to be invoked based on the current process node and process status information.

[0043] In an exemplary embodiment, the task execution unit is further configured to, during the execution of the business process, if the target business intelligence agent invoked is the first business intelligence agent in the business process, obtain the task information of the subtask corresponding to the target business intelligence agent and input it into the target business intelligence agent; if the target business intelligence agent invoked is not the first business intelligence agent in the business process, obtain the historical execution information required by the target business intelligence agent and the task information of the corresponding subtask and input it into the target business intelligence agent.

[0044] In an exemplary embodiment, the task execution unit is further configured to execute prompt information required to obtain the target business intelligence agent; if the target business intelligence agent being invoked is the first business intelligence agent in the business process, the prompt information and the task information are input into the target business intelligence agent for processing to obtain a task execution result; if the target business intelligence agent being invoked is not the first business intelligence agent in the business process, the prompt information, the historical execution information, and the task information are input into the target business intelligence agent for processing to obtain a task execution result.

[0045] In an exemplary embodiment, the process intelligence agent includes a process management module, a process prompt word module, a process decision module, and a process recording module. The process decision module determines the target business intelligence agent for each call; the process prompt word module determines the prompt information required by the target business intelligence agent; the process management module determines the historical execution information and corresponding sub-task task information required by the target business intelligence agent; the process recording module records the task execution results of the target business intelligence agent; and the process decision module extracts the execution process of the target business intelligence agent for each call based on the business scenario of the business process to obtain execution information.

[0046] According to a third aspect of the present disclosure, an electronic device is provided, comprising:

[0047] processor;

[0048] Memory used to store the processor's executable instructions;

[0049] The processor is configured to execute the instructions to implement the method as described in any of the preceding methods.

[0050] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided that, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the method described in any of the preceding claims.

[0051] According to a fifth aspect of the present disclosure, a computer program product is provided, the computer program product including instructions that, when executed by a processor of an electronic device, enable the electronic device to perform the method as described in any of the preceding claims.

[0052] The technical solutions provided by the embodiments of this disclosure bring at least the following beneficial effects: by constructing a general process intelligence agent, scheduling the independent business intelligence agents under the business process, deciding the business intelligence agent to be called each time, and when executing tasks through the business intelligence agent, historical execution information can be obtained as context information and input into the business intelligence agent together with the task information of the subtask corresponding to the business intelligence agent. In this way, the association between the independent business intelligence agents is established through the context information, so that when the business intelligence agent executes the task, it can trace back the context, coordinate process nodes with interdependent relationships, and improve the accuracy of task processing.

[0053] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0054] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0055] Figure 1 This is a flowchart illustrating a business process processing method according to an exemplary embodiment.

[0056] Figure 2 This is a schematic diagram illustrating the task execution principle of a business intelligence agent according to an exemplary embodiment.

[0057] Figure 3 This is a schematic diagram illustrating a business intelligence agent generation framework according to an exemplary embodiment.

[0058] Figure 4 This is a flowchart illustrating a business process processing method according to another exemplary embodiment.

[0059] Figure 5 This is a schematic diagram of a system architecture for implementing a business process processing method, according to an exemplary embodiment.

[0060] Figure 6 This is a schematic diagram illustrating a process of scheduling a business agent through a process agent, according to an exemplary embodiment.

[0061] Figure 7 This is a structural block diagram of a business process processing apparatus according to an exemplary embodiment.

[0062] Figure 8 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0063] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0064] It should be noted that the embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims. It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0065] In one exemplary embodiment, such as Figure 1 As shown, a business process processing method is provided. This embodiment illustrates the method applied to a terminal, but it is understood that the method can also be applied to a server, or to a system including both a terminal and a server, and is implemented through the interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. The server can be implemented using a standalone server or a server cluster consisting of multiple servers. In this embodiment, the method includes the following steps:

[0066] In step S110, the business process to be processed is determined; the business process to be processed includes multiple process nodes, and each process node corresponds to a subtask.

[0067] Among them, a business process refers to a standardized operational chain consisting of a series of logically related and orderly executed nodes (or task steps) to achieve specific business objectives (such as order completion, product release, and content compliance verification).

[0068] A business process comprises multiple process nodes, each corresponding to a sub-task. For example, order processing, development and release processes, content review processes, and customer service processes all fall under the category of business processes. Taking the development and release process as an example, it can be divided into four process nodes, corresponding to four sub-tasks: "Submit Release Order," "Release Order Goes Live," "Inspection," and "Popularization."

[0069] In step S120, at least one business agent required to execute the business process is generated, and a process agent is constructed; the process agent is used to schedule the various business agents under the business process.

[0070] Among them, an intelligent agent is an intelligent execution unit that can autonomously complete a single specific task.

[0071] A business agent is an intelligent entity that executes specific tasks; it is a solver for a single task. For example, ... Figure 2 The diagram shows the task execution principle of the business intelligence agent. The business intelligence agent is an intelligent agent built based on the Large Language Model (LLM). The task is input into the business intelligence agent, the Large Language Model in the business intelligence agent plans the task, calls the corresponding tools to process it, completes the task, and outputs the task execution result.

[0072] A process agent can be viewed as an intelligent agent system capable of managing, coordinating, and executing complete business processes. It not only focuses on solving single tasks but also on the full lifecycle management of the entire business process, making it a solution provider for the entire business process.

[0073] A process agent is not limited to managing agents within a single business process; it can manage agents across multiple business processes. For example, a process agent can manage four business processes: order processing, R&D release, content review, and customer service, with at least one business agent generated for each process.

[0074] Understandably, generally speaking, a business intelligence agent needs to be built for each process node. For example, if a business process has four process nodes, then four business intelligence agents are built. However, in some special cases, such as when the tasks of a process node do not require an intelligence agent to handle, or when the tasks of a process node are relatively simple, a business intelligence agent can be reused, that is, multiple process nodes correspond to one business intelligence agent. For example, for the business process "R&D Release Process", which includes four process nodes: "Submit Release Order", "Release Order Go-live", "Inspection", and "Large-up", since the tasks of "Release Order Go-live" and "Large-up" are relatively simple, only two business intelligence agents need to be built. Specifically, one business intelligence agent is built for the two process nodes of "Submit Release Order" and "Release Order Go-live", and another business intelligence agent is built for the two process nodes of "Inspection" and "Large-up".

[0075] The process intelligence agent comprises a process management module, a process prompt word module, a process recording module, and a process decision module. Building the process intelligence agent involves constructing each module, inputting the business information corresponding to the business process to be processed into the process management module, and constructing the prompt information corresponding to the business process to be processed into the process prompt word module. Specifically, the process management module manages and maintains the execution progress of each business process, the process prompt word module maintains the prompt information corresponding to each business process, the process recording module records the execution process of each business process, and the process decision module makes decisions about which business intelligence agent to invoke and extracts historical execution information (contextual information).

[0076] In step S130, during the execution of the business process, the target business intelligence agent for each call is determined through the process intelligence agent, and the historical execution information and corresponding subtask task information required by the target business intelligence agent are obtained; the historical execution information is filtered from the execution information of the business intelligence agents before the target business intelligence agent.

[0077] Specifically, during the execution of the business process to be processed, each execution process is determined by the process intelligence agent to be executed by which business intelligence agent, and the historical execution information and corresponding sub-task task information required by that business intelligence agent are obtained as input to that business intelligence agent.

[0078] In step S140, the historical execution information and the task information of the corresponding subtasks are input into the target business intelligence agent for processing to obtain the task execution result.

[0079] Specifically, after obtaining the historical execution information and corresponding subtask task information required by the target business agent, these are used as input information for the target business agent, and then input into the target business agent, such as... Figure 2 As shown, the target business intelligence agent calls the corresponding tools to process and execute tasks, and outputs the task execution results.

[0080] In the aforementioned business process processing method, the business process to be processed is determined; the business process to be processed includes multiple process nodes, each process node corresponding to a subtask; at least one business intelligence agent required to execute the business process is generated, and the process intelligence agent is constructed so that during the execution of the business process, the target business intelligence agent for each call is determined through the process intelligence agent, and the historical execution information and corresponding subtask task information required by the target business intelligence agent are obtained; the historical execution information and the corresponding subtask task information are input into the target business intelligence agent for processing to obtain the task execution result. This method constructs a general process intelligence agent to schedule the independent business intelligence agents under the business process, decides the business intelligence agent to be called each time, and when executing tasks through the business intelligence agent, it can obtain historical execution information as context information, which is input into the business intelligence agent along with the task information of the corresponding subtask. Thus, the relationship between the independent business intelligence agents is established through the context information, so that when the business intelligence agent executes the task, it can trace back the context, coordinate process nodes with interdependent relationships, and improve the accuracy of task processing.

[0081] In an exemplary embodiment, in step S120, generating at least one business agent required to execute the business process can be specifically achieved through the following steps: determining the business capabilities required to execute the business process; standardizing and encapsulating the business capabilities based on the model context protocol to generate a set of tools that can be called by the large language model; and generating at least one business agent required to execute the business process based on the set of tools and the large language model.

[0082] The Model Context Protocol (MCP) is used to integrate large language models with external data sources and tools, and to establish a secure, bidirectional connection between the large model and the data source.

[0083] In practical implementation, the business capabilities required to execute the business process are first determined. Business capabilities can be understood as executable code or interfaces that implement specific business functions. Based on the model context protocol, the business capabilities are standardized and encapsulated to generate a set of tools (LLM-tools) that can be recognized and invoked by the Large Language Model (LLM). Based on these toolsets, combined with the Large Language Model which has natural language understanding, task planning, and tool scheduling capabilities, a business intelligent agent can be obtained. Different business intelligent agents can be obtained through different sets of tools.

[0084] like Figure 3 The diagram shown illustrates a framework for generating a business intelligence agent in one embodiment. The business intelligence agent is generated using a common method and a model context protocol (MCP), combined with a large language model. The modules in the diagram are explained below:

[0085] The PlanManager (Task Planning and Execution Management) module is used for: generating task execution plans based on user input; monitoring the execution status of plans and outputting plan optimization suggestions; and dynamically adjusting plans.

[0086] The Analyzer module is used to convert the standardized CommonMethod automatic extraction tool function description, parameter specifications, and usage limitations into a standard FunctionProtocol; and to convert the standard FunctionProtocol into the FunctionCall protocols of various vendors.

[0087] The ToolsCollector module is used to collect all tools in the system, including MCP, A2A, and results analyzed by Analyzer; it supports dynamic tool registration and version management; it categorizes and tags tools; it records feedback mechanisms on tool usage effects and generates best practices for tool usage (tool invocation strategy optimization).

[0088] The Event system (event management) module is used to broadcast the black-box process of Plan execution through events; it also includes subscriber management and event replay.

[0089] In this embodiment, by determining the business capabilities required to execute the business process, the business capabilities are standardized and encapsulated based on the Model Context Protocol (MCP) to generate a set of tools that can be called by the large language model. Based on the tool set and the large language model, at least one business agent required to execute the business process is generated. There is no need to develop business logic and model interface from scratch. By reusing the defined business capabilities and the MCP standardized encapsulation mechanism, redundant development is avoided, and the rapid generation of business agents is achieved.

[0090] In an exemplary embodiment, step S120 involves constructing a process intelligence agent, including: constructing a process management module, a process prompt word module, a process recording module, and a process decision module; inputting business information corresponding to the business process into the process management module; and constructing prompt information corresponding to the business process and inputting it into the process prompt word module; and integrating the process management module for inputting business information, the process prompt word module for inputting prompt information, the process recording module, and the process decision module to obtain the process intelligence agent.

[0091] Specifically, the process intelligence agent includes a process management module (ProcessManager), a process prompt word module (ProcessPrompt), a process recording module (ProcessRecord), and a process decision module (ProcessDecision). When building the process intelligence agent, these four modules are built first. The functions of each module are as follows:

[0092] The process management module is used to manage and maintain the execution progress of each business process. It stores the business information of each business process so that it can be used when scheduling business intelligence agents.

[0093] The process prompt module is used to maintain the prompt information corresponding to each business process, so that it can be used by the business intelligence agent when performing tasks. Different business processes correspond to different prompt information. For example, the prompt information for the "R&D Release Process" is "You are now a release expert...", and the prompt information for the "Content Review Process" is "You are now a content review expert...". The process prompt module is used to manage the prompts of different business processes.

[0094] The process recording module is used to record the execution process of each business process.

[0095] The process decision module is used to invoke business intelligence agents for decision-making and extract historical execution information (context information).

[0096] The first two modules store information that serves as the basis for scheduling business agents or for them to execute tasks. Therefore, this information needs to be stored in advance. Thus, after constructing the process management module and the process prompt module, the business information corresponding to the business process needs to be entered into the process management module; and the prompt information corresponding to the business process needs to be constructed and entered into the process prompt module. The latter two modules primarily record information after the business agent executes a task, or for agents invoked through logical decisions; they do not require prior information storage. Therefore, the process agent is obtained through the process management module for entering business information, the process prompt module for entering process prompt information, the process recording module, and the process decision module.

[0097] It is understandable that process intelligence agents can be used not only for scheduling business intelligence agents under a single business process, but also for scheduling business intelligence agents under multiple business processes at the same time. When a new business process is added, the business information of the new business process is entered into the process management module and the prompt information is entered into the process prompt word module, thereby enabling the process intelligence agent to schedule the intelligence agents under the new business process.

[0098] In this embodiment, a general process intelligence agent is constructed to schedule the independent business intelligence agents under the business process. The association between the independent business intelligence agents is established through context information, so that when the business intelligence agent executes a task, it can trace back the context and coordinate process nodes with interdependent relationships, thereby improving the accuracy of task processing.

[0099] As mentioned earlier, process intelligence agents can be used to schedule business intelligence agents across multiple business processes. Each processing operation in a business process creates a process instance to record the process execution progress. The aforementioned process management module primarily manages these process instances. For example, in a development and release process (submit release order → release order go live → inspection → mass production), each release operation creates a process instance. When the process node transitions from "submit release order" to "release order go live," the process instance updates the current process node. Subsequent "inspection" operations will then use the process instance to find the current process node and continue execution.

[0100] Based on this, in order to distinguish each processing step of each business process, a business identifier can be set for each business process and a version identifier can be set for each processing step, so as to uniquely identify a specific processing operation of a business process through the business identifier and the version identifier.

[0101] In an exemplary embodiment, step S130, determining the target business intelligence agent for each call through the process intelligence agent includes: querying the process instance created for the current processing of the business process based on the business identifier of the business process and the version identifier of the current processing, determining the current process node and the corresponding process status information; and determining the target business intelligence agent to be called based on the current process node and process status information.

[0102] Each business process corresponds to a business identifier. For example, the order processing process, R&D release process, content review process, and customer service process each correspond to a business identifier. This business identifier can be a number or a name, as long as it can identify the uniqueness of the business process.

[0103] Each business process can involve multiple processing steps, thus corresponding to multiple version identifiers. For example, in a development release process, Xiao Wang executes the release process once, generating a release order; Xiao Li executes the release process once, also generating a release order. Both of these release processes belong to the "development release process," but they are two separate release operations. Therefore, each processing step is assigned a version identifier to distinguish between these two operations. Furthermore, each processing step creates a process instance to record the progress of the current process execution.

[0104] When scheduling business intelligence agents, since each process intelligence agent maintains multiple business processes, and each business process can correspond to multiple processing operations, it is necessary to locate a unique process instance based on the business identifier of the business process and the version identifier of the current processing. That is, first, all processing operations corresponding to the business process are retrieved based on the business identifier; then, the unique process instance is located based on the version identifier of the current processing, thereby determining the current process node and corresponding process status information. Further, based on the current process node and process status information, the target business intelligence agent to be invoked is determined.

[0105] It should be noted that a business process may not be a simple linear process where, after process node A ends, it necessarily enters process node B and calls the business intelligence agent of process node B. Instead, after process node A ends, there may be different states, and different states will lead to different next process nodes. Therefore, when determining the next business intelligence agent to be called, it is necessary to consider not only the current process node but also the process state information.

[0106] In this embodiment, the scheduling of business intelligence agents under multiple business processes can be managed simultaneously through process intelligence agents. Furthermore, by constructing process instances, when determining the business intelligence agent to be called each time under each business process, the process node can be determined by querying the process instance. Combining the current process node and process status information, the business intelligence agent to be called next can be determined, which can ensure the accuracy of the business intelligence agent to be called each time.

[0107] In an exemplary embodiment, the method further includes: during the execution of a business process, if the target business agent invoked is the first business agent in the business process, then the task information of the subtask corresponding to the target business agent is obtained and input into the target business agent; if the target business agent invoked is not the first business agent in the business process, then the historical execution information required by the target business agent and the task information of the corresponding subtask are obtained and input into the target business agent.

[0108] It is understandable that at least one business intelligence agent generated for a business process has a sequential execution order. Only business intelligence agents that are called later can utilize the execution information of earlier business intelligence agents as context information, thereby combining this context information for task processing. Therefore, during the execution of the business process to be processed, for the first business intelligence agent called, the task information of its corresponding subtask is obtained as input to execute the task and obtain the task execution result, without needing to obtain historical execution information. For business intelligence agents that are not called initially, in addition to obtaining the task information of their corresponding subtasks as input, the historical execution information of business intelligence agents called before this business intelligence agent can also be obtained as context information. This context information, along with the task information corresponding to this business intelligence agent, is input into the business intelligence agent for task processing to obtain the task execution result.

[0109] In this embodiment, depending on the position of the invoked business intelligence agent (first or not first), it is determined whether historical execution information needs to be obtained as input in order to achieve accurate task processing for business intelligence agents in different positions.

[0110] Furthermore, in an exemplary embodiment, the method further includes: obtaining the prompt information required by the target business intelligence agent; if the target business intelligence agent being called is the first business intelligence agent in the business process, then the prompt information and task information are input into the target business intelligence agent for processing to obtain the task execution result; if the target business intelligence agent being called is not the first business intelligence agent in the business process, then the prompt information, historical execution information, and task information are input into the target business intelligence agent for processing to obtain the task execution result.

[0111] Specifically, the input to the business agent in the business process to be processed also includes pre-built prompts for the business process to guide the business agent to execute tasks based on the prompts. Specifically, if the target business agent is the first business agent in the business process, the prompts and task information are input into the target business agent for processing to obtain the task execution result; if the target business agent is not the first business agent in the business process, the prompts, historical execution information, and task information are input into the target business agent for processing to obtain the task execution result.

[0112] In some embodiments, a single prompt message can be built for each business process, meaning that all business agents within the same business process share the same prompt message. Alternatively, in some embodiments, a separate prompt message can be built for each business agent within each business process, meaning that each business agent within the same business process uses different prompt messages.

[0113] In this embodiment, the input business intelligence agent also includes prompt information. The prompt information carries the business requirements in natural language, eliminating the need for manual coding instructions. This can lower the execution threshold of business tasks and ensure the accuracy and intelligence of task execution.

[0114] In an exemplary embodiment, the process intelligence agent includes a process management module, a process prompt word module, a process decision module, and a process recording module; the method further includes: determining the target business intelligence agent for each call through the process decision module; determining the prompt information required by the target business intelligence agent through the process prompt word module; determining the historical execution information and corresponding sub-task task information required by the target business intelligence agent through the process management module; recording the task execution results of the target business intelligence agent through the process recording module; and extracting the execution process of the target business intelligence agent for each call through the process decision module according to the business scenario of the business process to obtain execution information.

[0115] Specifically, the process agent determines the business agent to be invoked each time through the process decision module within the process agent. The prompts input to the business agent are obtained from the process prompt word module. The historical execution information and corresponding subtask information input to the business agent are obtained through the process management module.

[0116] After the target business intelligence agent receives the prompt and task information (and historical execution information for business intelligence agents not making their first call), and executes the task, the process recording module will record the task execution result. The process decision module will also extract the execution process of the target business intelligence agent based on the business scenario of the business process, obtaining execution information to serve as context information for subsequent business intelligence agents.

[0117] It is understandable that a business process can contain multiple business agents. If all the execution information of each business agent is recorded, it will result in too much data to record. Therefore, this embodiment uses a process decision module combined with the business scenario to extract key information and use the key information as execution information.

[0118] In this embodiment, the coordinated operation of the process management module, process prompt word module, process decision module, and process recording module enables the scheduling of multiple business agents under the business process, achieving full control over the business process. Based on the dependencies between different process nodes, the corresponding context information can be input into the business agent, making task execution more accurate.

[0119] In one exemplary embodiment, such as Figure 4 As shown, a flowchart of a business process processing method is also provided. In this embodiment, the method includes the following steps:

[0120] Step S410: Determine the business process M to be processed; the business process M to be processed includes multiple process nodes, and each process node corresponds to a subtask.

[0121] Step S420: Generate at least one business agent required to execute business process M.

[0122] Step S430: If a process intelligence body already exists, directly input the business information corresponding to the business process M into the process management module of the process intelligence body, and construct the prompt information corresponding to the business process M and input it into the process prompt word module of the process intelligence body.

[0123] Step S440: If no process agent exists, after constructing the process agent, the business information corresponding to the business process is entered into the process management module; and the prompt information corresponding to the business process is constructed and entered into the process prompt word module.

[0124] Step S450: The process involves scheduling the various business agents under business process M through the process agent. This process includes:

[0125] Step S460: Based on the business identifier of business process M and the version identifier of this processing, query the process instance created for this processing of business process M, and determine the current process node and the corresponding process status information.

[0126] Step S470: Based on the current process node and process status information, determine the business intelligence agent to be invoked.

[0127] Step S480: For the first business agent called under business process M, obtain the task information of the subtask corresponding to the first business agent and the prompt information of business process M, input the first business agent to execute the task, and obtain the task execution result.

[0128] Step S490: For the non-first business intelligent agent called under business process M, obtain the historical execution information required by the non-first business intelligent agent, the task information of the corresponding sub-task, and the prompt information of business process M, input the non-first business intelligent agent to execute the task, and obtain the task execution result.

[0129] Specifically, the process decision module determines the business intelligence agent for each call; the process prompt word module determines the prompt information required by the business intelligence agent; the process management module determines the historical execution information and corresponding sub-task information required by the business intelligence agent; the process recording module records the task execution results of the business intelligence agent; and the process decision module extracts the execution process of the business intelligence agent for each call based on the business scenario of the business process to obtain execution information.

[0130] This solution constructs a general process intelligence agent to schedule the independent business intelligence agents under the business process, decides which business intelligence agent to call each time, and when executing tasks through the business intelligence agent, it can obtain historical execution information as context information and input it into the business intelligence agent along with the task information of the corresponding subtask. In this way, the relationship between the independent business intelligence agents is established through context information, so that when the business intelligence agent executes tasks, it can trace back the context, coordinate process nodes with interdependent relationships, and improve the accuracy of task processing.

[0131] In an exemplary embodiment, to facilitate understanding of the embodiments of this disclosure by those skilled in the art, the following will provide further explanation with reference to the accompanying drawings.

[0132] refer to Figure 5 This diagram illustrates a system architecture for implementing a business process processing method. As shown, the ProcessAgent can simultaneously manage multiple business processes, such as order processing, R&D release, content review, and customer service. Each operation within each business process generates a ProcessInstance. The ProcessAgent acts as a coordinator, associated with each business process, knowing all the business agents within each process, and scheduling these agents. This involves a ProcessManager module, a ProcessPrompt module, a ProcessRecord module, and a ProcessDecision module.

[0133] The ProcessManager module is used to manage the individual process instances of each business process.

[0134] The ProcessPrompt module is used to maintain the prompt information (Prompt) corresponding to each business process, so that it can be used when the business intelligence agent performs tasks.

[0135] The ProcessRecord module is used to record the execution process of each business process.

[0136] The ProcessDecision module includes the following functions:

[0137] (1) Context backtracking of business agent: Before calling business agent, the process decision module will backtrack the key context of the previous process, select the most relevant information in the current scenario, provide richer information to the business agent in this process, and increase the accuracy of business agent execution.

[0138] (2) Execution decision of business agent: The process decision module will decide the business agent to be called to execute the corresponding process based on the current business status information (including user operation behavior) to achieve optimal business agent matching.

[0139] (3) Context extraction of business agents: The process decision module will coordinate N business agents. If all the contexts of each business agent are recorded, the context will be too long. Therefore, the process decision module extracts the key information of the business agent context in combination with the business scenario.

[0140] like Figure 5 As shown, the business intelligence agent generated for the business process executes tasks according to the scheduling instructions of the process intelligence agent. The output task execution results, execution process and other information are synchronized to the process intelligence agent, and the process recording module, process management module and process decision module in the process intelligence agent record the information or extract the context.

[0141] refer to Figure 6 This is a schematic diagram illustrating a process for scheduling a business intelligence agent through a process intelligence agent, as shown in one embodiment, including:

[0142] (1) The Process Management Module (ProcessManager) queries the corresponding Process Instance (ProcessInstance) based on the business identifier (bizCode) of the business process and the version identifier (bizId) of the current processing to determine the current process node and process status information, so that the Process Decision Module (ProcessDecision) can make a decision to call the business Agent.

[0143] (2) Using the business identifier (bizCode) of the business process as an index, obtain the prompt information (Prompt) corresponding to the business process through the process prompt word module (ProcessPrompt). In some embodiments, the prompt information includes the system-level SystemPrompt (you are a business process processing assistant) and the business-defined ExtPrompt (some additional prompts for the business).

[0144] (3) Input these prompts, task information and context information into the determined business agent to obtain the execution result AgentResult of the business agent.

[0145] (4) The process result (ProcessResult) and the current process status (ProcessStatus) are associated and stored through the process record module (ProcessRecord) to persist the process status and result for use in the next process drive.

[0146] This solution constructs a general business agent management framework (AgentFramework), which internally collects and manages all tools to form a unified protocol, and externally can adapt to various large-scale models, exhibiting high flexibility. On the other hand, it constructs a process agent, which expands upon the traditional agent, enabling the management of the entire business process and coordinating and scheduling all business agents within the business process, allowing business agents to execute tasks based on context information.

[0147] Understandably, in a traditional agent-based workflow, a task begins with user input, the larger model plans and calls different tools to complete the task, and finally outputs the result, thus completing the task. The agent has memory capabilities during the current task, but this memory disappears upon task completion. Furthermore, traditional agent-based workflows are stateless; the agent's start-to-completion process is a continuous action, and its lifecycle ends upon task completion. However, for business applications, a business process can be very long, requiring long-term business memory to refine the context of the larger model and coordinate the dependencies between process nodes in subsequent business process processing. Moreover, business operations often involve multiple rounds of human-machine collaboration to advance the process, thus necessitating the recording of the current state to ensure the correct execution of subsequent processes.

[0148] Through the above design of this solution: (1) it can understand complex business processes, maintain the process of process handling, and have relevant processing memory; (2) it can maintain the process state, track the process through the state, and realize the context maintenance of each process node; (3) with the support of state persistence, it naturally supports human-machine collaboration, and the execution of the process can be promoted in the business through human-machine collaboration; (4) through process persistence and context maintenance, fine task planning can be carried out at each process node / at the same process node.

[0149] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0150] It is understood that the same / similar parts between the various embodiments of the methods described above in this specification can be referred to each other. Each embodiment focuses on the differences from other embodiments, and relevant parts can be referred to the description of other method embodiments.

[0151] Based on the same inventive concept, this disclosure also provides a business process processing apparatus for implementing the business process processing method described above.

[0152] Figure 7 This is a structural block diagram illustrating a business process processing apparatus according to an exemplary embodiment. (Refer to...) Figure 7 The device includes:

[0153] The business determination unit 710 is configured to execute a business process to be processed; the business process to be processed includes multiple process nodes, and each process node corresponds to a subtask.

[0154] The agent generation unit 720 is configured to generate at least one business agent required for the execution of the business process, and to construct the process agent; the process agent is used to schedule the various business agents under the business process.

[0155] The intelligent agent scheduling unit 730 is configured to execute during the execution of a business process, determine the target business intelligent agent for each call through the process intelligent agent, and obtain the historical execution information and corresponding subtask task information required by the target business intelligent agent; the historical execution information is filtered from the execution information of the business intelligent agents before the target business intelligent agent;

[0156] The task execution unit 740 is configured to input historical execution information and the task information of the corresponding subtasks into the target business intelligence agent for processing, and obtain the task execution result.

[0157] In an exemplary embodiment, the agent generation unit 720 is further configured to execute business capabilities required to determine the execution of a business process; to standardize and encapsulate the business capabilities based on a model context protocol to generate a set of tools that can be called by a large language model; and to generate at least one business agent required to execute the business process based on the set of tools and the large language model.

[0158] In an exemplary embodiment, the intelligent agent generation unit 720 is further configured to execute a process management module, a process prompt word module, a process recording module, and a process decision module; input business information corresponding to the business process into the process management module; and input prompt information corresponding to the business process into the process prompt word module; and integrate the process management module for inputting business information, the process prompt word module for inputting prompt information, the process recording module, and the process decision module to obtain a process intelligent agent.

[0159] In an exemplary embodiment, a process intelligence agent is used for scheduling business intelligence agents under multiple business processes; wherein, for each processing of any business process, a process instance is created to record the process execution progress; the intelligence agent scheduling unit 730 is further configured to query the process instance created for the current processing of the business process based on the business identifier of the business process and the version identifier of the current processing, determine the current process node and the corresponding process status information; and determine the target business intelligence agent to be invoked based on the current process node and process status information.

[0160] In an exemplary embodiment, the task execution unit 740 is further configured to, during the execution of a business process, if the target business intelligence agent being invoked is the first business intelligence agent in the business process, obtain the task information of the subtask corresponding to the target business intelligence agent and input it into the target business intelligence agent; if the target business intelligence agent being invoked is not the first business intelligence agent in the business process, obtain the historical execution information required by the target business intelligence agent and the task information of the corresponding subtask and input it into the target business intelligence agent.

[0161] In an exemplary embodiment, the task execution unit 740 is further configured to execute prompt information required to obtain the target business intelligence agent; if the target business intelligence agent called is the first business intelligence agent in the business process, the prompt information and task information are input into the target business intelligence agent for processing to obtain the task execution result; if the target business intelligence agent called is not the first business intelligence agent in the business process, the prompt information, historical execution information and task information are input into the target business intelligence agent for processing to obtain the task execution result.

[0162] In an exemplary embodiment, the process intelligence agent includes a process management module, a process prompt word module, a process decision module, and a process recording module. The process decision module determines the target business intelligence agent for each call; the process prompt word module determines the prompt information required by the target business intelligence agent; the process management module determines the historical execution information and corresponding sub-task task information required by the target business intelligence agent; the process recording module records the task execution results of the target business intelligence agent; and the process decision module extracts the execution process of the target business intelligence agent for each call based on the business scenario of the business process to obtain execution information.

[0163] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0164] Figure 8 This is a block diagram illustrating an electronic device 800 for implementing a business process processing method according to an exemplary embodiment. For example, the electronic device 800 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0165] Reference Figure 8 The electronic device 800 may include one or more of the following components: processing component 802, memory 804, power supply component 806, multimedia component 808, audio component 810, input / output (I / O) interface 812, sensor component 814, and communication component 816.

[0166] Processing component 802 typically controls the overall operation of electronic device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0167] Memory 804 is configured to store various types of data to support the operation of electronic device 800. Examples of such data include instructions for any application or method operating on electronic device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, optical disk, or graphene memory.

[0168] Power supply component 806 provides power to various components of electronic device 800. Power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 800.

[0169] Multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0170] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when electronic device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0171] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0172] Sensor assembly 814 includes one or more sensors for providing state assessments of various aspects of electronic device 800. For example, sensor assembly 814 can detect the on / off state of electronic device 800, the relative positioning of components such as the display and keypad of electronic device 800, changes in position of electronic device 800 or its components, the presence or absence of user contact with electronic device 800, orientation or acceleration / deceleration of device 800, and temperature changes of electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0173] Communication component 816 is configured to facilitate wired or wireless communication between electronic device 800 and other devices. Electronic device 800 can access wireless networks based on communication standards, such as WiFi, carrier networks (such as 2G, 3G, 4G, or 5G), or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0174] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0175] In one exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, which can be executed by a processor 820 of an electronic device 800 to perform the above-described method. For example, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0176] In one exemplary embodiment, a computer program product is also provided, which includes instructions that can be executed by a processor 820 of an electronic device 800 to perform the above-described method.

[0177] It should be noted that the above-mentioned apparatus, electronic equipment, computer-readable storage medium, computer program product, etc., may also include other implementation methods according to the description of the method embodiments. For specific implementation methods, please refer to the description of the relevant method embodiments, which will not be elaborated here.

[0178] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0179] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A business process processing method, characterized in that, include: Identify the business processes to be processed; The business process to be processed includes multiple process nodes, and each process node corresponds to a sub-task. Generate at least one business agent required to execute the business process, and construct the process agent; The process intelligence agent is used to schedule the various business intelligence agents under the business process. During the execution of the business process, the process agent determines the target business agent for each call and obtains the historical execution information and corresponding subtask task information required by the target business agent. The historical execution information is filtered from the execution information of previous business intelligence agents before the target business intelligence agent; The historical execution information and the corresponding subtask task information are input into the target business agent for processing to obtain the task execution result.

2. The method according to claim 1, characterized in that, The generation of at least one business agent required to execute the business process includes: Determine the business capabilities required to execute the business process; Based on the model context protocol, the business capabilities are standardized and encapsulated to generate a set of tools that can be called by a large language model. Based on the aforementioned toolset and large language model, at least one business agent required to execute the aforementioned business process is generated.

3. The method according to claim 1, characterized in that, The construction process intelligent agent includes: Build a process management module, a process prompt word module, a process recording module, and a process decision module; The business information corresponding to the business process is entered into the process management module; and the prompt information corresponding to the business process is constructed and entered into the process prompt word module. The process intelligent agent is obtained by integrating the process management module for inputting the business information, the process prompt word module for inputting the prompt information, the process recording module, and the process decision module.

4. The method according to claim 1, characterized in that, The process intelligence agent is used for scheduling business intelligence agents under multiple business processes; wherein, for each processing of any business process, a process instance is created to record the process execution progress. The step of determining the target business agent for each call through the process agent includes: Based on the business identifier of the business process and the version identifier of this processing, query the process instance created for this processing of the business process, and determine the current process node and the corresponding process status information. Based on the current process node and process status information, the target business intelligence agent to be invoked is determined.

5. The method according to claim 1, characterized in that, The method further includes: During the execution of the business process, if the target business agent called is the first business agent of the business process, then the task information of the subtask corresponding to the target business agent is obtained and input into the target business agent; If the target business agent being invoked is not the first business agent in the business process, then the historical execution information and corresponding subtask task information required by the target business agent are obtained and input into the target business agent.

6. The method according to claim 5, characterized in that, The method further includes: Obtain the prompt information required by the target business intelligent agent; If the target business agent invoked is the first business agent in the business process, then the prompt information and the task information are input into the target business agent for processing to obtain the task execution result; If the target business agent being invoked is not the first business agent in the business process, then the prompt information, the historical execution information, and the task information are input into the target business agent for processing to obtain the task execution result.

7. The method according to any one of claims 1-6, characterized in that, The process intelligence agent includes a process management module, a process prompt word module, a process decision module, and a process recording module; the method further includes: The process decision module determines the target business intelligence agent for each call. The process prompting module determines the prompting information required by the target business intelligent agent; The process management module determines the historical execution information and corresponding sub-task information required by the target business intelligent agent. The process recording module records the task execution results of the target business intelligence agent. The process decision module extracts the execution process of the target business agent for each call based on the business scenario of the business process, and obtains the execution information.

8. A business process processing device, characterized in that, include: The business determination unit is configured to execute a determined business process to be processed. The business process to be processed includes multiple process nodes, and each process node corresponds to a sub-task. The agent generation unit is configured to generate at least one business agent required to execute the business process, and to construct the process agent; The process intelligence agent is used to schedule the various business intelligence agents under the business process. The agent scheduling unit is configured to, during the execution of the business process, determine the target business agent for each call through the process agent, and obtain the historical execution information and corresponding subtask task information required by the target business agent. The historical execution information is filtered from the execution information of previous business intelligence agents before the target business intelligence agent; The task execution unit is configured to input the historical execution information and the task information of the corresponding subtasks into the target business intelligence agent for processing, and obtain the task execution result.

9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the business process processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the business process processing method as described in any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the business process processing method according to any one of claims 1 to 7.

Images