Intelligent business and process processing method, device, computer equipment, readable storage medium and program product

Abstract

The present application relates to an intelligent business and process processing method, device, computer equipment, computer-readable storage medium and computer program product. The method comprises: obtaining initial business operation description information, and disassembling the initial business operation description information to obtain at least one process node; matching each process node with each standard node in a standard flow chart, and determining the dependency relationship of the process node based on the dependency relationship of each standard node matched with the process node; generating a known process path to be executed based on the dependency relationship of each process node and the standard flow chart; and performing business processing based on the known process path to be executed. The use of this method can improve the level of intelligence.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an intelligent business and process processing method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] The Large Language Model (LLM) is an artificial intelligence language model based on deep learning. With its powerful semantic understanding, content generation, and logical reasoning capabilities, the large model can achieve human-level conversations and chats. In addition, the intelligent agent based on the large model can enable people to automatically perform and handle one or more professional or complex work tasks in natural language interaction, thereby releasing the energy of personnel to a great extent. After being promoted and applied in recent years, it has gained wide attention and recognition in the industry.

[0003] There are a large number of business systems in financial enterprises, and each business node is composed of strict business processes. These systems must be operated by professional staff who have received certain training. At the same time, the trial and error costs are often high, and the requirements for operators are naturally high, which undoubtedly increases the operating costs of the enterprise.

[0004] Traditional process automation has been widely used in various industries, especially in the financial field, which often has many business scenarios with complicated rules and lengthy processes. This saves a lot of human resources, freeing up human resources to be applied to more challenging, creative and complex work tasks. Despite this, traditional process automation technology still faces considerable challenges and difficulties in dealing with real industry problems. It has a low level of intelligence and cannot effectively understand user needs and interact with users intelligently. Summary of the invention

[0005] Based on this, it is necessary to provide an intelligent business and process processing method, device, computer equipment, computer-readable storage medium and computer program product that can improve the level of intelligence in response to the above-mentioned technical problems.

[0006] In a first aspect, the present application discloses an intelligent business and process processing method, the method comprising:

[0007] Acquire initial business operation description information, and decompose the initial business operation description information to obtain at least one process node;

[0008] Matching each of the process nodes with each standard node in the standard flow chart, and determining the dependency relationship of the process nodes based on the dependency relationship of each of the standard nodes matched with the process nodes;

[0009] Based on the dependency relationship of each of the process nodes and the standard flow chart, generating a known process path to be executed;

[0010] Business processing is performed based on the known process path to be executed.

[0011] In one embodiment, generating a known process path to be executed based on the dependency relationship of each process node and the standard flow chart includes:

[0012] Determining whether there is a missing necessary node based on the standard nodes matched by each of the process nodes and the dependency relationship of the standard nodes;

[0013] In the case where the missing necessary node exists and the missing necessary node is unique, generating a known process path to be executed based on the missing necessary node, the standard flow chart and each of the process nodes;

[0014] In the case where the missing necessary node exists and the missing necessary node is not unique, candidate nodes are determined based on the standard flowchart, and target missing necessary nodes are determined from the candidate nodes based on a guided inquiry interaction method, and known process paths to be executed are generated based on the determined target missing necessary nodes, the standard flowchart, and each of the process nodes;

[0015] If there is no missing necessary node, a known process path to be executed is generated based on the standard flow chart and each of the process nodes.

[0016] In one embodiment, after generating the known process path to be executed based on the dependency relationship of each process node and the standard process diagram, the method further includes:

[0017] Obtain the first node of the known process path to be executed;

[0018] Determine whether the first node has a preceding node based on the standard flow chart;

[0019] If the first node has the preceding node and the initial business operation description information does not contain necessary parameter information corresponding to the preceding node, obtain the necessary parameter information corresponding to the preceding node through a guided inquiry interaction; update the first node of the known process path to be executed to be the preceding node;

[0020] If the first node has only one predecessor node, and the initial business operation description information contains necessary parameter information corresponding to the predecessor node, updating the first node of the known process path to be executed to be the predecessor node;

[0021] In the case that there are multiple predecessor nodes for the first node, and the necessary parameter information corresponding to the predecessor node does not exist in the initial business operation description information, based on the multiple predecessor nodes, a target predecessor node and necessary parameter information corresponding to the target predecessor node are determined through a guided inquiry interaction method, and the first node of the known process path to be executed is updated to be the target predecessor node;

[0022] In the case that there are multiple predecessor nodes of the first node, and the necessary parameter information corresponding to the predecessor node does not exist in the initial business operation description information, based on obtaining the priorities of the multiple predecessor nodes, updating the first node of the known process path to be executed to be the predecessor node with the highest priority, wherein the priority of the node is stored in the standard flow chart;

[0023] Continue to execute the step of determining whether the first node has a predecessor node based on the standard flow chart until the first node has no predecessor node.

[0024] In one embodiment, the performing business processing based on the to-be-executed known process path includes:

[0025] Based on the dependency relationship between the nodes in the known process path to be executed, execute each node in sequence;

[0026] If the node is in the executed state, skip the node;

[0027] When the state of the node is unexecuted, the node is executed through the interface tool, and after the execution is completed, the state of the node is modified to executed.

[0028] In one embodiment, executing the node through the interface tool and, after the execution is completed, modifying the state of the node to executed includes:

[0029] Executing the node through the interface tool, and if the node is successfully executed, changing the state of the node to executed;

[0030] The node is executed through the interface tool, and in the event that the node fails to execute, information on the execution failure is collected, and based on the information on the execution failure, the node information of the node is supplemented through a guided inquiry interaction method, and the node is executed through the interface tool based on the supplemented node information until the node is successfully executed, and the node status is changed to executed.

[0031] In one embodiment, before the business processing is performed based on the to-be-executed known process path, the method further includes:

[0032] Checking the necessary parameter information of each node in the known process path to be executed;

[0033] In the case where there is a node that lacks necessary parameter information, the necessary parameter information of the node is supplemented through an active query interaction.

[0034] In one embodiment, the method further comprises:

[0035] Determine whether there is a post-node in the known process path to be executed based on the standard process diagram;

[0036] In the case that there is a unique post-node in the known process path to be executed, necessary parameter information of the post-node is obtained through active query interaction, and the execution result of the post-node is obtained based on the necessary parameter information, and the post-node is used as the last node of the known process path to be executed;

[0037] In the case where there are multiple post-nodes in the known process path to be executed, post-node selection information is output through a guided inquiry interaction mode, and in the case of receiving an ignore selection instruction, the post-node with the highest priority is selected as the first target post-node, and necessary parameter information of the first target post-node is obtained, and the execution result of the first target post-node is obtained based on the necessary parameter information, and the first target post-node is used as the last node of the known process path to be executed;

[0038] In the case where there are multiple post-nodes in the known process path to be executed, post-node selection information is output through a guided inquiry interaction mode, and when a confirmation instruction of a second target post-node is received, necessary parameter information of the second target post-node is obtained, and an execution result of the second target post-node is obtained based on the necessary parameter information, and the second target post-node is used as the last node of the known process path to be executed;

[0039] Continue to execute the step of determining whether there is a subsequent node in the known process path to be executed based on the standard flowchart until there is no subsequent node in the known process path to be executed or it is confirmed that the execution is terminated.

[0040] In one embodiment, the method further comprises:

[0041] When the known process path to be executed is executed to the last node and other process node selection instructions are received, the target business description information corresponding to the other process nodes is obtained;

[0042] The known process path to be executed is used as the upper-level process, the target business operation description information is used as the initial business operation description information of the branch process, and the step of disassembling the initial business operation description information to obtain at least one process node is continued.

[0043] In one embodiment, the method further comprises:

[0044] After the execution of the known process path to be executed corresponding to the branch process is completed, jump to the last node of the known process path to be executed corresponding to the upper-level process, and continue to execute the step of determining whether there is a post-node in the known process path to be executed based on the standard flowchart.

[0045] In one embodiment, the method further comprises:

[0046] Acquire historical business process information, obtain a target process node based on the business process information, and decompose the target process node into an operation type and an operation object;

[0047] Establishing a dependency relationship between each of the target process nodes based on the historical business process information, and configuring a priority of each of the target process nodes based on the dependency relationship;

[0048] A standard flow chart is generated based on the target process node, the operation type, the operation object, the dependency relationship and the priority.

[0049] In one embodiment, configuring the priority of each target process node based on the dependency relationship includes at least one of the following methods:

[0050] configuring a fixed priority of each of the target process nodes based on the dependency relationship; or

[0051] The initial priority of each of the target process nodes is configured based on the dependency relationship, user habit information is obtained, and the initial priority is adjusted based on the user habit information.

[0052] In a second aspect, the present application further discloses an intelligent business and process processing device, the device comprising:

[0053] A process node generation module, used to obtain initial business operation description information, and disassemble the initial business operation description information to obtain at least one process node;

[0054] A matching module, used for matching each of the process nodes with each of the standard nodes in the standard flow chart, and determining the dependency relationship of the process nodes based on the dependency relationship of each of the standard nodes matched with the process nodes;

[0055] A known process path generation module to be executed, used to generate a known process path to be executed based on the dependency relationship of each process node and the standard flow chart;

[0056] The business processing module is used to perform business processing based on the known process path to be executed.

[0057] In a third aspect, the present application further discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0058] In a fourth aspect, the present application further discloses a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0059] In a fifth aspect, the present application also discloses a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0060] The above-mentioned intelligent business and process processing method, device, computer equipment, computer-readable storage medium and computer program product obtain the initial business operation description information, and disassemble the initial business operation description information to obtain at least one process node; match each process node with each standard node in the standard flow chart, and determine the dependency of the process node based on the dependency of each standard node matched with the process node; generate a known process path to be executed based on the dependency of each process node and the standard flow chart; perform business processing based on the known process path to be executed and freely perform intelligent interaction of subsequent business processes, which greatly weakens the threshold of business system process operation, while reducing the workload of enterprise personnel and improving the overall investment and research efficiency of the enterprise. From the user's perspective, these process executions and operations are all executed in the background, which is imperceptible to the user, that is, they have a better user experience and improve the level of intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1 An application environment diagram of an intelligent business and process processing method in an embodiment;

[0063] Figure 2 A flowchart of an intelligent business and process processing method in one embodiment;

[0064] Figure 3 A schematic diagram of a standard flow chart construction step in one embodiment;

[0065] Figure 4 A flowchart of an intelligent business and process processing method in another embodiment;

[0066] Figure 5 A flowchart of a business interface agent in one embodiment;

[0067] Figure 6 A schematic diagram of a first node determination step in an embodiment;

[0068] Figure 7 A flowchart of a post-node boot execution process in one embodiment;

[0069] Figure 8 It is a structural block diagram of an intelligent business and process processing device in one embodiment;

[0070] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0072] The intelligent business and process processing method provided in the embodiments of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers.

[0073] The terminal 102 can send the initial task description information generated during the question-and-answer process to the server 104. The server 104 obtains the initial business operation description information, and disassembles the initial business operation description information to obtain at least one process node; matches each process node with each standard node in the standard flow chart, and determines the dependency relationship of the process node based on the dependency relationship of each standard node matched with the process node; generates a known process path to be executed based on the dependency relationship of each process node and the standard flow chart; performs business processing based on the known process path to be executed based on the process path to be executed, which greatly weakens the threshold of business system process operation, and at the same time reduces the workload of enterprise personnel and improves the overall investment research efficiency of the enterprise. From the user's perspective, these process executions and operations are all executed in the background, which is imperceptible to the user, that is, it has a better user experience and improves the level of intelligence.

[0074] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0075] In an exemplary embodiment, Figure 2 As shown, an intelligent business and process processing method is provided, which is applied to Figure 1 The server in the example is used to illustrate, including the following steps 202 to 208. Among them:

[0076] S202: Acquire initial business operation description information, and decompose the initial business operation description information to obtain at least one process node.

[0077] The initial business operation description information is the first business operation description input by the user through natural language, which may include the operation of a single process node or the operation of several consecutive process nodes. The description may describe the complete user process operation requirements, or may only be a partial operation requirement, that is, a partial process is executed and serves as the entry point for subsequent processes. There will be further process operation descriptions later. No specific restrictions are imposed on the initial business operation description information.

[0078] The process of process planning is to decompose the initial business operation description information to obtain at least one process node. The initial business operation description information is decomposed to obtain at least one process node. These process nodes are unordered. Optionally, in this embodiment, only one process node can be decomposed or multiple process nodes can be decomposed.

[0079] Optionally, the process planning can use the planning capabilities of the large model to parse and decompose the user input description into a number of structured continuous process sequences, including strictly self-increasing process node numbers and process nodes (i.e. descriptions). This step is completed by the process planning agent, whose role is to achieve the above goals.

[0080] The steps of process planning include: building a planning agent prompt. In order to allow the agent to produce results that meet the user's expectations, a prompt specifically for process planning is built. The prompt includes process node descriptions, process node standard names, output structure standardization, and 3-5 task planning examples. Output examples include: 1. Operation: Create factor group, object: XXX, 2. Operation: Create factor, object: XXX. The planning process does not need to consider node dependencies, and its dependencies are determined by the subsequent standard flow chart.

[0081] S204: Match each process node with each standard node in the standard flow chart, and determine the dependency relationship of the process node based on the dependency relationship of each standard node matched with the process node.

[0082] S206: Generate a known process path to be executed based on the dependency relationship of each process node and the standard flow chart.

[0083] Optionally, after the above process sequence is generated, the large model determines which nodes in the standard flow chart each process node in the sequence belongs to. In the standard flow chart, the matching nodes are linked through the inter-node dependency relationship in the standard flow chart to generate a known process path to be executed, and the dependency relationship of each process node is obtained.

[0084] The standard flowchart is pre-generated and built by industry experts for the traditional business system of the enterprise. Unless the business system is updated or upgraded, the standard flowchart will be updated accordingly. All subsequent user business operation needs are guided interactive execution of business process operations through natural language and based on the standard flowchart.

[0085] In one of the optional embodiments, the method for generating a standard flowchart includes: obtaining historical business process information, and obtaining a target process node based on the business process information, and decomposing the target process node into an operation type and an operation object; establishing a dependency relationship among each target process node based on the historical business process information, and configuring a priority of each target process node based on the dependency relationship; generating a standard flowchart based on the target process node, operation type, operation object, dependency relationship and priority.

[0086] Optionally, the priority of each target process node is configured based on the dependency relationship, including at least one of the following methods: configuring a fixed priority of each target process node based on the dependency relationship; or configuring an initial priority of each target process node based on the dependency relationship, obtaining user habit information, and adjusting the initial priority based on the user habit information.

[0087] Among them, combined Figure 3 As shown, the process of constructing this standard flow chart includes:

[0088] Step 1: Sort out the traditional or existing business systems of the enterprise, and decompose the process nodes into operation types and operation objects for sorting. Operation types include business operation actions such as creation, deletion, query, modification, review, execution, output, and import. Operation objects include objects to which operation actions are applied, such as users, accounts, factors, calculation tasks, and reports. By making a complete combination of the two dimensions of operation type and operation object (such as creating users, importing factors, outputting reports, etc.), a set of process nodes sufficient to cover all business nodes can be generated. Of course, in real scenarios, not all types of object combination nodes are valid or meaningful. When establishing node dependencies in the future, ignore the dependencies of this type of nodes, making them isolated nodes, so that they will not enter and affect the guided automation process mechanism.

[0089] Step 2: Establish effective process node dependencies. With the help of professional opinions from industry experts who are familiar with the business system, based on the design base of the directed acyclic graph, the above process nodes are used as the vertices of the graph, and the dependencies between the nodes are used as the edges of the graph. For example, after the factor is created, the calculation task based on the factor can be created, and then the analysis report based on the calculation task can be generated. That is, the above three nodes are connected by edges to reflect the dependencies and sequence between them. At the same time, in order to deal with complex situations that are more in line with real-life scenarios, the dependencies between nodes are not one-to-one. There will be several subsequent nodes after each process node (for example, after creating a record A, the user may continue to create a new record B, or may continue other operations on record A). And the subsequent nodes will be distinguished by the initial priority order given by industry experts (that is, the node with the highest priority is more likely to become the next node selected by the user than other nodes. If the user does not explicitly specify the next node, the system will select the node with the highest priority as the next node). In addition, this priority module is dynamically adjusted based on user usage habits. As the number of actual selections by subsequent users in actual use is used as a weight, the priority order is continuously optimized and adjusted, so that users have a better user experience.

[0090] Step 3: Generate a standard flow chart. Based on the graph object constructed in the above steps, a standard flow chart suitable for the business system is finally generated and persisted as a system module for subsequent calls.

[0091] S208: Perform business processing based on the known process path to be executed.

[0092] Specifically, combined Figure 4 As shown in , after generating a known process path to be executed, the upper-level process execution body can call the business interface intelligent body to perform business operations until the business operations are completed. Figure 4 The initial business operation description information is user Query, and a single process or multiple processes are obtained through the process planning agent. The single process matches the process nodes, and the multiple processes match the process nodes and generate the known process path to be executed. Among them, the single process can also be regarded as a known process path to be executed with only one process node. Subsequently, the upper-level process execution body calls the business interface agent to perform business operations until the business operation is completed.

[0093] In one of the optional embodiments, in combination Figure 5 As shown, Figure 5It is a flow chart of the business interface agent. This agent only relies on the big model and its function calling function, and based on the tree-like organizational structure of many tools (the tools here can be interpreted as enterprise business operation interfaces, including private domain interfaces), it uses multiple big model requests for the same task, each time hitting the right tree fork node until the target tool is selected. This design is also to overcome the practical difficulties of the large language model's capabilities and context length limitations. The language model cannot handle a large number of tools at one time. Its essence is to gradually obtain all the information through multiple inquiries, each query only returns the key information of concern to that layer. At the same time, the tree-like organizational structure requires human experts to classify the existing tools in layers in advance, which is equivalent to giving the agent expert opinions, which is particularly suitable for use in tool intelligent calling scenarios with complex business scenarios and long business chains. The specific steps are as follows:

[0094] Step 1: Tool construction and registration. Since the tools (interfaces) need to be reconstructed in a tree-like organization, the tools can be hierarchically classified according to the department system and functional granularity. In summary, each node in the abstract class layer needs to build a category tool (the function of this tool is to return the position of the current node), until the actual tool at the bottom layer. The tool needs to include two parts: 1. The text description of the tool, including the actual function of the tool, the tool name, the parameters included in the tool, the parameter type and the parameter meaning; 2. The implementation of the tool, including the acquisition of the tool parameters, can be processed into the required parameters through the general parameter extractor. Register the tool with the build number in the project for subsequent calls (i.e., write to the variable space).

[0095] Step 2: Based on the tree structure, execute from the top level of the tree downwards, write the first layer of candidate tools into the function call parameters of the big model, and the big model returns the tool node related to the query request.

[0096] Step 3: Starting from the tool node position in the previous step, write the second-layer candidate tool under the node into the function call parameter of the large model, and the large model returns the next-layer tool node related to the query request. And so on, until the actual tool is reached, that is, the last layer ends the loop.

[0097] Step 4: While hitting the actual tool in the previous step, return the structured parameters required by the tool.

[0098] Step 5: If the standard parameters are not found, the system returns to prompt the user for further filling.

[0099] Step 6. Execute the selected tool, perform the process operation, and return the process execution result.

[0100] The above-mentioned intelligent business and process processing method, device, computer equipment, computer-readable storage medium and computer program product obtain the initial business operation description information, and disassemble the initial business operation description information to obtain at least one process node; match each process node with each standard node in the standard flow chart, and determine the dependency of the process node based on the dependency of each standard node matched with the process node; generate a known process path to be executed based on the dependency of each process node and the standard flow chart; perform business processing based on the known process path to be executed based on the process path to be executed, which greatly weakens the threshold of business system process operation, and at the same time reduces the workload of enterprise personnel and improves the overall investment research efficiency of the enterprise. From the user's perspective, these process executions and operations are all executed in the background, which is imperceptible to the user, that is, it has a better user experience and improves the level of intelligence.

[0101] In one of the optional embodiments, a known process path to be executed is generated based on the dependency relationship of each process node and the standard flowchart, including: determining whether there is a missing necessary node based on the standard nodes matched by each process node and the dependency relationship of the standard nodes; if there is a missing necessary node and the missing necessary node is unique, generating the known process path to be executed based on the missing necessary node, the standard flowchart and each process node; if there is a missing necessary node and the missing necessary node is not unique, determining candidate nodes based on the standard flowchart, and determining the target missing necessary node from the candidate nodes based on a guided query interaction method, generating the known process path to be executed based on the determined target missing necessary node, the standard flowchart and each process node; if there is no missing necessary node, generating the known process path to be executed based on the standard flowchart and each process node.

[0102] Among them, in this embodiment, based on the dependency relationship of each process node and the standard flowchart, there may be three situations in which the known process path to be executed is generated. Specifically, if there is a path interruption in the generated process path, that is, the node that should be in the path is not mentioned in the user description and there are multiple combinations of the missing path part, it can be confirmed with the user in the subsequent guided inquiry interaction. If there is only one combination of the missing path part, the process path can be automatically completed according to the standard flowchart, without the user further participating in the guided selection, and only the necessary parameters of the part need to be obtained through interaction with the user. If there is no missing necessary node, the known process path to be executed is generated based on the standard flowchart and each process node.

[0103] In one of the optional embodiments, after generating a known process path to be executed based on the dependency relationship of each process node and the standard flowchart, it also includes: obtaining the first node of the known process path to be executed; judging whether the first node has a predecessor node based on the standard flowchart; if there is a predecessor node for the first node and there is no necessary parameter information corresponding to the predecessor node in the initial business operation description information, obtaining the necessary parameter information corresponding to the predecessor node through a guided inquiry interaction method; updating the first node of the known process path to be executed as a predecessor node; if there is a unique predecessor node for the first node and there is necessary parameter information corresponding to the predecessor node in the initial business operation description information, updating the first node of the known process path to be executed as a predecessor node; if there are multiple predecessor nodes for the first node predecessor nodes, and the necessary parameter information corresponding to the predecessor node does not exist in the initial business operation description information, based on multiple predecessor nodes, the target predecessor node and the necessary parameter information corresponding to the target predecessor node are determined through a guided inquiry interaction method, and the first node of the known process path to be executed is updated to be the target predecessor node; when there are multiple predecessor nodes for the first node, and the necessary parameter information corresponding to the predecessor node does not exist in the initial business operation description information, based on obtaining the priorities of the multiple predecessor nodes, the first node of the known process path to be executed is updated to be the predecessor node with the highest priority, wherein the priority of the node is stored in the standard flowchart; continue to execute the step of determining whether the first node has a predecessor node based on the standard flowchart until the first node has no predecessor node.

[0104] Specifically, combined Figure 6 As shown, Figure 6 This is a schematic diagram of the first node determination step in an embodiment. In this embodiment, the first node is the starting node. Because the first node provided by the user may not be the starting node of a valid process path. For example, the first node in the user description is to create a factor, but the starting node in a valid process path should be the factor group where the factor is determined (if not, the factor group node must be created first). At this time, if the first node in the known process path needs to execute the preceding node first (determined by the node relationship between the standard flow chart) when executing and the description information does not have the necessary parameters required to execute the preceding node. Then actively interactively inquire the user, obtain the necessary information and use the preceding node as the first node. If the necessary parameter information of the preceding node already exists in the description and the preceding node is unique, the preceding node is automatically used as the first node. If there are multiple preceding nodes, multiple nodes are actively used as options and the user is asked to select the target node as the real preceding node or the node with the largest priority weight as the default node. The above steps are iteratively executed, and the executed preceding nodes are marked with the "executed" label until the first node is completely self-consistent and self-sufficient, and the node can be used as the initial node.

[0105] In one of the optional embodiments, business processing is performed based on a known process path to be executed based on a process path to be executed, including: executing each node in sequence based on the dependency relationship of each node in the known process path to be executed; skipping the node when the status of the node is executed; executing the node through an interface tool when the status of the node is not executed, and after the execution is completed, changing the status of the node to executed.

[0106] In one of the optional embodiments, a node is executed through an interface tool, and after the execution is completed, the state of the node is modified to executed, including: executing the node through the interface tool, and if the node is successfully executed, modifying the state of the node to executed; executing the node through the interface tool, and if the node fails to execute, collecting execution failure information, and based on the execution failure information, supplementing the node information of the node through a guided inquiry interaction method, executing the node through the interface tool based on the supplemented node information, until the node is successfully executed, and modifying the state of the node to executed.

[0107] Among them, combined Figure 7 As shown, enter the upper-level process executor to execute the known process path. Starting from the above initial node, follow the execution path and the node relationship in the standard flowchart, execute all nodes on the path in sequence, and skip the process nodes with the node label "executed". After each node is executed, after receiving the 'SUCCESS' returned by the tool interface, mark the node with the "executed" label. If the execution is not successful, the error message of the tool interface (such as missing required parameters) is returned to the user, and the user modifies the description and resubmits the execution until the execution is successful.

[0108] In one of the optional embodiments, before performing business processing based on the known process path to be executed, it also includes: checking the necessary parameter information of each node in the known process path to be executed; in the case where there are nodes that lack necessary parameter information, supplementing the necessary parameter information of the nodes through active query interaction.

[0109] Specifically, in order to avoid execution failure, the necessary parameters will be checked for missing before execution. If missing, the necessary parameter information and user interaction will be involved before the node is executed, that is, the necessary parameter information will be obtained through interaction with the user before the corresponding node is executed. According to the above logic, all known nodes are executed until they are all completed.

[0110] In one of the optional embodiments, the method further includes: determining whether there is a post-node in the known process path to be executed based on the standard flowchart; in the case that there is a unique post-node in the known process path to be executed, obtaining the necessary parameter information of the post-node through an active query interaction, and obtaining the execution result of the post-node based on the necessary parameter information, and taking the post-node as the last node of the known process path to be executed; in the case that there are multiple post-nodes in the known process path to be executed, outputting the post-node selection information through a guided query interaction, and in the case of receiving an ignore selection instruction, selecting the post-node with the highest priority as the first target post-node, and obtaining the necessary parameter information of the first target post-node, and based on The necessary parameter information is used to obtain the execution result of the first target post-node, and the first target post-node is used as the last node of the known process path to be executed; when there are multiple post-nodes in the known process path to be executed, the post-node selection information is output through a guided inquiry interaction method, and when a confirmation instruction of the second target post-node is received, the necessary parameter information of the second target post-node is obtained, and the execution result of the second target post-node is obtained based on the necessary parameter information, and the second target post-node is used as the last node of the known process path to be executed; the step of determining whether there is a post-node in the known process path to be executed based on the standard flowchart is continued until there is no post-node in the known process path to be executed or the execution is confirmed to end.

[0111] Among them, after all known process nodes are executed, the process stops at the last node of the known process path, that is, the last business operation node in the current user description, indicating that all current user business operation requirements have been completed. In a relatively complex business process system, users often do not describe all operation requirements at one time. At this time, the guided mode can help users continue with subsequent business process operations, that is, help users gradually filter and clarify the user's true intentions until all business operations required by the true intentions are completed (see the guided mode for details). Figure 4 ). According to the subsequent nodes (there may be several) of the current last node designed in the standard flow chart, the system will guide the user to choose the next actual intention or end the current demand. If the user chooses "Ignore", the default option will be taken, that is, the option with the highest priority among several options as the next node. If there is only one subsequent node, the subsequent node will be executed directly without guiding the user to choose, reducing unnecessary guidance and improving user experience.

[0112] In one of the optional embodiments, the method also includes: when the known process path to be executed is executed to the last node and other process node selection instructions are received, obtaining target business description information corresponding to other process nodes; using the completed known process path to be executed as the upper-level process, using the target business operation description information as the initial business operation description information of the branch process, and continuing to execute the step of disassembling the initial business operation description information to obtain at least one process node.

[0113] In one of the optional embodiments, the method also includes: after the execution of the known process path to be executed corresponding to the branch process is completed, jump to the last node of the known process path to be executed corresponding to the upper-level process, and continue to execute the step of determining whether there is a post-node in the known process path to be executed based on the standard flowchart.

[0114] In order to adapt to the complex real-life scenarios, in addition to the above-mentioned normal process, i.e. the upper-level process processing mechanism, we have also designed a branch process processing mechanism. That is, if the user does not select a node in the guidance options and selects "other process nodes" (i.e. non-post-process nodes), the system will actively ask the user for descriptions of other process nodes, and use the above-mentioned node matching method to match the corresponding process node from the standard flowchart, and use the node as the first node to create a branch process path in the current upper-level process path. Similarly, according to the above logic, the actual intention initial node under the branch path is found. The branch process can use the execution logic in the above steps to start executing the branch path node process until the user chooses to end the branch path business operation requirements or the standard flowchart reaches the end (i.e. the theoretical end point of the business process), and the branch process ends.

[0115] Afterwards, the system will automatically roll back to the last node in the upper-level process before entering the branch path process as the current node to continue the subsequent execution of the upper-level process. At the same time, combined with the execution path recorder cached in the current node of the upper-level process path, it will retrieve the historical log of the upper-level process execution, restore the relevant information since the execution of the upper-level process, return to the user's original business operation requirements in the upper-level process, and continue the subsequent execution of the original upper-level process according to the normal guided process processing mechanism until the user chooses to end all current business operation requirements or the standard flowchart reaches the end (that is, the end point of the business process in theory), and the guided process automation process ends.

[0116] The intelligent business and process processing method of the present application, with the help of the powerful semantic understanding ability of the big model, allows the business process that previously needed to be strictly operated according to the business operation process to be completed through a natural language description and a small amount of simple interaction with an assistant who understands the business. At the same time, this model also has certain advantages over the currently popular robotic process automation (RPA), that is, it can interact with the business system in a natural language manner, and more importantly, it has a higher degree of freedom in process execution, and can execute simpler, more complex or more arbitrary process requirements. This will greatly weaken the threshold for business system process operation, while reducing the workload of enterprise personnel and improving the overall investment and research efficiency of the enterprise. From the user's perspective, these process executions and operations are all executed in the background, which is imperceptible to the user, that is, they have a better user experience. At the same time, this application relies on the underlying interface of the original business system. Unless the underlying interface is updated and changed, the general update and change of the business system will not affect the intelligent automation process mechanism involved in this application, so it has good robustness. In addition, the entire method and system are scalable. In the face of more professional needs within the enterprise in the future, more business system interfaces and standard flow charts can be customized, and more and more professional business and work scenarios can be realized.

[0117] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0118] Based on the same inventive concept, the embodiment of the present application also provides an intelligent business and process processing device for implementing the intelligent business and process processing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more intelligent business and process processing device embodiments provided below can refer to the limitations of the intelligent business and process processing method above, and will not be repeated here.

[0119] In an exemplary embodiment, Figure 8As shown, an intelligent business and process processing device is provided, including: a process node generation module 801, a matching module 802, a known process path generation module 803 to be executed, and a business processing module 804, wherein:

[0120] A process node generation module 801 is used to obtain initial business operation description information and decompose the initial business operation description information to obtain at least one process node;

[0121] A matching module 802 is used to match each process node with each standard node in the standard flow chart, and determine the dependency relationship of the process node based on the dependency relationship of each standard node matched with the process node;

[0122] A known process path generation module 803 to be executed is used to generate a known process path to be executed based on the dependency relationship of each process node and the standard flow chart;

[0123] The intelligent business and process processing module 804 is used to perform business processing based on the process path to be executed and the known process path to be executed.

[0124] In one of the optional embodiments, the above-mentioned known process path generation module 803 to be executed is specifically used to determine whether there are missing necessary nodes based on the standard nodes matched by each process node and the dependency relationship of the standard nodes; if there are missing necessary nodes and the missing necessary nodes are unique, the known process path to be executed is generated based on the missing necessary nodes, the standard flowchart and each process node; if there are missing necessary nodes and the missing necessary nodes are not unique, the candidate nodes are determined based on the standard flowchart, and the target missing necessary nodes are determined from the candidate nodes based on the guided inquiry interaction method, and the known process path to be executed is generated based on the determined target missing necessary nodes, the standard flowchart and each process node; if there are no missing necessary nodes, the known process path to be executed is generated based on the standard flowchart and each process node.

[0125] In one of the optional embodiments, the above-mentioned device also includes: a first node determination module, which is used to obtain the first node of the known process path to be executed; determine whether the first node has a predecessor node based on the standard flowchart; if the first node has a predecessor node and there is no necessary parameter information corresponding to the predecessor node in the initial business operation description information, obtain the necessary parameter information corresponding to the predecessor node through a guided inquiry interaction method; update the first node of the known process path to be executed as a predecessor node; if the first node has a unique predecessor node and there is necessary parameter information corresponding to the predecessor node in the initial business operation description information, update the first node of the known process path to be executed as a predecessor node; if there are multiple predecessor nodes for the first node and the initial When necessary parameter information corresponding to the predecessor node does not exist in the business operation description information, the target predecessor node and necessary parameter information corresponding to the target predecessor node are determined through guided inquiry interaction based on multiple predecessor nodes, and the first node of the known process path to be executed is updated to be the target predecessor node; when there are multiple predecessor nodes of the first node, and necessary parameter information corresponding to the predecessor node does not exist in the initial business operation description information, based on obtaining the priorities of the multiple predecessor nodes, the first node of the known process path to be executed is updated to be the predecessor node with the highest priority, wherein the priority of the node is stored in the standard flowchart, and the step of determining whether there is a predecessor node for the first node based on the standard flowchart is continued until the first node has no predecessor node.

[0126] In one of the optional embodiments, the above-mentioned intelligent business and process processing module 804 is specifically used to execute each node in sequence based on the dependency relationship of each node in the known process path to be executed; when the status of the node is executed, skip the node; when the status of the node is not executed, execute the node through the interface tool, and after the execution is completed, modify the status of the node to executed.

[0127] In one of the optional embodiments, the above-mentioned intelligent business and process processing module 804 is specifically used to execute the node through the interface tool, and when the node is successfully executed, modify the node status to executed; execute the node through the interface tool, and when the node execution fails, collect the execution failure information, and based on the execution failure information, supplement the node information of the node through a guided inquiry interaction method, execute the node through the interface tool based on the supplemented node information, until the node is successfully executed, and modify the node status to executed.

[0128] In one of the optional embodiments, the intelligent business and process processing module 804 is specifically used to check the necessary parameter information of each node in the known process path to be executed; in the case where there are nodes that lack necessary parameter information, the necessary parameter information of the node is supplemented through active query interaction.

[0129] In one of the optional embodiments, the above-mentioned device also includes: a post-execution module, which is used to determine whether there is a post-node in the known process path to be executed based on the standard flowchart; when there is a unique post-node in the known process path to be executed, the necessary parameter information of the post-node is obtained through an active query interaction method, and the execution result of the post-node is obtained based on the necessary parameter information, and the post-node is used as the last node of the known process path to be executed; when there are multiple post-nodes in the known process path to be executed, the post-node selection information is output through a guided query interaction method, and when an ignore selection instruction is received, the post-node with the highest priority is selected as the first target post-node, and the necessary parameter information of the first target post-node is obtained. information, and obtain the execution result of the first target post-node based on the necessary parameter information, and use the first target post-node as the last node of the known process path to be executed; in the case that there are multiple post-nodes in the known process path to be executed, output the post-node selection information through a guided inquiry interaction method, and when receiving a confirmation instruction of the second target post-node, obtain the necessary parameter information of the second target post-node, and obtain the execution result of the second target post-node based on the necessary parameter information, and use the second target post-node as the last node of the known process path to be executed; continue to execute the step of determining whether there is a post-node in the known process path to be executed based on the standard flowchart until there is no post-node in the known process path to be executed or it is confirmed that the execution is terminated.

[0130] In one of the optional embodiments, the above-mentioned post-execution module is also used to obtain the target business description information corresponding to the other process nodes when the known process path to be executed is executed to the last node and other process node selection instructions are received; the executed known process path to be executed is used as the upper-level process, the target business operation description information is used as the initial business operation description information of the branch process, and the step of disassembling the initial business operation description information to obtain at least one process node is continued.

[0131] In one of the optional embodiments, the above-mentioned post-execution module is also used to jump to the last node of the known process path to be executed corresponding to the upper-level process after the execution of the known process path to be executed corresponding to the branch process is completed, and continue to execute the step of determining whether there is a post-node in the known process path to be executed based on the standard flowchart.

[0132] In one of the optional embodiments, the above-mentioned device also includes: a standard flowchart generation module, which is used to obtain historical business process information, and obtain the target process node based on the business process information, and decompose the target process node into operation type and operation object; establish the dependency relationship of each target process node based on the historical business process information, and configure the priority of each target process node based on the dependency relationship; generate a standard flowchart based on the target process node, operation type, operation object, dependency relationship and priority.

[0133] In one of the optional embodiments, the above-mentioned standard flowchart generation module is specifically used to determine the priority based on any one of the following methods: configuring a fixed priority of each target process node based on the dependency relationship; or configuring the initial priority of each target process node based on the dependency relationship, obtaining user habit information, and adjusting the initial priority based on the user habit information.

[0134] Each module in the above intelligent business and process processing device can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0135] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store standard flow charts. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent business and process processing method is realized.

[0136] Those skilled in the art will understand that Fig. 9The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0137] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0138] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0139] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0140] It should 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 analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0141] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0142] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0143] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An intelligent business and process processing method, characterized in that: The method comprises: Acquire initial business operation description information, and decompose the initial business operation description information to obtain at least one process node; Matching each of the process nodes with each standard node in the standard flow chart, and determining the dependency relationship of the process nodes based on the dependency relationship of each of the standard nodes matched with the process nodes; Based on the dependency relationship of each of the process nodes and the standard flow chart, generating a known process path to be executed; Performing business processing based on the known process path to be executed; The generating of a known process path to be executed based on the dependency relationship of each process node and the standard process diagram includes: Determining whether there is a missing necessary node based on the standard nodes matched by each of the process nodes and the dependency relationship of the standard nodes; In the case where the missing necessary node exists and the missing necessary node is unique, generating a known process path to be executed based on the missing necessary node, the standard flow chart and each of the process nodes; In the case where the missing necessary node exists and the missing necessary node is not unique, candidate nodes are determined based on the standard flowchart, and target missing necessary nodes are determined from the candidate nodes based on a guided inquiry interaction method, and known process paths to be executed are generated based on the determined target missing necessary nodes, the standard flowchart, and each of the process nodes; If there is no missing necessary node, generating a known process path to be executed based on the standard flow chart and each of the process nodes; The performing business processing based on the known process path to be executed includes: Based on the dependency relationship between the nodes in the known process path to be executed, execute each node in sequence; If the node is in the executed state, skip the node; When the state of the node is not executed, execute the node through the interface tool, and after the execution is completed, change the state of the node to executed; Executing the node through the interface tool and, after the execution is completed, modifying the state of the node to executed, includes: Executing the node through the interface tool, and if the node is successfully executed, changing the state of the node to executed; The node is executed through the interface tool, and in the event that the node fails to execute, information on the execution failure is collected, and based on the information on the execution failure, the node information of the node is supplemented through a guided inquiry interaction method, and the node is executed through the interface tool based on the supplemented node information until the node is successfully executed, and the node status is changed to executed.

2. The method according to claim 1, characterized in that: After generating the known process path to be executed based on the dependency relationship of each process node and the standard process diagram, the method further includes: Obtain the first node of the known process path to be executed; Determine whether the first node has a preceding node based on the standard flow chart; If the first node has the preceding node and the initial business operation description information does not contain necessary parameter information corresponding to the preceding node, obtain the necessary parameter information corresponding to the preceding node through a guided inquiry interaction; update the first node of the known process path to be executed to be the preceding node; If the first node has only one predecessor node, and the initial business operation description information contains necessary parameter information corresponding to the predecessor node, updating the first node of the known process path to be executed to be the predecessor node; In the case that there are multiple predecessor nodes for the first node, and the necessary parameter information corresponding to the predecessor node does not exist in the initial business operation description information, based on the multiple predecessor nodes, a target predecessor node and necessary parameter information corresponding to the target predecessor node are determined through a guided inquiry interaction method, and the first node of the known process path to be executed is updated to be the target predecessor node; In the case that there are multiple predecessor nodes of the first node, and the necessary parameter information corresponding to the predecessor node does not exist in the initial business operation description information, based on obtaining the priorities of the multiple predecessor nodes, updating the first node of the known process path to be executed to be the predecessor node with the highest priority, wherein the priority of the node is stored in the standard flow chart; Continue to execute the step of determining whether the first node has a predecessor node based on the standard flow chart until the first node has no predecessor node.

3. The method according to claim 1, characterized in that Before performing business processing based on the known process path to be executed, the method further includes: Checking the necessary parameter information of each node in the known process path to be executed; In the case where there is a node that lacks necessary parameter information, the necessary parameter information of the node is supplemented through an active query interaction.

4. The method according to claim 1, characterized in that: The method further comprises: Determine whether there is a post-node in the known process path to be executed based on the standard process diagram; In the case that there is a unique post-node in the known process path to be executed, necessary parameter information of the post-node is obtained through active query interaction, and the execution result of the post-node is obtained based on the necessary parameter information, and the post-node is used as the last node of the known process path to be executed; In the case where there are multiple post-nodes in the known process path to be executed, post-node selection information is output through a guided inquiry interaction mode, and in the case of receiving an ignore selection instruction, the post-node with the highest priority is selected as the first target post-node, and necessary parameter information of the first target post-node is obtained, and the execution result of the first target post-node is obtained based on the necessary parameter information, and the first target post-node is used as the last node of the known process path to be executed; In the case where there are multiple post-nodes in the known process path to be executed, post-node selection information is output through a guided inquiry interaction mode, and when a confirmation instruction of a second target post-node is received, necessary parameter information of the second target post-node is obtained, and an execution result of the second target post-node is obtained based on the necessary parameter information, and the second target post-node is used as the last node of the known process path to be executed; Continue to execute the step of determining whether there is a subsequent node in the known process path to be executed based on the standard flowchart until there is no subsequent node in the known process path to be executed or it is confirmed that the execution is terminated.

5. The method according to claim 4, characterized in that The method further comprises: When the known process path to be executed is executed to the last node and other process node selection instructions are received, the target business operation description information corresponding to the other process nodes is obtained; The known process path to be executed is used as the upper-level process, the target business operation description information is used as the initial business operation description information of the branch process, and the step of disassembling the initial business operation description information to obtain at least one process node is continued.

6. The method according to claim 5, characterized in that The method further comprises: After the execution of the known process path to be executed corresponding to the branch process is completed, jump to the last node of the known process path to be executed corresponding to the upper-level process, and continue to execute the step of determining whether there is a post-node in the known process path to be executed based on the standard flowchart.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Acquire historical business process information, obtain a target process node based on the business process information, and decompose the target process node into an operation type and an operation object; Establishing a dependency relationship between each of the target process nodes based on the historical business process information, and configuring a priority of each of the target process nodes based on the dependency relationship; A standard flow chart is generated based on the target process node, the operation type, the operation object, the dependency relationship and the priority.

8. The method according to claim 7, characterized in that The configuring the priority of each target process node based on the dependency relationship includes at least one of the following methods: Configuring a fixed priority of each of the target process nodes based on the dependency relationship; or The initial priority of each of the target process nodes is configured based on the dependency relationship, user habit information is obtained, and the initial priority is adjusted based on the user habit information.

9. An intelligent business and process processing device, characterized in that: The device comprises: A process node generation module, used to obtain initial business operation description information, and disassemble the initial business operation description information to obtain at least one process node; A matching module, used for matching each of the process nodes with each of the standard nodes in the standard flow chart, and determining the dependency relationship of the process nodes based on the dependency relationship of each of the standard nodes matched with the process nodes; A known process path generation module to be executed, used to generate a known process path to be executed based on the dependency relationship of each process node and the standard flow chart; An intelligent business and process processing module, used for performing business processing based on the known process path to be executed; The module for generating the known process path to be executed is specifically used to determine whether there is a missing necessary node based on the standard nodes matched by each process node and the dependency relationship of the standard nodes; if the missing necessary node exists and the missing necessary node is unique, the known process path to be executed is generated based on the missing necessary node, the standard flowchart and each process node; if the missing necessary node exists and the missing necessary node is not unique, the candidate node is determined based on the standard flowchart, and the target missing necessary node is determined from the candidate nodes based on a guided inquiry interaction method, and the known process path to be executed is generated based on the determined target missing necessary node, the standard flowchart and each process node; if the missing necessary node does not exist, the known process path to be executed is generated based on the standard flowchart and each process node; The intelligent business and process processing module is specifically used to execute each node in sequence based on the dependency relationship of each node in the known process path to be executed; if the status of the node is executed, skip the node; if the status of the node is not executed, execute the node through the interface tool, and after the execution is completed, modify the status of the node to executed; The intelligent business and process processing module is specifically used to execute the node through the interface tool, and when the node is successfully executed, modify the node status to executed; execute the node through the interface tool, and when the node fails to execute, collect execution failure information, and based on the execution failure information, supplement the node information of the node through a guided inquiry interaction method, execute the node through the interface tool based on the supplemented node information, until the node is successfully executed, and modify the node status to executed.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images