Decision support method and system based on large model technology

Abstract

The invention discloses a decision support method and system based on a large model technology. The method comprises the following steps: acquiring target business process data in a process of executing a target business and a plurality of target business nodes corresponding to the target business, and constructing a target business atlas according to the nodes and the process data; determining the similarity among the nodes through the map, and generating a target similarity matrix; evaluating a target importance score set and an automatic feasibility score set of each node from multiple dimensions; performing deep analysis on the business process data, the similarity matrix, the importance score set and the automatic feasibility score set by using a pre-trained target large model, and generating an optimization processing strategy for each node, including keeping an original state, deleting redundant nodes or performing node automatic configuration; and processing each target service node according to the optimization strategy. According to the invention, the technical problem of low efficiency caused by tedious service processing nodes when related services are processed is solved.

Description

Technical Field

[0001] The present application relates to the field of financial services technology, and in particular to a decision support method and system based on large model technology. Background Art

[0002] In the current business process management, with the increase in enterprise scale and business complexity, business nodes are becoming increasingly cumbersome, and modern enterprise business processes contain a large number of nodes, usually involving multiple departments and systems, and the dependencies between nodes are complex. At present, many business processes still rely on manual management and adjustment, especially in node optimization and resource allocation. There is a lack of automated tool support, and the data of different business nodes are scattered in various systems, which is difficult to integrate and analyze, limiting the global optimization of the overall process. Due to the excessive and complex business nodes, manual processing is prone to delays and errors, affecting the overall business efficiency. Traditional methods are difficult to effectively identify and eliminate unnecessary business nodes, resulting in waste of resources. In addition, existing technologies cannot dynamically adjust node configurations based on business data, and optimization strategies are mostly based on experience and lack scientific basis.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiment of the present application provides a decision support method and system based on large model technology, so as to at least solve the technical problem of low efficiency caused by cumbersome business processing nodes when processing related businesses.

[0005] According to one aspect of an embodiment of the present application, a decision support method based on big model technology is provided, including: obtaining target business process data and multiple target business nodes corresponding to the target business in the process of executing the target business, and constructing a target business graph based on the multiple target business nodes and the target business process data; determining the target similarity between each target business node based on the target business graph, and constructing a target similarity matrix based on each target similarity; determining a target importance score set corresponding to each target business node from multiple dimensions based on the target business graph, and determining a target automation feasibility score set corresponding to each target business node from multiple dimensions; using a pre-trained target big model to analyze the target business process data, the target similarity matrix, multiple target importance score sets, and multiple target automation feasibility score sets to obtain an optimization processing strategy for each target business node, wherein the optimization processing strategy includes at least one of the following: maintaining the original state, deleting redundant nodes, and node automation configuration; executing the corresponding optimization processing strategy for each target business node.

[0006] Optionally, target business process data and multiple target business nodes corresponding to the target business in the process of executing the target business are obtained, and a target business graph is constructed based on the multiple target business nodes and the target business process data, including: obtaining target business process data in the process of executing the target business, wherein the target business process data includes at least one of the following: operation logs, task records, processing timestamps, and resource allocation information; determining multiple target business nodes corresponding to the target business, and determining multi-dimensional target attribute information of each target business node and task dependency relationships between each target business node based on the target business process data, wherein the target attribute information includes at least one of the following: node name, number of executions, single execution time, single input data, single output data, preset node level, number of execution exceptions, and single resource consumption; constructing a target business graph corresponding to the target business based on each target business node and the corresponding target attribute information and task dependency relationships.

[0007] Optionally, the target similarity between each target business node is determined based on the target business graph, and a target similarity matrix is ​​constructed based on each target similarity, including: for every two target business nodes, respectively calculating the target sub-similarity between the target attribute information of the two target business nodes in each dimension; performing weighted summation of the target sub-similarity in multiple dimensions based on a preset weight coefficient to obtain the target similarity between the two target business nodes; and constructing a target similarity matrix based on the target similarity between each target business node.

[0008] Optionally, a target importance score set corresponding to each target business node is determined from multiple dimensions based on the target business graph, including: for each target business node, the number of executions, single execution time, preset node level, and single resource consumption of the target business node are obtained from the target business graph; the execution frequency score of the target business node is determined based on the number of executions; the average execution time of the target business node is determined based on the single execution time, and the efficiency score of the target business node is determined based on the average execution time; the average resource consumption of the target business node is determined based on the single resource consumption, and the target Cost scoring of a business node; determining an importance score of a target business node based on a preset node level; determining the in-degree and out-degree of a target business node based on a target business graph, and determining the in-degree score and out-degree score of the target business node based on the in-degree and out-degree, respectively; determining a centrality index of the target business node in the target business graph, wherein the centrality index includes at least one of the following: degree centrality index, closeness centrality index, betweenness centrality index; combining execution frequency score, efficiency score, cost score, importance score, in-degree score, out-degree score, and centrality index to obtain a target importance score set of the target business node.

[0009] Optionally, a target automation feasibility score set corresponding to each target business node is determined from multiple dimensions, including: for each target business node, determining the single input data, single output data, and number of execution exceptions of the target business node based on the target business graph; determining the input standardization score of the target business node based on the single input data; determining the processing logic rules of the target business node when executing the target business based on the single input data and the single output data, and determining the rule score of the target business node based on the processing logic rules; determining the abnormal risk score of the target business node based on the number of execution exceptions; and combining the input standardization score, rule score, and abnormal risk score to obtain a target automation feasibility score set for the target business node.

[0010] Optionally, the training process of the target big model includes: obtaining multiple groups of business process data corresponding to multiple businesses, and determining multiple business nodes corresponding to each business, and constructing a business graph for each business; for each business, determining the similarity matrix corresponding to the multiple business nodes of the business, the importance score set and the automation feasibility score set of each business node based on the business graph of the business; using the business process data, similarity matrix, multiple importance score sets and multiple automation feasibility score sets corresponding to the business as a training sample, and using the optimization processing strategy for the business as the corresponding sample label; constructing an initial big model, and using multiple training samples and sample labels to iteratively train the initial big model, and using the trained big model as the target big model.

[0011] Optionally, in the case where the optimization processing strategy is node automation configuration, the optimization processing strategy also includes an automation script generated by the target large model for the target business node to be automatically configured, wherein the automation script includes code instructions and process control logic required to implement the functions of the target business node; executing the corresponding optimization processing strategy on the target business node, including: adding the automation script to the target business node.

[0012] Optionally, according to another aspect of the embodiment of the present application, a decision support system based on big model technology is also provided, including: an acquisition module, used to acquire target business process data and multiple target business nodes corresponding to the target business in the process of executing the target business, and construct a target business graph based on multiple target business nodes and target business process data; a construction module, used to determine the target similarity between each target business node based on the target business graph, and construct a target similarity matrix based on each target similarity; a determination module, used to determine the target importance score set corresponding to each target business node from multiple dimensions based on the target business graph, and determine the target automation feasibility score set corresponding to each target business node from multiple dimensions; a strategy generation module, used to use a pre-trained target big model to analyze the target business process data, the target similarity matrix, multiple target importance score sets and multiple target automation feasibility score sets to obtain an optimization processing strategy for each target business node, wherein the optimization processing strategy includes at least one of the following: maintaining the original state, deleting redundant nodes, and node automation configuration; an execution module, used to execute the corresponding optimization processing strategy for each target business node.

[0013] According to another aspect of an embodiment of the present application, a computer program product is also provided, the computer program product comprising: a computer program, wherein when the computer program is executed by a processor, the above-mentioned decision support method based on large model technology is implemented.

[0014] According to another aspect of an embodiment of the present application, an electronic device is also provided, which includes: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned decision support method based on large model technology through the computer program.

[0015] In the embodiment of the present application, by acquiring the target business process data in the process of executing the target business and multiple target business nodes in the business process, a target business graph reflecting the business process structure and the relationship between nodes is constructed; based on the target business graph, the similarity between each business node is determined, and then a target similarity matrix is ​​constructed. This matrix can help identify repeated or similar links in the process and provide a basis for deleting redundant nodes; using the target business graph, the target importance score set of each business node is determined from multiple dimensions (such as execution frequency, efficiency, cost, etc.), and the automation feasibility score set is determined from different angles (such as input data standardization, processing logic regularization, abnormal risk, etc.); through the pre-trained target large model, the target business process data is trained. , target similarity matrix, target importance score set and automation feasibility score set for in-depth analysis. Based on its understanding and prediction ability of business processes, the big model can generate optimization processing strategies for each business node, such as maintaining status, deleting redundant nodes or automating node configuration. These strategies are data-driven and can maximize process efficiency and reduce costs. The analysis of the target big model provides data-driven optimization suggestions to help decision makers make more scientific and accurate process improvement decisions. By making decisions such as deleting redundant nodes and automating node configuration, manual operations are reduced, the execution time of business processes is further shortened, and the overall processing efficiency is improved, thereby solving the technical problem of inefficiency caused by cumbersome business processing nodes when processing related businesses. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 It is a flowchart of an optional decision support method based on large model technology according to an embodiment of the present application;

[0018] Figure 2 is a schematic diagram of the structure of an optional decision support system based on large model technology according to an embodiment of the present application;

[0019] Figure 3 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first", "second", etc. in the specification, claims and drawings of the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] The information collected in the embodiments of the present application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0023] Example 1

[0024] According to an embodiment of the present application, a decision support method based on big model technology is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 is a flow chart of a decision support method based on large model technology provided in an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0026] Step S102, obtaining target business process data and multiple target business nodes corresponding to the target business during the execution of the target business, and constructing a target business graph based on the multiple target business nodes and the target business process data;

[0027] Step S104, determining the target similarity between each target business node according to the target business graph, and constructing a target similarity matrix according to each target similarity;

[0028] Step S106, determining a target importance score set corresponding to each target business node from multiple dimensions according to the target business graph, and determining a target automation feasibility score set corresponding to each target business node from multiple dimensions;

[0029] Step S108, using the pre-trained target big model to analyze the target business process data, the target similarity matrix, multiple target importance score sets and multiple target automation feasibility score sets, to obtain an optimization processing strategy for each target business node, wherein the optimization processing strategy includes at least one of the following: maintaining the original state, deleting redundant nodes, and node automation configuration;

[0030] Step S110: executing a corresponding optimization processing strategy for each target service node.

[0031] The following describes the various steps of the decision support method based on large model technology in conjunction with the specific implementation process.

[0032] First, the target business process data and multiple target business nodes corresponding to the target business are obtained during the execution of the target business, and a target business graph is constructed based on the multiple target business nodes and the target business process data. The process can be carried out in the following steps:

[0033] Obtain target business process data in the process of executing the target business, wherein the target business process data includes at least one of the following: operation logs, task records, processing timestamps, and resource allocation information; determine multiple target business nodes corresponding to the target business, and determine multi-dimensional target attribute information of each target business node and task dependency relationships between each target business node based on the target business process data, wherein the target attribute information includes at least one of the following: node name, number of executions, single execution time, single input data, single output data, preset node level, number of execution exceptions, and single resource consumption; construct a target business graph corresponding to the target business based on each target business node and the corresponding target attribute information and task dependency relationships.

[0034] The acquired business process data may be business process data of executing the same business multiple times.

[0035] For example, in a bank processing system, the operation log records the operation records of account managers, approval personnel, etc. during the business processing process, including operation time, operation type, operation results, etc. Task records track the processing status of each business node, recording the start and end time of the task, task status (such as pending, completed, abnormal), task executor and other information. The processing timestamp accurately records the time points when each business node starts and completes processing, which helps to calculate the processing time of the node. Resource allocation information involves the resources consumed by each node during the execution process, including manpower, system resources, financial resources, etc., and is an important basis for evaluating node costs and efficiency.

[0036] A target business node refers to a step or link in the target business process that can be individually identified and analyzed. Taking credit business as an example, business nodes may include "customer information collection", "credit assessment", "loan approval", "contract signing", "loan disbursement", etc. Identifying these nodes and collecting relevant attribute information is the key to building a business graph. Attribute information may include but is not limited to: the name of each node, such as "customer credit assessment"; the total number of times each node is triggered, reflecting the activity of the node; the execution time of each node execution, used to evaluate efficiency and optimization points; the data type and format required before and after the node execution, as well as the output results generated; levels preset according to the importance and risk level of the node, such as 1 to 5, etc.

[0037] For a single business, depending on the design of the business process and the needs of the specific business scenario, in some standardized and automated business processes, a business node of the business may be designed to be executed only once to ensure the consistency and efficiency of the business process and avoid repeated operations and waste of resources. For example, in a loan approval business process, the "credit assessment" node may be set to be executed only once after the loan application is submitted to generate a customer's credit report. This step is critical and unique in the process, ensuring the accuracy and timeliness of the credit assessment. However, in complex business processes or certain specific conditions, a business node may need to be executed multiple times. This usually occurs in scenarios that require cyclic processing or adjustment of processing logic according to business status. For example, in post-loan management, the "repayment monitoring" node may need to be executed repeatedly on a regular basis to check the repayment status of loan customers and ensure the normal recovery of loans. In customer consultation or complaint processing, the "customer service response" node may need to be executed multiple times until the customer's problem is completely resolved.

[0038] By analyzing operation logs and task records, we can identify the dependencies between nodes in the business process. For example, in the credit business, "customer information collection" may need to be completed before "loan approval", and "loan approval" depends on the results of "credit assessment". The identification of such dependencies is crucial to building a correct business process map, ensuring the accuracy and practicality of the map.

[0039] After obtaining the target business graph, the target similarity between each target business node is determined according to the target business graph, and a target similarity matrix is ​​constructed according to each target similarity. The process can be carried out in the following steps:

[0040] For every two target business nodes, the target sub-similarity between the target attribute information of the two target business nodes in each dimension is calculated respectively; the target sub-similarity in multiple dimensions is weighted and summed according to the preset weight coefficient to obtain the target similarity between the two target business nodes; and a target similarity matrix is ​​constructed based on the target similarity between each target business node.

[0041] The most suitable similarity calculation method can be selected according to the nature of the target attribute information and business needs. For example, for discrete attributes such as node names, Jaccard similarity may be used. The setting of weight coefficients is a key step, which determines the bias of similarity calculation. The weight coefficients can be set based on expert experience or automatically determined through machine learning methods such as principal component analysis or feature selection algorithms.

[0042] After obtaining the target business graph, determine the target importance score set corresponding to each target business node from multiple dimensions based on the target business graph, and determine the target automation feasibility score set corresponding to each target business node from multiple dimensions. This process can be carried out in the following steps:

[0043] For each target business node, the number of executions, single execution time, preset node level, and single resource consumption of the target business node are obtained from the target business graph;

[0044] Determine the execution frequency score of the target business node based on the number of executions;

[0045] For example, business node A is for customer information review, and business node B is for loan amount calculation. In a single loan approval process, node A may be triggered multiple times because in complex processes such as loan approval, the information submitted by the customer may need to go through multiple rounds of review to ensure the accuracy and completeness of the information. For example, the initial review may require checking basic information and then resubmitting specific details for review, or customer information may need to be reviewed at different stages of the loan (such as application, loan issuance, and post-loan management). In contrast, node B may only be triggered once in the process to determine the customer's loan amount.

[0046] To calculate the execution frequency score, you can find the node with the most execution times among all nodes and record its execution times as a reference value. Then compare the execution times of the current node with the reference value, calculate a ratio value, and finally convert this ratio value into a percentage score. The more times a node is executed, the higher its execution frequency score.

[0047] Determine the average execution time of the target business node based on the single execution time, and determine the efficiency score of the target business node based on the average execution time;

[0048] For example, use multiple single execution times to calculate the average execution time, find the node with the shortest average execution time among all nodes, and record its execution time as a reference value. Then compare the reference value with the average execution time of the current node, calculate a ratio value, and finally convert this ratio value into a percentage score. The shorter the single execution time of the node, the higher its efficiency score.

[0049] Determine the average resource consumption of the target business node based on the single resource consumption, and determine the cost score of the target business node based on the average resource consumption;

[0050] For example, count the average amount of resources (such as memory, network bandwidth, etc.) consumed by the node each time it is executed, find the node with the lowest average resource consumption among all nodes, and record its average resource consumption as a reference value. Then compare the reference value with the single resource consumption of the current node, calculate a ratio value, and finally convert this ratio value into a percentage score. The node with less average resource consumption has a higher cost score.

[0051] Determine the importance score of the target business node based on the preset node level;

[0052] For example, when designing a business process, each node will be pre-evaluated and assigned a grade. This grade is based on the importance and complexity of the node in the process. A node directly involved in financial transactions may be assigned a higher grade, while some pure document processing nodes may have a lower grade. According to the grade of the node, a scoring range can be set. For example, a high-level node can be set to 80 to 100 points, a medium-level node to 50 to 80 points, and a low-level node to 0 to 50 points. The specific score can be adjusted within the set range according to the grade of the node.

[0053] Determine the in-degree and out-degree of the target business node according to the target business graph, and determine the in-degree score and out-degree score of the target business node according to the in-degree and out-degree respectively;

[0054] The in-degree indicates how many nodes point to the current node, that is, the number of times the current node is a prerequisite for subsequent nodes. The in-degree score reflects the "dependency" of the node, that is, how many other nodes' work results will enter the node. The out-degree indicates how many other nodes the current node points to, that is, how many other nodes the current node's work results are a prerequisite for. The out-degree score reflects the "influence" of the node, that is, the degree of influence of the node on subsequent processes. The in-degree and out-degree scores can be determined based on the number of in-degrees and out-degrees of the node in the graph. For example, the higher the number of in-degrees and out-degrees, the higher the score; otherwise, the lower the score.

[0055] For the in-degree score, you can refer to the following calculation method: find the node with the highest in-degree among all nodes, and record its in-degree value as a reference value, compare the in-degree of the current node with the reference value, calculate a ratio value, and finally convert this ratio value into a percentage score. The higher the in-degree of the node, the higher its in-degree score. This means that the node is relied on by more other nodes and plays a more important role in the business process. For the out-degree score, you can refer to the following calculation method: find the node with the highest out-degree among all nodes, and record its out-degree value as a reference value, compare the out-degree of the current node with the reference value, calculate a ratio value, and finally convert this ratio value into a percentage score. The higher the out-degree of the node, the higher its out-degree score, which indicates that the node has a stronger connection with other nodes and plays a more complex role in the business process.

[0056] Determine the centrality index of the target business node in the target business graph, wherein the centrality index includes at least one of the following: degree centrality index, closeness centrality index, betweenness centrality index; combine the execution frequency score, efficiency score, cost score, importance score, in-degree score, out-degree score, and centrality index to obtain a target importance score set of the target business node.

[0057] For example, the degree centrality index represents the direct connection degree of a node, that is, the number of other nodes directly associated with the node. A node with high degree centrality has more direct connections in the graph, indicating that it plays a core role in the process. The closeness centrality index reflects the "centrality" of the node in the graph, that is, the average shortest path length between the node and other nodes in the entire graph. A node with high closeness centrality means that it is in a "central position" in the graph and can interact with other nodes in the graph quickly and effectively. The betweenness centrality index measures the frequency of a node as an intermediate node in the shortest path between other nodes in the graph. Nodes with high betweenness centrality play the role of a "bridge" in the graph and have an important impact on information flow.

[0058] For the degree centrality index, you can refer to the following calculation method: in the business graph, count the number of direct connections (i.e., degree) between the current node and other nodes, find the node with the highest degree among all nodes, and record its degree as a reference value, compare the degree of the current node with the reference value, calculate a ratio value, and finally convert this ratio value into a percentage score. The higher the degree of the node, the higher its degree centrality score, which indicates that the node has more direct connections with other nodes in the business process.

[0059] For the closeness centrality index, you can refer to the following calculation method: in the business graph, calculate the shortest path length from the current node to all other nodes, and find the average of these path lengths, find the node with the smallest average shortest path length among all nodes, and record its average path length as a reference value, compare the reference value with the average shortest path length of the current node, calculate a ratio value, and finally convert this ratio value into a percentage score. The shorter the average shortest path length of the node, the higher its closeness centrality score, which indicates that the node is easier to reach other nodes in the business process.

[0060] For the betweenness centrality index, you can refer to the following calculation method: in the business graph, count the number of times the current node acts as an "intermediary" in all shortest paths between other nodes, find the node with the highest betweenness centrality value among all nodes, and record its betweenness centrality value as a reference value, compare the betweenness centrality value of the current node with the reference value, calculate a ratio value, and finally convert this ratio value into a percentage score. The higher the betweenness centrality value of the node, the higher its betweenness centrality score, which indicates that the node plays a more important bridge role in the business process.

[0061] As an optional implementation method, the target automation feasibility score set corresponding to each target business node is determined from multiple dimensions, and the following steps can be taken: for each target business node, the single input data, single output data, and number of execution exceptions of the target business node are determined based on the target business graph; the input standardized score of the target business node is determined based on the single input data; the processing logic rules of the target business node when executing the target business are determined based on the single input data and the single output data, and the rule score of the target business node is determined based on the processing logic rules; the abnormal risk score of the target business node is determined based on the number of execution exceptions; the input standardized score, rule score, and abnormal risk score are combined to obtain the target automation feasibility score set of the target business node.

[0062] In the business process map, each node has its specific input and output data format and type. Single input data refers to the entire data set received by the node when processing a specific business, and single output data refers to the output result set after the node is processed. These data may include customer information, transaction records, approval status, risk assessment results, etc. The format and content consistency of input data are crucial to automation. If the input data of a node can follow a unified structure and template in most cases, then the node has a higher input standardization score, which means it is easier to be automated. For standardized scoring, you can refer to the following calculation method: define a standard template or rule for input data (for example, whether the data field is complete, whether the data type matches, etc.), check the degree of match between each input data and the standard template, and assign a score based on the degree of match. For example: if it is completely matched, the score is 100, if it is partially matched, the score is calculated based on the matching ratio (such as 80% match, the score is 80), if it is completely unmatched, the score is 0.

[0063] The processing logic rules of a point determine whether it can be accurately converted into an automated processing strategy. The higher the score of a clear and definable rule, the greater the feasibility of automated implementation. The rule score is determined as follows: Rule clarity: Analyze the processing logic of the node to check whether it is based on a predefined rule set and whether the rule description is detailed and clear. Evaluate the complexity of the node processing logic, including the number of rules, their dependencies, and the handling of exceptions. Examine whether the node processing logic remains stable over a long period of time. Frequently changing rules will reduce the feasibility of automation. The calculation of the rule score can be based on a comprehensive consideration of the above three dimensions. The rule clarity, rule complexity, and rule stability are quantified into scores and then weighted averaged.

[0064] The number of abnormalities reflects the probability of problems that may occur after the node is automated. The more abnormalities there are, the lower the abnormality risk score is. The abnormality risk score can be calculated as follows: count the total number of executions and abnormalities of the node, compare the number of abnormalities of the current node with the total number of executions, calculate a ratio value, and finally convert this ratio value into a percentage score.

[0065] After obtaining the target similarity matrix, multiple target importance score sets and multiple target automation feasibility score sets, the target business process data, the target similarity matrix, multiple target importance score sets and multiple target automation feasibility score sets are analyzed using the pre-trained target big model to obtain an optimization processing strategy for each target business node, wherein the optimization processing strategy includes at least one of the following: maintaining the original state, deleting redundant nodes, and automating node configuration.

[0066] Among them, as an optional implementation method, the training process of the target big model can be carried out in the following steps: obtain multiple groups of business process data corresponding to multiple businesses, and determine multiple business nodes corresponding to each business, and build a business graph for each business; for each business, determine the similarity matrix corresponding to the multiple business nodes of the business, the importance score set and the automation feasibility score set of each business node based on the business graph of the business; use the business process data, similarity matrix, multiple importance score sets and multiple automation feasibility score sets corresponding to the business as a training sample, and use the optimization processing strategy for the business as the corresponding sample label; build an initial big model, and use multiple training samples and sample labels to iteratively train the initial big model, and use the trained big model as the target big model.

[0067] After obtaining the optimization processing strategy for each service node, the corresponding optimization processing strategy is executed on each target service node.

[0068] As an optional implementation, when the optimization processing strategy is node automation configuration, the optimization processing strategy also includes an automation script generated by the target large model for the target business node to be automatically configured, wherein the automation script includes the code instructions and process control logic required to implement the functions of the target business node; executing the corresponding optimization processing strategy on the target business node, including: adding the automation script to the target business node.

[0069] For example, the target big model analyzes the target similarity matrix, target importance score set, target automation feasibility score set based on its understanding of the business process, and outputs the optimization processing strategy. For the automated configuration, the model generates an automated script containing code instructions and process control logic to implement the node function, taking into account other nodes in the business process and potential exception handling mechanisms. The generation of the automated script depends on the specific needs analysis of the target business node. The big model automatically generates the corresponding code instructions based on the input data, processing logic, and output data of the node. For example, if the node needs to process data standardization and format conversion, the script will contain data cleaning and conversion code; if the node involves decision analysis, the script will include rule-based decision logic or machine learning model calls.

[0070] Based on the policy output of the target big model, a detailed implementation plan can be determined, including the schedule, resource allocation and responsible personnel, to deploy automation scripts in the production environment, activate automation nodes, monitor the operating status and performance indicators of the nodes, and for nodes identified as redundant, perform node deletion operations and simplify the process based on the redesign of business processes. After removing redundant nodes and activating automation nodes, re-evaluate and adjust the entire business process to ensure the continuity and efficiency of the process.

[0071] Based on these indicators, banks can evaluate the effectiveness of optimization strategies and make adjustments as needed. For example, they can regularly collect performance data of business processes and compare it with the baseline data before optimization, collect customer satisfaction feedback on process improvements, understand the impact of automated processing on customer experience, regularly review business processes, identify new optimization opportunities or revise implemented strategies, and adjust automation scripts based on monitoring results and customer feedback to optimize business processes and ensure the continued effectiveness and adaptability of strategies.

[0072] In the embodiment of the present application, by acquiring the target business process data in the process of executing the target business and multiple target business nodes in the business process, a target business graph reflecting the business process structure and the relationship between nodes is constructed; based on the target business graph, the similarity between each business node is determined, and then a target similarity matrix is ​​constructed. This matrix can help identify repeated or similar links in the process and provide a basis for deleting redundant nodes; using the target business graph, the target importance score set of each business node is determined from multiple dimensions (such as execution frequency, efficiency, cost, etc.), and the automation feasibility score set is determined from different angles (such as input data standardization, processing logic regularization, abnormal risk, etc.); through the pre-trained target large model, the target business process data is trained. , target similarity matrix, target importance score set and automation feasibility score set for in-depth analysis. Based on its understanding and prediction ability of business processes, the big model can generate optimization processing strategies for each business node, such as maintaining status, deleting redundant nodes or automating node configuration. These strategies are data-driven and can maximize process efficiency and reduce costs. The analysis of the target big model provides data-driven optimization suggestions to help decision makers make more scientific and accurate process improvement decisions. By making decisions such as deleting redundant nodes and automating node configuration, manual operations are reduced, the execution time of business processes is further shortened, and the overall processing efficiency is improved, thereby solving the technical problem of inefficiency caused by cumbersome business processing nodes when processing related businesses.

[0073] Example 2

[0074] According to the embodiment of the present application, a decision support system based on large model technology is also provided for implementing the decision support method based on large model technology in embodiment 1, such as Figure 2 As shown, the decision support system based on the large model technology at least includes: an acquisition module 21, a construction module 22, a determination module 23, a strategy generation module 24 and an execution module 25, wherein:

[0075] An acquisition module 21 is used to acquire target business process data and a plurality of target business nodes corresponding to the target business during the execution of the target business, and to construct a target business graph according to the plurality of target business nodes and the target business process data;

[0076] A construction module 22, used to determine the target similarity between each of the target service nodes according to the target service graph, and to construct a target similarity matrix according to each of the target similarities;

[0077] A determination module 23, configured to determine a target importance score set corresponding to each target business node from multiple dimensions based on the target business graph, and to determine a target automation feasibility score set corresponding to each target business node from multiple dimensions;

[0078] The strategy generation module 24 is used to analyze the target business process data, the target similarity matrix, multiple target importance score sets and multiple target automation feasibility score sets using the pre-trained target big model to obtain an optimization processing strategy for each target business node, wherein the optimization processing strategy includes at least one of the following: maintaining the original state, deleting redundant nodes, and automatically configuring nodes;

[0079] The execution module 25 is used to execute the corresponding optimization processing strategy for each target service node.

[0080] The following describes the functions of each module of the decision support system based on large model technology in conjunction with the specific implementation process.

[0081] First, the acquisition module acquires the target business process data and multiple target business nodes corresponding to the target business during the execution of the target business, and constructs a target business graph based on multiple target business nodes and target business process data. The process can be carried out in the following steps:

[0082] Obtain target business process data in the process of executing the target business, wherein the target business process data includes at least one of the following: operation logs, task records, processing timestamps, and resource allocation information; determine multiple target business nodes corresponding to the target business, and determine multi-dimensional target attribute information of each target business node and task dependency relationships between each target business node based on the target business process data, wherein the target attribute information includes at least one of the following: node name, number of executions, single execution time, single input data, single output data, preset node level, number of execution exceptions, and single resource consumption; construct a target business graph corresponding to the target business based on each target business node and the corresponding target attribute information and task dependency relationships.

[0083] After obtaining the target business graph, the construction module determines the target similarity between each target business node according to the target business graph, and constructs a target similarity matrix according to each target similarity. The process can be carried out in the following steps:

[0084] For every two target business nodes, the target sub-similarity between the target attribute information of the two target business nodes in each dimension is calculated respectively; the target sub-similarity in multiple dimensions is weighted and summed according to the preset weight coefficient to obtain the target similarity between the two target business nodes; and a target similarity matrix is ​​constructed based on the target similarity between each target business node.

[0085] After obtaining the target business graph, the determination module determines the target importance score set corresponding to each target business node from multiple dimensions based on the target business graph, and determines the target automation feasibility score set corresponding to each target business node from multiple dimensions. This process can be carried out in the following steps:

[0086] For each target business node, the number of executions, single execution time, preset node level, and single resource consumption of the target business node are obtained from the target business graph; the execution frequency score of the target business node is determined based on the number of executions; the average execution time of the target business node is determined based on the single execution time, and the efficiency score of the target business node is determined based on the average execution time; the average resource consumption of the target business node is determined based on the single resource consumption, and the cost score of the target business node is determined based on the average resource consumption; the importance score of the target business node is determined based on the preset node level; the in-degree and out-degree of the target business node are determined based on the target business graph, and the in-degree score and out-degree score of the target business node are determined based on the in-degree and out-degree, respectively; the centrality index of the target business node in the target business graph is determined, wherein the centrality index includes at least one of the following: degree centrality index, closeness centrality index, betweenness centrality index; the execution frequency score, efficiency score, cost score, importance score, in-degree score, out-degree score, and centrality index are combined to obtain a target importance score set of the target business node.

[0087] As an optional implementation method, the target automation feasibility score set corresponding to each target business node is determined from multiple dimensions, and the following steps can be taken: for each target business node, the single input data, single output data, and number of execution exceptions of the target business node are determined based on the target business graph; the input standardized score of the target business node is determined based on the single input data; the processing logic rules of the target business node when executing the target business are determined based on the single input data and the single output data, and the rule score of the target business node is determined based on the processing logic rules; the abnormal risk score of the target business node is determined based on the number of execution exceptions; the input standardized score, rule score, and abnormal risk score are combined to obtain the target automation feasibility score set of the target business node.

[0088] After obtaining the target similarity matrix, multiple target importance score sets and multiple target automation feasibility score sets, the strategy generation module uses the pre-trained target large model to analyze the target business process data, the target similarity matrix, multiple target importance score sets and multiple target automation feasibility score sets to obtain an optimization processing strategy for each target business node, wherein the optimization processing strategy includes at least one of the following: maintaining the original state, deleting redundant nodes, and automating node configuration.

[0089] Among them, as an optional implementation method, the training process of the target big model can be carried out in the following steps: obtain multiple groups of business process data corresponding to multiple businesses, and determine multiple business nodes corresponding to each business, and build a business graph for each business; for each business, determine the similarity matrix corresponding to the multiple business nodes of the business, the importance score set and the automation feasibility score set of each business node based on the business graph of the business; use the business process data, similarity matrix, multiple importance score sets and multiple automation feasibility score sets corresponding to the business as a training sample, and use the optimization processing strategy for the business as the corresponding sample label; build an initial big model, and use multiple training samples and sample labels to iteratively train the initial big model, and use the trained big model as the target big model.

[0090] After obtaining the optimization processing strategy for each service node, the execution module executes the corresponding optimization processing strategy for each target service node.

[0091] As an optional implementation, when the optimization processing strategy is node automation configuration, the optimization processing strategy also includes an automation script generated by the target large model for the target business node to be automatically configured, wherein the automation script includes the code instructions and process control logic required to implement the functions of the target business node; executing the corresponding optimization processing strategy on the target business node, including: adding the automation script to the target business node.

[0092] It should be noted that each module in the decision support system based on big model technology in the embodiment of the present application corresponds one by one to each implementation step of the decision support method based on big model technology in Example 1. Since a detailed description has been given in Example 1, some details not reflected in this embodiment can be referred to Example 1 and will not be repeated here.

[0093] Example 3

[0094] According to an embodiment of the present application, a computer program product is also provided, which includes a computer program, wherein when the computer program is executed by a processor, the decision support method based on the large model technology in Example 1 is implemented.

[0095] According to an embodiment of the present application, a non-volatile storage medium is also provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the decision support method based on large model technology in Example 1 by running the computer program.

[0096] According to an embodiment of the present application, a processor is also provided, which is used to run a computer program, wherein the decision support method based on the large model technology in Example 1 is executed when the computer program is running.

[0097] According to an embodiment of the present application, an electronic device is also provided, which includes: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the decision support method based on large model technology in Example 1 through the computer program.

[0098] Specifically, the computer program executes the following steps when it is running: obtaining target business process data and multiple target business nodes corresponding to the target business in the process of executing the target business, and constructing a target business graph based on the multiple target business nodes and the target business process data; determining the target similarity between each target business node based on the target business graph, and constructing a target similarity matrix based on each target similarity; determining a target importance score set corresponding to each target business node from multiple dimensions based on the target business graph, and determining a target automation feasibility score set corresponding to each target business node from multiple dimensions; using a pre-trained target large model to analyze the target business process data, the target similarity matrix, multiple target importance score sets, and multiple target automation feasibility score sets, to obtain an optimization processing strategy for each target business node, wherein the optimization processing strategy includes at least one of the following: maintaining the original state, deleting redundant nodes, and node automation configuration; executing the corresponding optimization processing strategy for each target business node.

[0099] As an optional implementation, the electronic device may be in the form of a mobile terminal, a computer terminal or a similar computing device. Figure 3 FIG. 1 shows a hardware structure block diagram of an electronic device for implementing a decision support method based on a large model technology. Figure 3 As shown, the electronic device 30 may include one or more (302a, 302b, ..., 302n are used to illustrate) processors 302 (the processor 302 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 304 for storing data, and a transmission device 306 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components as shown, or with Figure 3 Different configurations shown.

[0100] It should be noted that the one or more processors 302 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the electronic device 30. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0101] The memory 304 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the decision support method based on the large model technology in the embodiment of the present application. The processor 302 executes various functional applications and data processing by running the software programs and modules stored in the memory 304, that is, realizing the vulnerability detection method of the above-mentioned application. The memory 304 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 304 may further include a memory remotely arranged relative to the processor 302, and these remote memories may be connected to the electronic device 30 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0102] The transmission device 306 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the electronic device 30. In one example, the transmission device 306 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 306 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0103] The display may be, for example, a touch screen liquid crystal display (LCD) that may enable a user to interact with a user interface of the electronic device 30 .

[0104] The serial numbers of the above embodiments are only for description and do not represent the advantages or disadvantages of the embodiments.

[0105] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0106] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0107] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0108] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0109] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0110] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A decision support method based on large model technology, characterized in that: include: Acquire target business process data and multiple target business nodes corresponding to the target business during the execution of the target business, and construct a target business graph based on the multiple target business nodes and the target business process data; Determine the target similarity between each of the target service nodes according to the target service graph, and construct a target similarity matrix according to each of the target similarities; Determine a target importance score set corresponding to each target business node from multiple dimensions according to the target business graph, and determine a target automation feasibility score set corresponding to each target business node from multiple dimensions; The target business process data, the target similarity matrix, a plurality of target importance score sets and a plurality of target automation feasibility score sets are analyzed by using a pre-trained target big model to obtain an optimization processing strategy for each target business node, wherein the optimization processing strategy includes at least one of the following: maintaining the original state, deleting redundant nodes, and automatically configuring nodes; A corresponding optimization processing strategy is executed on each of the target service nodes.

2. The method according to claim 1, characterized in that Obtaining target business process data and multiple target business nodes corresponding to the target business during the execution of the target business, and constructing a target business graph based on the multiple target business nodes and the target business process data, including: Acquire target business process data in the process of executing the target business, wherein the target business process data includes at least one of the following: operation log, task record, processing timestamp, resource allocation information; Determine multiple target business nodes corresponding to the target business, and determine multi-dimensional target attribute information of each target business node and the task dependency relationship between each target business node based on the target business process data, wherein the target attribute information includes at least one of the following: node name, number of executions, single execution time, single input data, single output data, preset node level, number of execution exceptions, and single resource consumption; The target business graph corresponding to the target business is constructed based on each of the target business nodes and the corresponding target attribute information and the task dependency relationship.

3. The method according to claim 2, characterized in that Determining target similarities between the target service nodes according to the target service graph, and constructing a target similarity matrix according to the target similarities, including: For every two target service nodes, respectively calculate the target sub-similarity between the target attribute information of the two target service nodes in each dimension; Performing weighted summation on the target sub-similarity under multiple dimensions according to a preset weight coefficient to obtain the target similarity between the two target service nodes; The target similarity matrix is ​​constructed according to the target similarities between the target service nodes.

4. The method according to claim 2, characterized in that: Determining a target importance score set corresponding to each target business node from multiple dimensions according to the target business graph includes: For each target service node, the number of executions, single execution time, preset node level, and single resource consumption of the target service node are obtained from the target service graph; Determining an execution frequency score of the target service node according to the number of executions; Determining an average execution time of the target service node according to the single execution time, and determining an efficiency score of the target service node according to the average execution time; Determining an average resource consumption of the target service node according to the single resource consumption, and determining a cost score of the target service node according to the average resource consumption; Determining the importance score of the target service node according to the preset node level; Determine the in-degree and out-degree of the target business node according to the target business graph, and determine the in-degree score and out-degree score of the target business node according to the in-degree and out-degree respectively; Determine a centrality index of the target service node in the target service graph, wherein the centrality index includes at least one of the following: a degree centrality index, a closeness centrality index, and a betweenness centrality index; The execution frequency score, efficiency score, cost score, importance score, in-degree score, out-degree score, and centrality index are combined to obtain a target importance score set of the target business node.

5. The method according to claim 2, characterized in that: Determine a target automation feasibility score set corresponding to each target business node from multiple dimensions, including: For each target service node, determine the single input data, single output data, and execution exception times of the target service node according to the target service graph; Determining an input standardized score of the target service node based on the single input data; Determine a processing logic rule of the target service node when executing the target service according to the single input data and the single output data, and determine a rule score of the target service node according to the processing logic rule; Determining an abnormality risk score of the target service node according to the number of execution abnormalities; The input standardized score, rule score, and abnormal risk score are combined to obtain a target automation feasibility score set for the target business node.

6. The method according to claim 1, characterized in that The training process of the target large model includes: Obtain multiple groups of business process data corresponding to multiple businesses, determine multiple business nodes corresponding to each business, and build a business graph for each business; For each business, determine, based on the business graph of the business, a similarity matrix corresponding to multiple business nodes of the business, an importance score set of each business node, and an automation feasibility score set; The business process data, similarity matrix, multiple importance score sets and multiple automation feasibility score sets corresponding to the business are used as a training sample, and the optimization processing strategy for the business is used as the corresponding sample label; An initial large model is constructed, and the initial large model is iteratively trained using a plurality of the training samples and sample labels, and the trained large model is used as the target large model.

7. The method according to claim 1, characterized in that In the case where the optimization processing strategy is node automatic configuration, the optimization processing strategy also includes an automation script generated by the target large model for the target business node to be automatically configured, wherein the automation script includes code instructions and process control logic required to implement the functions of the target business node; Executing a corresponding optimization processing strategy on the target service node includes: adding the automation script to the target service node.

8. A decision support system based on large model technology, characterized in that: include: An acquisition module, used to acquire target business process data and multiple target business nodes corresponding to the target business during the execution of the target business, and to construct a target business graph based on the multiple target business nodes and the target business process data; A construction module, used to determine the target similarity between each of the target business nodes according to the target business graph, and to construct a target similarity matrix according to each of the target similarities; A determination module, used to determine a target importance score set corresponding to each target business node from multiple dimensions based on the target business graph, and to determine a target automation feasibility score set corresponding to each target business node from multiple dimensions; A strategy generation module is used to analyze the target business process data, the target similarity matrix, multiple target importance score sets and multiple target automation feasibility score sets using a pre-trained target big model to obtain an optimization processing strategy for each target business node, wherein the optimization processing strategy includes at least one of the following: maintaining the original state, deleting redundant nodes, and automatically configuring nodes; The execution module is used to execute the corresponding optimization processing strategy for each target service node.

9. A computer program product, characterized in that include: A computer program, wherein when the computer program is executed by a processor, the decision support method based on large model technology described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the decision support method based on large model technology as described in any one of claims 1 to 7 through the computer program.

Images