Collaborative process intelligent auxiliary approval method and system based on dynamic risk modeling

Abstract

The invention relates to the technical field of intelligent auxiliary approval, in particular to a collaborative process intelligent auxiliary approval method and system based on dynamic risk modeling, and the method comprises the steps: obtaining a delay factor of each approval role type node according to the difference between all approval durations of each approval role type node in all structure trees and a reference approval duration; obtaining an overall delay factor of each approval task according to the delay factor and the weight coefficient; mapping all approval tasks in the history in the risk feature space to obtain a plurality of data points; clustering all data points in the risk feature space to obtain a plurality of class clusters; and according to the distance between each point to be analyzed and the center points of all the class clusters and the distance between the center points of the class clusters and the original point, obtaining an abnormal risk factor of each point to be analyzed so as to obtain a priority, and performing approval through the priority. According to the invention, the efficiency and fluency of intelligent auxiliary approval are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent auxiliary approval, and in particular to a collaborative process intelligent auxiliary approval method and system based on dynamic risk modeling. BACKGROUND

[0002] At present, with the increase of enterprise scale and business complexity, traditional approval processes have significant defects in efficiency and risk management. Many enterprises still rely on manual approval, resulting in cumbersome and time-consuming approval processes, poor information transmission, and even errors due to human factors. In addition, existing approval systems are mostly based on rule engines, which have improved automation but lack real-time dynamic risk assessment and response mechanisms, and cannot flexibly respond to external environmental changes (such as policy changes, market fluctuations, etc.) and complex situations that occur during the approval process.

[0003] Especially in multi-department collaborative approval processes, coordination and communication between each link still rely on manual operation, which is prone to poor communication, delayed approval, and other problems. While traditional intelligent approval systems can improve efficiency, their fixed approval rules and processes are difficult to adapt to rapidly changing risk environments, resulting in a lack of flexibility and accuracy in decision-making. Therefore, developing an intelligent auxiliary approval method based on dynamic risk modeling can optimize the approval process according to real-time risk changes and effectively coordinate the collaborative work between departments, which is an urgent need to improve approval efficiency and reduce approval risks. SUMMARY

[0004] The present application provides a collaborative process intelligent auxiliary approval method and system based on dynamic risk modeling to solve the problems of low efficiency, lack of dynamic risk assessment, and poor coordination in existing approval processes.

[0005] The object of the present application can be achieved by the following technical solutions: The first aspect of the present application is to provide a collaborative process intelligent auxiliary approval method based on dynamic risk modeling, comprising: constructing a tree structure for each approval task to obtain a structure tree for each approval task; obtaining all historical data of the approval task; the historical data includes approval duration, number of modifications; obtaining a delay factor for each approval role type node according to the difference between all approval durations of each approval role type node in all structure trees and a reference approval duration; determining the task type in each approval task, and determining the importance of each node through the task type; obtaining the weight coefficient of each node according to the importance of each node and the level corresponding to each node; obtaining the overall delay factor of each approval task according to the delay factor and the weight coefficient; obtaining compliance risk and legal risk of each approval task in the structure tree; linearly normalizing the amount in the financial risk, the compliance risk, the legal risk and the modification times to obtain a financial risk factor, a compliance risk factor, a legal risk factor and a modification factor, constructing a risk feature space through the overall delay factor, the financial risk factor, the compliance risk factor, the legal risk factor and the modification factor; mapping all the approval tasks in the history in the risk feature space to obtain a plurality of data points; clustering all the data points in the risk feature space to obtain a plurality of clusters; mapping all the current approval tasks in the risk feature space to obtain a plurality of to-be-analyzed points; obtaining an abnormal risk factor of each to-be-analyzed point according to the distance between each to-be-analyzed point and all cluster center points and the distance between the cluster center points and the origin; determining the priority of all the current approval tasks through the abnormal risk factor, and approving through the priority.

[0006] Further, the delay factor of each approval role type node is obtained according to the difference between all approval durations of each approval role type node in all the structure trees and a reference approval duration, including:

[0007] In the formula, the mean of all approval durations of each approval role type in all the structure trees is denoted as the reference approval duration of each approval role type is denoted as the activation function is denoted as the activation function is denoted as, which is used for data normalization; the delay factor of each approval role type node is denoted as

[0008] Further, the task type in each approval task is determined, and the importance of each node is determined through the task type; the weight coefficient of each node is obtained according to the importance of each node and the level corresponding to each node, including: The task type includes the task type corresponding to the financial risk, the legal risk and the compliance risk; the importance of the node corresponding to the financial risk is denoted as a preset first importance, the importance of the node corresponding to the legal risk is denoted as a preset second importance, and the importance of the node corresponding to the compliance risk is denoted as a preset third importance; The weight coefficient of each node is specifically represented by a formula:

[0009] In the formula, the importance of each node is denoted as Indicates the level number corresponding to each node, represents the weight coefficient of each node, represents the linear normalization function.

[0010] Furthermore, obtaining the overall delay factor of each approval task according to the delay factor and the weight coefficient includes: Obtain the delay factor of each node in each approval task through the delay factor of each approval role type node; The overall delay factor of each approval task is specifically expressed by the formula:

[0011] Where, Indicates the first The delay factor of each node, Indicates the first The weight coefficient of each node, Indicates the number of all nodes in each approval task. Indicates the overall delay factor of each approval task.

[0012] Furthermore, all data points in the risk feature space are clustered to obtain several clusters, including: All data points in the risk feature space are clustered using the K-means clustering algorithm to obtain several clusters; the number of clusters is obtained using the elbow method.

[0013] Furthermore, obtaining the abnormal risk factor of each point to be analyzed based on the distance between each point to be analyzed and the center points of all clusters and the distance between the center points of the clusters and the origin includes:

[0014]

[0015] Where, Indicates that each point to be analyzed The distance between the cluster centers, Indicates the The distance between the center point of each cluster and the origin of the risk feature space, represents the number of all clusters, Indicates the The risk reference weight of each cluster for each point to be analyzed; represents the abnormal risk factor of each point to be analyzed, Represents an exponential function with a natural constant as its base.

[0016] Further, the priority of all current approval tasks is determined by the abnormal risk factor, and the approval is performed according to the priority, comprising: The abnormal risk factors of all current approval tasks are normalized, and the normalization result is used as the priority of all current approval tasks, and the approval is performed according to the priority of all current approval tasks in descending order.

[0017] The second aspect of the present application provides a collaborative process intelligent auxiliary approval system based on dynamic risk modeling, comprising: A historical data acquisition module is configured to construct a tree structure for each approval task, obtain a structure tree of each approval task, and acquire all historical data of the approval task, wherein the historical data includes approval duration, modification times; A delay analysis module is configured to obtain a delay factor of each approval role type node according to the difference between the approval duration of each approval role type node in all structure trees and a reference approval duration, determine the task type in each approval task, and determine the importance of each node according to the task type, obtain a weight coefficient of each node according to the importance of each node and the level corresponding to each node, and obtain an overall delay factor of each approval task according to the delay factor and the weight coefficient; An approval task risk determination module is configured to acquire the compliance risk and legal risk of each approval task in the structure tree, perform linear normalization on the amount of money in the financial risk, the compliance risk, the legal risk, and the modification times, respectively, to obtain a financial risk factor, a compliance risk factor, a legal risk factor, and a modification factor, construct a risk feature space according to the overall delay factor, the financial risk factor, the compliance risk factor, the legal risk factor, and the modification factor, map all approval tasks in history in the risk feature space to obtain a plurality of data points, cluster all data points in the risk feature space to obtain a plurality of clusters, map all current approval tasks in the risk feature space to obtain a plurality of to-be-analyzed points, and obtain an abnormal risk factor of each to-be-analyzed point according to the distance between each to-be-analyzed point and all cluster center points and the distance between the cluster center points and the origin; A priority determination and approval module is configured to determine the priority of all current approval tasks by the abnormal risk factor, and perform the approval according to the priority.

[0018] The third aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to realize the collaborative process intelligent auxiliary approval method based on dynamic risk modeling.

[0019] The fourth aspect of the present application provides a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program is executed by a processor to realize the intelligent auxiliary examination and approval method based on dynamic risk modeling.

[0020] Compared with the prior art, the beneficial effects of the present application are: obtaining a delay factor of each examination and approval role type node according to the difference between all examination and approval time lengths of each examination and approval role type node in all structure trees and the reference examination and approval time length; obtaining a weight coefficient of each node according to the importance of each node and the level corresponding to each node; obtaining an overall delay factor of each examination and approval task according to the delay factor and the weight coefficient; improving the accuracy of delay influence analysis between different levels; mapping all examination and approval tasks in history in a risk feature space to obtain a plurality of data points; clustering all data points in the risk feature space to obtain a plurality of clusters; mapping all current examination and approval tasks in the risk feature space to obtain a plurality of to-be-analyzed points; obtaining an abnormal risk factor of each to-be-analyzed point according to the distance between each to-be-analyzed point and all cluster center points and the distance between the cluster center points and the origin; improving the accuracy of dynamic risk analysis and reducing the influence of risk on the examination and approval process; determining the priority of all current examination and approval tasks through the abnormal risk factor, and improving the efficiency and fluency of intelligent auxiliary examination and approval through the priority. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.

[0022] Figure 1 The step flowchart of the intelligent auxiliary examination and approval method based on dynamic risk modeling is provided for the present application. Figure 2 The module flowchart of the intelligent auxiliary examination and approval system based on dynamic risk modeling is provided for the present application. DETAILED DESCRIPTION

[0023] In order to make the personnel in the technical field better understand the present application scheme, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", and the like in the description and claims of the application and the above drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0025] In view of the problems in the background art, a collaborative process intelligent auxiliary approval method and system based on dynamic risk modeling are designed, which has important practical significance.

[0026] As shown in Figure 1 The first aspect of the present application is to provide a collaborative process intelligent auxiliary approval method based on dynamic risk modeling, comprising the following steps: Step S001: Construct a tree structure for each approval task to obtain a structure tree for each approval task; obtain all historical data of the approval task.

[0027] It should be noted that in order to clearly understand the relationship between different levels in the approval task and the dependency relationship, the key nodes and potential risks of each link are identified through a visual method. The tree structure can clearly show the order of task execution and the association of each approval link, facilitate monitoring the progress of the task, and ensure that there is no omission or inefficient link. At the same time, it also helps to optimize resource allocation, improve processing efficiency, prioritize high-risk or delayed nodes, avoid bottlenecks or errors in task execution, and thus improve the standardization and accuracy of the overall approval process.

[0028] It should be further noted that in order to improve the flexibility and efficiency of the system approval, the priority of each approval task is determined by analyzing the historical data and the specific circumstances of the approval task.

[0029] Specifically, a tree structure is constructed for each approval task to obtain a structure tree for each approval task. All historical data of the approval task is obtained; the historical data includes the approval duration, the number of modifications of each approval task.

[0030] At this point, the construction of the approval task structure tree and all historical data of all approval tasks in the approval process are completed.

[0031] Step S002: obtaining a delay factor of each approval role type node according to the difference between all approval durations of each approval role type node in all structure trees and the reference approval duration; obtaining a weight coefficient of each node according to the importance of each node and the level corresponding to each node; and obtaining an overall delay factor of each approval task according to the delay factor and the weight coefficient.

[0032] It should be noted that, in one approval task, there are multiple people of different levels who perform approval, and these approvers correspond to different nodes in the structure tree, that is, one node corresponds to one approver.

[0033] It should be further noted that, because the approvers of different nodes correspond to different positions, the points of attention of the approvers of different nodes are different when performing an approval task; for example, in one approval task, there can be general manager approval, financial approval, and department manager approval; therefore, the risks of different nodes are different when performing approval, and thus the duty types of the approvers of each node need to be combined to analyze different risk situations.

[0034] It should be further noted that, in order to determine the risk situation of each node, the approval role type of each node needs to be determined, and the approval delay degree corresponding to each node is analyzed according to historical data through the same approval role type.

[0035] Specifically, the approval role type corresponding to the node is first determined; wherein the approval role type includes financial approval, leadership approval, department manager approval, senior management approval, specialist approval, and administrative approval; that is, the approval role type nodes include financial approval nodes, leadership approval nodes, department manager approval nodes, senior management approval nodes, specialist approval nodes, and administrative approval nodes.

[0036] A delay factor of each approval role type node is obtained according to the difference between all approval durations of each approval role type node in all structure trees and the reference approval duration; wherein the delay factor of each approval role type node is specifically represented by a formula as follows:

[0037] In the formula, μ represents the mean of all approval durations of each approval role type in all structure trees, μ ref represents the reference approval duration of each approval role type, σ represents the standard deviation of all approval durations of each approval role type, σ ref represents the standard deviation of the reference approval duration of each approval role type, f represents an activation function, f ref represents an activation function for data normalization, and d represents the delay factor of each approval role type node.

[0038] wherein,​​​​​ It represents the difference between the mean of all approval times for each approval role type in all structure trees and the reference approval time. A larger difference indicates that this approval role type experienced a delay in the historical approval process, and the delay was longer. A smaller positive difference indicates that there was a delay, but the delay was shorter. A negative difference indicates that there was no delay in the historical approval process for this approval role type, and that the approval was generally completed within the specified approval time.

[0039] At this point, the delay factor of each approval role type node is obtained through the above method; similarly, the delay factor of each node in each approval task is also obtained.

[0040] It should be noted that, since the corresponding importance levels are different in the approval of different nodes, it is necessary to analyze the importance of each node.

[0041] It's also important to note that higher-level nodes carry greater responsibilities, so their importance should be greater. During the approval process, nodes at the same level may handle different types of approvals, such as data and amounts, or legal risks. Therefore, the importance of each node needs to be analyzed based on these different types.

[0042] Specifically, determine the task type in each approval task. In this embodiment, the task types corresponding to financial risk, legal risk and compliance risk are used as examples for illustration, but the task type is not specifically limited. The implementer can determine it based on the actual situation of the specific task type.

[0043] The importance of the node corresponding to financial risk is recorded as the preset first importance, the importance of the node corresponding to legal risk is recorded as the preset second importance, and the importance of the node corresponding to compliance risk is recorded as the preset third importance. In this embodiment, the preset first importance is 0.8, the preset second importance is 0.7, and the preset third importance is 0.5. In this embodiment, the preset first importance, preset second importance, and preset third importance are not specifically limited and can be determined by the implementer based on specific circumstances.

[0044] According to the importance of each node and the level corresponding to each node, the weight coefficient of each node is obtained; wherein the weight coefficient of each node is specifically expressed by the formula:

[0045] Where, Indicates the importance of each node. Indicates the level number corresponding to each node, represents the weight coefficient of each node, represents the linear normalization function.

[0046] Among them, when the importance of each node and the level corresponding to each node are greater, the weight coefficient of each node is greater; otherwise, the weight coefficient of each node is smaller.

[0047] Based on the delay factor and weight coefficient of each node in the history, the overall delay factor of each approval task is obtained; the overall delay factor of each approval task is specifically expressed by the formula:

[0048] Where, Indicates the first The delay factor of each node, Indicates the first The weight coefficient of each node, Indicates the number of all nodes in each approval task. Indicates the overall delay factor of each approval task.

[0049] in, It represents the delay contribution of each node and the overall delay factor of each approval task is calculated by taking a weighted average of all nodes.

[0050] At this point, the overall delay factor of each approval task in the history is obtained through the above method.

[0051] Step S003: Construct a risk feature space; map all historical approval tasks in the risk feature space to obtain several data points; cluster all data points in the risk feature space to obtain several clusters; map all current approval tasks in the risk feature space to obtain several points to be analyzed; obtain the abnormal risk factor of each point to be analyzed based on the distance between each point to be analyzed and the center points of all clusters and the distance between the center points of the clusters and the origin.

[0052] It should be noted that the larger the amount in the approval task, the greater the financial risk; and the larger the overall delay factor of each approval task in all structure trees, the greater the financial risk, the greater the compliance risk, and the greater the legal risk, the greater the risk of the approval task in the history. Combined with the number of modifications of each approval task in all structure trees, the greater the number of modifications and the greater the risk, the approval task should be given a higher priority for review during the approval process.

[0053] Specifically, by analyzing all the approval materials files submitted by each approval task in each structure tree through a large language model, the compliance risk and legal risk of each approval task in each structure tree are obtained; wherein the large language model in this embodiment is OpenAI GPT (OpenAI Generative Pre-trained Transformer) or LegalBERT (Legal Bidirectional Encoder Representations from Transformers); wherein the large language model is not specifically limited in this embodiment, and the implementer can determine according to the specific circumstances.

[0054] It should be further pointed out that when analyzing the financial risk of each approval task, the size of the amount involved therein can be analyzed. In order to eliminate the influence of different dimensions, the financial risk, compliance risk, legal risk and modification frequency data are processed to eliminate the influence of dimensions.

[0055] Specifically, the amount in the financial risk, the compliance risk, the legal risk and the modification frequency are linearly normalized respectively to obtain the financial risk factor, the compliance risk factor, the legal risk factor and the modification factor.

[0056] The overall delay factor, the financial risk factor, the compliance risk factor, the legal risk factor and the modification factor of each approval task are respectively taken as dimension features to construct a risk feature space; each approval task in all the structure trees is mapped in the risk feature space to obtain a data point; all the approval tasks in the history are mapped in the risk feature space to obtain a plurality of data points.

[0057] All the data points in the risk feature space are clustered by a K-means clustering algorithm to obtain a plurality of clusters; wherein the number of clusters is obtained by an elbow method; wherein the K-means clustering algorithm and the elbow method are both known technologies, and will not be described in detail here.

[0058] It should be pointed out that the closer each cluster is to the origin of the risk feature space, the smaller the risk of the corresponding approval task in the cluster is; the farther each cluster is to the origin of the risk feature space, the greater the risk of the corresponding approval task in the cluster is. Therefore, by mapping all the current approval tasks in the risk feature space, the positional relationship between all the clusters is analyzed to determine the degree of risk of each current approval task, and the priority of each approval task is determined by the degree of risk.

[0059] Specifically, a plurality of to-be-analyzed points are obtained by mapping all the current approval tasks in a risk feature space; an abnormal risk factor of each to-be-analyzed point is obtained according to a distance between each to-be-analyzed point and all cluster center points and a distance between the cluster center points and the origin; wherein the abnormal risk factor of each to-be-analyzed point is specifically expressed by a formula as follows:

[0060]

[0061] In the formula, d represents a distance between each to-be-analyzed point and the i-th cluster center point, d represents a distance between the i-th cluster center point and the origin of the risk feature space (used to represent an abnormal risk situation of each cluster), n represents a number of all clusters, wi represents a risk reference weight of the i-th cluster to each to-be-analyzed point; r represents an abnormal risk factor of each to-be-analyzed point, e represents an exponential function with a natural constant as a base. Wherein, the closer the distance between each to-be-analyzed point and each cluster center point is, the more worthy the abnormal risk situation of the cluster is as a reference abnormal risk of the to-be-analyzed point, that is, the risk reference weight of the cluster to each to-be-analyzed point should be larger; otherwise, the risk reference weight of the cluster to each to-be-analyzed point should be smaller. Then, the abnormal risk factor of each to-be-analyzed point is obtained by combining all risk reference weights with the abnormal risk situations of all clusters. Up to now, the abnormal risk factor of each to-be-analyzed point is obtained by the above method.

[0062] Step S004: determining a priority of all the current approval tasks through the abnormal risk factor and approving through the priority.

[0063] It should be noted that the priority of all the approval tasks is determined through the abnormal risk factor by analyzing all the current approval tasks; that is, the larger the abnormal risk factor of each approval task is, the larger the priority of the approval task should be, that is, the task should be approved more preferentially.

[0064]

[0065] It should be noted that the priority of all the approval tasks is determined through the abnormal risk factor by analyzing all the current approval tasks; that is, the larger the abnormal risk factor of each approval task is, the larger the priority of the approval task should be, that is, the task should be approved more preferentially.

[0066] ​​​Specifically, through the process of obtaining the abnormal risk factors of each point to be analyzed, the abnormal risk factors of all current approval tasks are obtained; the abnormal risk factors of all current approval tasks are normalized, and the normalized results are used as the priorities of all current approval tasks, and the approval is carried out in order from large to small according to the priorities of all current approval tasks.

[0067] At this point, this embodiment is completed.

[0068] like Figure 2 As shown, the second aspect of the present invention is to provide a collaborative process intelligent auxiliary approval system based on dynamic risk modeling, including: Historical data acquisition module 101: used to construct a tree structure for each approval task, obtain the structure tree of each approval task; obtain all historical data of the approval task; the historical data includes the approval time and the number of revisions; Delay analysis module 102: used to obtain a delay factor for each approval role type node based on the difference between all approval times and reference approval times for each approval role type node in all the structure trees; determine the task type in each approval task, and determine the importance of each node based on the task type; obtain a weight coefficient for each node based on the importance of each node and the level corresponding to each node; and obtain an overall delay factor for each approval task based on the delay factor and the weight coefficient; Approval task risk determination module 103: used to obtain the compliance risk and legal risk of each approval task in the structure tree; linearly normalize the amount, compliance risk, legal risk, and modification number of financial risk to obtain a financial risk factor, a compliance risk factor, a legal risk factor, and a modification factor, and construct a risk feature space through the overall delay factor, the financial risk factor, the compliance risk factor, the legal risk factor, and the modification factor; map all historical approval tasks in the risk feature space to obtain a number of data points; cluster all data points in the risk feature space to obtain a number of clusters; map all current approval tasks in the risk feature space to obtain a number of points to be analyzed; and obtain the abnormal risk factor of each point to be analyzed based on the distance between each point to be analyzed and the center points of all clusters, and the distance between the center points of the clusters and the origin. The priority determination and approval module 104 is used to determine the priorities of all current approval tasks based on the abnormal risk factors, and to perform approval based on the priorities.

[0069] The third aspect of the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, a collaborative process intelligent assisted approval method based on dynamic risk modeling is implemented.

[0070] The fourth aspect of the present application provides a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program is executed by a processor to realize a method for intelligent auxiliary examination and approval based on dynamic risk modeling.

[0071] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems, or computer program products. Accordingly, the present application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can be embodied in the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk memory, optical memory, etc.) having computer-usable program code embodied thereon.

[0072] The present application is described with reference to flowcharts and / or block diagrams of methods, systems, and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing apparatus, generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the functions specified in the flowchart

[0073] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction means, which implement the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the functions specified in the flowchart

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the functions specified in the flowchart

[0075] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application but not to limit it. Although the present application has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that the specific embodiments of the present application can be modified or equivalently replaced without departing from the spirit and scope of the present application, and any modification or equivalent replacement should be covered within the protection scope of the present application.

Claims

1. A collaborative process intelligent assisted approval method based on dynamic risk modeling, characterized by: include: Build a tree structure for each approval task and obtain the structure tree of each approval task; Obtain all historical data of the approval task; the historical data includes approval time and number of revisions; Obtaining a delay factor for each approval role type node based on the difference between all approval times and a reference approval time for each approval role type node in all the structure trees; determining a task type in each approval task, and determining the importance of each node based on the task type; Obtaining a weight coefficient for each node based on the importance of each node and the level corresponding to each node; obtaining an overall delay factor for each approval task based on the delay factor and the weight coefficient; Obtaining the compliance risk and legal risk of each approval task in the structure tree; Linearly normalizing the amount, compliance risk, legal risk, and number of modifications in the financial risk to obtain a financial risk factor, a compliance risk factor, a legal risk factor, and a modification factor, and constructing a risk feature space using the overall delay factor, the financial risk factor, the compliance risk factor, the legal risk factor, and the modification factor; Map all historical approval tasks into the risk feature space to obtain several data points; Cluster all data points in the risk feature space to obtain several clusters; map all current approval tasks in the risk feature space to obtain several points to be analyzed; obtain the abnormal risk factor of each point to be analyzed based on the distance between each point to be analyzed and the center points of all clusters, as well as the distance between the cluster center points and the origin; The priorities of all current approval tasks are determined by the abnormal risk factors, and approval is performed based on the priorities.

2. The collaborative process intelligent assisted approval method based on dynamic risk modeling according to claim 1 is characterized in that: Obtaining the delay factor of each approval role type node according to the difference between all approval durations of each approval role type node in all the structure trees and the reference approval duration includes: Where, Indicates the average of all approval times for each approval role type in all structure trees. Indicates the reference approval time for each approval role type. represents the activation function, Represents the activation function, used for data normalization; Indicates the delay factor for each approval role type node.

3. The collaborative process intelligent assisted approval method based on dynamic risk modeling according to claim 1 is characterized in that: Determining the task type in each approval task and determining the importance of each node based on the task type; According to the importance of each node and the level corresponding to each node, the weight coefficient of each node is obtained, including: The task types include task types corresponding to financial risks, legal risks and compliance risks; The importance of the node corresponding to financial risk is recorded as the preset first importance, the importance of the node corresponding to legal risk is recorded as the preset second importance, and the importance of the node corresponding to compliance risk is recorded as the preset third importance; The weight coefficient of each node is specifically expressed by the formula: Where, Indicates the importance of each node. Indicates the level number corresponding to each node, represents the weight coefficient of each node, represents the linear normalization function.

4. The collaborative process intelligent assisted approval method based on dynamic risk modeling according to claim 1 is characterized in that: Obtaining the overall delay factor of each approval task according to the delay factor and the weight coefficient includes: Obtain the delay factor of each node in each approval task through the delay factor of each approval role type node; The overall delay factor of each approval task is specifically expressed by the formula: Where, Indicates the first The delay factor of each node, Indicates the first The weight coefficient of each node, Indicates the number of all nodes in each approval task. Indicates the overall delay factor of each approval task.

5. The collaborative process intelligent assisted approval method based on dynamic risk modeling according to claim 1 is characterized in that: The method clusters all data points in the risk feature space to obtain several clusters, including: All data points in the risk feature space are clustered using the K-means clustering algorithm to obtain several clusters; the number of clusters is obtained using the elbow method.

6. The collaborative process intelligent assisted approval method based on dynamic risk modeling according to claim 1 is characterized in that: The abnormal risk factor of each point to be analyzed is obtained according to the distance between each point to be analyzed and the center points of all clusters and the distance between the center points of the clusters and the origin, including: Where, Indicates that each point to be analyzed The distance between the cluster centers, Indicates the The distance between the center point of each cluster and the origin of the risk feature space, represents the number of all clusters, Indicates the The risk reference weight of each cluster for each point to be analyzed; represents the abnormal risk factor of each point to be analyzed, Represents an exponential function with a natural constant as its base.

7. The collaborative process intelligent assisted approval method based on dynamic risk modeling according to claim 1 is characterized in that: Determining the priorities of all current approval tasks based on the abnormal risk factors and approving based on the priorities includes: Normalize the abnormal risk factors of all current approval tasks, use the normalized results as the priority of all current approval tasks, and approve them in descending order based on the priority of all current approval tasks.

8. The collaborative process intelligent auxiliary approval system based on dynamic risk modeling is characterized by: include: Historical data acquisition module: used to build a tree structure for each approval task and obtain the structure tree of each approval task; Obtain all historical data of the approval task; the historical data includes approval time and number of revisions; Delay analysis module: used to obtain the delay factor of each approval role type node based on the difference between all approval times and the reference approval time of each approval role type node in all the structure trees; determine the task type in each approval task, and determine the importance of each node based on the task type; Obtaining a weight coefficient for each node based on the importance of each node and the level corresponding to each node; obtaining an overall delay factor for each approval task based on the delay factor and the weight coefficient; Approval task risk determination module: used to obtain the compliance risk and legal risk of each approval task in the structure tree; Linearly normalizing the amount, compliance risk, legal risk, and number of modifications in the financial risk to obtain a financial risk factor, a compliance risk factor, a legal risk factor, and a modification factor, and constructing a risk feature space using the overall delay factor, the financial risk factor, the compliance risk factor, the legal risk factor, and the modification factor; Map all historical approval tasks into the risk feature space to obtain several data points; Cluster all data points in the risk feature space to obtain several clusters; map all current approval tasks in the risk feature space to obtain several points to be analyzed; obtain the abnormal risk factor of each point to be analyzed based on the distance between each point to be analyzed and the center points of all clusters, as well as the distance between the cluster center points and the origin; Priority determination and approval module: used to determine the priority of all current approval tasks based on the abnormal risk factors, and approve them based on the priority.

9. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the collaborative process intelligent assisted approval method based on dynamic risk modeling as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the collaborative process intelligent assisted approval method based on dynamic risk modeling as described in any one of claims 1 to 7.

Images