An electronic contract approval management system

Abstract

The present invention discloses an electronic contract approval management system, which specifically relates to the technical field of electronic contract management, including a process monitoring module, an editing tracking module, a risk sign detection module, a data analysis module, a joint identification module and a response decision module; dynamic behavior data such as approval path, processing time and transfer failure are obtained through process monitoring, and the editing tracking module collects multi-person editing behavior trajectory data; the risk sign detection module analyzes data combination patterns and outputs risk trigger signals; the data analysis module constructs a multidimensional data set, calculates the process anomaly index and content conflict index, and the joint identification module performs fuzzy reasoning based on the two indices to divide risk levels; the response decision module executes a graded intervention strategy according to the risk level; the present invention can identify process anomalies and guide repairs, accurately warn of multi-person editing conflicts, ensure content consistency, and has the ability to self-evaluate and optimize strategy response effects, thereby improving the intelligent level of contract approval.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic contract management, and more particularly, to an electronic contract approval management system. Background Art

[0002] With the widespread application of electronic contracts in various business scenarios, including government affairs, finance, manufacturing, and the internet, enterprise contract management systems are gradually moving towards online, automated, and intelligent processes. Contract approval, a critical link in the lifecycle of an electronic contract, often involves multiple business roles, approval conditions, and branching paths. The contract content itself typically requires multiple people to edit, review, and confirm. However, existing contract approval systems have significant shortcomings when it comes to handling complex process configurations and high-concurrency collaborative editing scenarios.

[0003] On the one hand, traditional systems often use static process templates, lacking the ability to dynamically identify and respond to abnormal behavior during actual operation. When process configuration becomes unreasonable or the execution status of an approval node is abnormal, the system struggles to detect and fix it in a timely manner, leading to frequent approval delays, incorrect signatures, or omissions. On the other hand, when editing contract content, the common multi-person collaborative model is prone to problems such as overlapping edits, version overwriting, and content confusion. This is especially true when user editing behaviors overlap significantly or editing conflicts are uncontrolled, which can easily lead to major errors, thereby affecting contract performance or compliance audits.

[0004] Most existing risk response mechanisms remain at the fixed rule level, lacking dynamic assessment and policy adjustment capabilities based on data feedback. This makes it difficult to adapt to evolving business processes and collaborative behaviors, resulting in delayed system responses to risks, imprecise interventions, and insufficient overall management capabilities. Therefore, there is an urgent need for an electronic contract approval management system that can monitor approval processes and collaborative editing behaviors, and that offers intelligent identification, quantitative assessment, and graded response capabilities to improve the efficiency, accuracy, and security of contract transactions. Summary of the Invention

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An electronic contract approval management system, comprising:

[0007] The process monitoring module is used to obtain dynamic behavior data in the electronic contract approval process, including approval path flow, processing duration, and transfer failure events;

[0008] The edit tracking module is used to collect editing trajectory data of contract documents in multi-person editing scenarios, including editing time distribution, content coverage area, and behavioral interaction sequences between concurrent users;

[0009] The risk sign detection module is used to analyze the above process behavior data and editing trajectory data, and output a risk calculation trigger signal after detecting an abnormal event combination pattern;

[0010] The data analysis module responds to risk trigger signals, constructs a multidimensional data set, and calculates two core indices for joint risk identification: the process anomaly index and the content conflict index, which are then used by downstream modules.

[0011] The joint identification module performs fuzzy reasoning based on the process anomaly index and content conflict index to classify the joint risk level;

[0012] The response decision module performs differentiated interventions based on risk level results, including process correction, permission constraints, notification push, and log archiving.

[0013] In a preferred embodiment, the process monitoring module further includes a node graph construction submodule and a time matrix analysis submodule. The node graph construction submodule abstracts the approval process into a node-edge data structure based on the graph neural structure, identifies disconnected segments and abnormal transfer paths, and the time matrix analysis submodule records the average residence time and fluctuation range of each node by constructing a time-node two-dimensional tensor structure. If the path jump probability exceeds the preset jump threshold, or the processing time standard deviation of a node exceeds the preset ratio threshold (for example, 20%) of the average processing time standard deviation of its adjacent nodes, it is determined to be an abnormal process behavior event.

[0014] In a preferred embodiment, the editing tracking module further includes an editing behavior encoding submodule and a collaborative interaction matrix generation submodule. The former serializes and encodes the operations of each user to generate an editing behavior vector; the latter forms a user interaction density matrix by establishing an editing cross-relationship table between users. If more than q users have high-frequency interlaced editing behaviors in adjacent areas within a certain time window, it is identified as a conflict editing risk. All encoded data and matrix data enter the content conflict index construction model to provide input for subsequent conflict intensity quantification. High-frequency interlaced editing behavior refers to the editing update frequency exceeding the preset editing threshold.

[0015] In a preferred embodiment, the risk sign detection module adopts a combination rule judgment method to identify the continuous occurrence of a preset event pattern. When the corresponding event pattern appears, it is marked as 1, and when it does not appear, it is marked as 0, to obtain an event combination data string composed of 1 and 0. If 1 appears in the event combination data string, a risk calculation trigger signal is output to trigger the subsequent data analysis module to enter the calculation state.

[0016] In a preferred embodiment, the calculation method of the process anomaly index in the data analysis module is:

[0017] The approval process is modeled as a directed graph structure, where nodes represent approval operations and edges represent flow directions. The graph structure is vectorized using a graph embedding algorithm. Then, the abnormal subpath vectors and the standard process vectors are extracted. The process abnormality index FI is defined as the distance between the two: ; Embedding vector i-th dimension component of the current approval process diagram, is the i-th dimension component of the embedding vector of the standard approval flowchart, is the impact factor corresponding to the process structure of the i-th dimension, indicating the importance weight assigned to this dimension in the approval process diagram, which is pre-set by the system based on the training data. is a preset smoothing factor used to avoid the denominator being zero in the calculation. The value is a positive real number less than 1 (such as 0.01), and n is the dimension of the embedding vector.

[0018] In a preferred embodiment, the content conflict index is calculated in the data analysis module as follows:

[0019] Within the unit time window T, extract the set of content blocks edited by all users, record the editing status of each content block, and construct the editing density function: ; Same document location Edit frequency, For the The document location corresponding to the editing operation, is the document position index point currently being evaluated, m is the total number of all editing operations within the time window, Content distribution diffusion coefficient, which indicates the degree of dispersion of editing behavior on the document. The calculated document position index point The corresponding edit density value; ; ; The average of all edit positions;

[0020] Introducing content crossover rate : ; Indicates the number of content segments where multi-user editing occurs. Indicates the total number of content segments;

[0021] The maximum editing density value is recorded as , and content crossover rate Combined content conflict index: ; Indicates the content conflict index.

[0022] In a preferred embodiment, the joint identification module performs fuzzy reasoning based on the combined result of the process anomaly index FI and the content conflict index CI, wherein FI and CI are respectively divided into three levels of "low", "medium" and "high" according to a preset fuzzy membership function, for example, interval mapping is achieved by a triangular membership function, and the reasoning rule is as follows: if FI is "high" and CI is "high", the reasoning result is "serious risk";

[0023] If FI is "medium" and CI is "high", the inference result is "heavier risk";

[0024] If FI is "high" and CI is "medium", the inference result is "medium risk";

[0025] If both are “low”, the inference result is “normal risk”;

[0026] The inference results are quantified into four levels of output signals, with corresponding values of 0, 1, 2, and 3, representing normal, moderate, severe, and serious risks, respectively.

[0027] The response decision module includes the following strategy selection mechanisms:

[0028] If the risk level is severe, the approval process is suspended, all editing permissions are locked, and administrator intervention is forced;

[0029] If the risk level is high, restrict multiple people from editing and rebuilding conflicting nodes in the approval path;

[0030] If the risk level is medium, issue an early warning and record a risk log;

[0031] If the risk level is normal, no intervention is performed but the behavioral data is archived.

[0032] In a preferred embodiment, the response decision module further includes a supervision mechanism:

[0033] After each risk response is triggered, the following three indicators are recorded: process repair success rate, conflict reduction rate, and approval acceleration. These three indicators are then subjected to polynomial regression modeling. Based on the output data of the polynomial regression modeling, namely the improvement value, the least squares method is used to fit a fitting straight line between the improvement value and the response time. The slope of the fitting straight line is compared with the preset standard slope. If the slope of the fitting straight line is greater than or equal to the preset standard slope, the current response is valid. If the slope of the fitting straight line is less than the preset standard slope, the current response is invalid, and the manual intervention window mode is entered, forcing the administrator to intervene.

[0034] Technical effects and advantages of the present invention:

[0035] The present invention constructs an approval process graph structure, combines graph embedding with time tensor analysis technology, and realizes the dynamic identification of path jumps, disconnected segments, and processing time fluctuations between process nodes. Unlike the existing static template comparison inspection method, the present invention can continuously monitor the process execution status during actual operation. Once structural deviation behavior is found, such as abnormal node processing time standards and irregular jump paths, the system immediately marks the process as abnormal and records the abnormal path vector. This mechanism can not only detect problems such as process freezes and misrouting in the first place, but also trigger subsequent response strategies to repair or reconstruct abnormal nodes, thereby effectively improving the stability and closed-loop rate of the process.

[0036] The present invention constructs a behavioral coding model and interaction density matrix for editing behavior monitoring, which can accurately identify high-frequency editing behaviors of multiple people on adjacent or overlapping document areas within the same time window, and then evaluate the intensity of conflicts. The system calculates the content conflict index through the editing density function and the content intersection rate. The content conflict index can provide early warning of potential high-risk operations such as version overwrites and incorrect changes. Compared with traditional version control mechanisms, the present invention can not only identify risks, but also conduct differentiated interventions based on the density of conflict locations, such as restricting editing permissions, thereby effectively ensuring the consistency, traceability and correctness of contract content during the collaborative process of multiple people.

[0037] The present invention introduces a supervision mechanism in the risk response module. The system not only automatically intervenes according to the risk level, but also records and models the effects after each response, extracts multi-dimensional feedback indicators such as the process repair success rate, conflict reduction rate, and approval acceleration, and forms an evolutionary trend of the "strategy improvement value" through polynomial regression and trend fitting. The system then compares the fitted slope with the standard slope to achieve a continuous judgment on the effectiveness of the response strategy, and forces the system to enter the manual intervention mode when the strategy fails. This mechanism gives the system the ability to "learn to judge whether the strategy is sustainable", getting rid of the defects of rigid rules and broken feedback in the past, and realizing the technological leap from a fixed response mechanism to a self-evolving one. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0039] Figure 1 This is a schematic diagram of an electronic contract approval management system in the present invention.

[0040] Figure 2 This is a schematic diagram of the process monitoring module in the present invention.

[0041] Figure 3 This is a schematic diagram of the editing and tracking module in the present invention.

[0042] Figure 4This is a schematic diagram of the collaboration principle of the joint identification module and the response decision module in the present invention. DETAILED DESCRIPTION

[0043] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0044] Reference Figure 1-4 The following examples were obtained:

[0045] As digital management continues to improve in enterprises, electronic contracts are widely adopted in various business processes. However, in complex practical application scenarios, the approval process for electronic contracts often involves multiple roles, multiple levels, and multiple conditional branches. If the approval path is not designed properly, the role configuration is mismatched, or the node processing efficiency fluctuates, it is very easy to cause process jams, interruptions, or incorrect approvals. At the same time, the collaborative editing of contract content also faces problems such as multiple people operating simultaneously, frequent content conflicts, and the lack of traceability of editing behavior. Once an incorrect signature, an omission, or a disordered editing sequence occurs, it will seriously affect the legal validity and performance security of the contract.

[0046] This invention aims to provide an electronic contract approval management system with intelligent identification and proactive intervention capabilities. Through process monitoring and editorial behavior analysis, it ensures both the integrity of the approval path and the consistency of content collaboration. Upon detecting anomalies, the system automatically initiates risk assessment, constructs a process anomaly index and a content conflict index, and uses a fuzzy inference model to determine the combined risk level. Based on the risk level, the system dynamically selects a corresponding response strategy and evaluates its effectiveness through regression modeling and trend analysis, ensuring effective responses and enhancing the stability, reliability, and adaptability of the contract approval system.

[0047] Based on this, the present invention proposes an electronic contract approval management system, comprising:

[0048] The process monitoring module is used to obtain dynamic behavior data in the electronic contract approval process, including approval path flow, processing duration, and transfer failure events;

[0049] The edit tracking module is used to collect editing trajectory data of contract documents in multi-person editing scenarios, including editing time distribution, content coverage area, and behavioral interaction sequences between concurrent users;

[0050] The risk sign detection module is used to analyze process behavior data and editing trajectory data, and output a risk calculation trigger signal after detecting a combination of abnormal events;

[0051] The data analysis module responds to risk trigger signals, constructs a multidimensional data set, and calculates two core indices for joint risk identification: the process anomaly index and the content conflict index, which are then used by downstream modules.

[0052] The joint identification module performs fuzzy reasoning based on the process anomaly index and content conflict index to classify the joint risk level;

[0053] The response decision module performs differentiated interventions based on risk level results, including process correction, permission constraints, notification push, and log archiving.

[0054] "Dynamic behavior data" refers to the process status change data collected and analyzed by the system during the execution of the electronic contract approval process, which mainly includes the following three core contents: Approval path flow information: refers to whether the approval operations between nodes are carried out in the set order, including flow time, whether nodes are skipped, and whether loops are returned; Processing duration: refers to the time taken for each node to go from pending to completed processing, which is used to measure approval efficiency and identify node anomalies; Transfer failure events: refers to abnormal termination, interruption, failed return, inability to execute logic, and other behaviors in the flow of approval processes between nodes.

[0055] The process monitoring module automatically connects with the approval system and records the corresponding information every time the node status changes; transmission destination: the collected data will be sent to the risk sign detection module for abnormal event combination analysis to determine whether the trigger conditions are met; association with the process anomaly index: some data (such as node jumps and delays) will enter the process anomaly index calculation model to calculate the degree of deviation between the current process and the standard process.

[0056] "Editing trajectory data" refers to the system's continuous record of each user's operating behavior during the collaborative editing of contract documents by multiple people. Its core includes: Editing time distribution: refers to the time point and time period of the user's document operation, which is used to analyze the editing density and collaboration opportunities; Content coverage area: refers to the document content range involved in the user's editing operation (such as paragraph number, character index interval, etc.); Concurrent user interaction sequence: refers to the intersection and overlap relationship of multiple users' editing behaviors in the document space within the same time window, which is used to build a user collaboration conflict model. Data source: recorded by the editing tracking module when the user uses the contract editing system; Transmission destination: The editing behavior is vectorized and sent to the content conflict index calculation model; The concurrent cross-behavior matrix is sent to the risk sign detection module to identify high-frequency staggered editing patterns; Impact module: This type of data mainly supports the calculation of the content conflict index.

[0057] The electronic contract approval management system proposed in this invention first accesses the enterprise's internal approval process and contract document collaboration platform through the front end, and continuously collects and records the full amount of dynamic data on the approval execution process and content editing behavior. In terms of process, the system tracks the execution status, processing time and path flow logic of each approval node, and establishes a structured flow chart; in terms of content, the system performs temporal and spatial encoding on the editing behavior of collaborative users, identifying editing hot spots, behavior frequency and changes in collaboration density. Through the fusion analysis of these two types of data, the system can discover abnormal patterns hidden behind imbalances in the approval process and conflicts among multiple editors, forming risk signs with early warning value.

[0058] When risk indicators are activated, the system activates its internal data analysis engine, extracts the current process structure state and editing behavior sequence, and maps them into a multi-dimensional feature vector. The system constructs two core indicators: the process anomaly index and the content conflict index. The former measures the degree of deviation of the current approval path from the preset process template, and the latter measures the degree of overlap and conflict intensity during the collaborative editing process. After the index is generated, the system uses a fuzzy inference mechanism to convert the numerical results into identifiable risk levels. These are divided into four levels: normal, moderate, severe, and serious. This meticulously presents the actual severity and scope of the risk, providing precise input for subsequent response modules.

[0059] According to the different joint risk levels, this system has the ability to respond with multiple strategies in a coordinated manner. For risks at a minor or warning level, the system only records logs or issues notification reminders; when the risk level reaches a heavier or severe level, the system will automatically perform intervention actions such as process reconstruction and editing permission adjustment to prevent the risk from spreading further. At the same time, the system also has a supervision mechanism, which records and trends the repair results after each response behavior, and uses the fitting results to evaluate the effectiveness of the current strategy. When the system detects that the policy execution effect continues to be poor, it will automatically switch to manual intervention mode to ensure the stable operation and final closure of the entire contract approval process. This whole process reflects the high degree of integration and closed-loop control capabilities of the present invention in the four stages of risk identification, analysis, response, and evaluation.

[0060] The process monitoring module further includes a node graph construction submodule and a time matrix analysis submodule. The node graph construction submodule abstracts the approval process into a node-edge data structure based on the graph neural structure, identifies disconnected segments and abnormal transfer paths, and the time matrix analysis submodule records the average residence time and fluctuation range of each node by constructing a time-node two-dimensional tensor structure. If the path jump probability exceeds the preset jump threshold, or the processing time standard deviation of a node exceeds the preset ratio threshold (for example, 20%) of the average processing time standard deviation of its adjacent nodes, it is determined to be an abnormal process behavior event.

[0061] In the present invention, the process monitoring module is not only used to record the basic behavioral information in the approval process, but also further includes a node graph construction submodule and a time matrix analysis submodule, so as to achieve a comprehensive evaluation of the structural stability and operating efficiency of the approval process.

[0062] The node graph construction submodule models the contract approval process and abstracts the approval process into a graph structure model consisting of nodes and paths. In this model, each approval action is modeled as a graph node, and the sequential flow relationship between two adjacent approval links constitutes a directed edge. The system encodes the graph through a graph neural structure and extracts the graph embedding vector of each node for subsequent structural feature learning. During the graph construction process, the system simultaneously detects the following two types of structural anomalies: (1) the existence of non-connected segments in the graph that cannot be accessed from the starting node to certain intermediate or terminal nodes; (2) non-linear jumps in the approval path, that is, jumping directly from a node to a non-directly adjacent node, violating the preset approval order.

[0063] To identify these jumps, the system counts the jump frequency of all actual approval paths, obtains the probability of a node jumping to a non-adjacent node across all process instances, and compares this probability with a set jump threshold. If the jump probability exceeds this threshold and the path behavior isn't configured as a valid conditional branch path, the system identifies the path as an abnormal transfer.

[0064] The time matrix analysis submodule is used to record the processing time of each approval node in multiple contract instances and construct a two-dimensional tensor structure based on time and node number. Each row of the matrix represents an approval node, and the column vector is its processing time series. The system calculates the average processing time and the standard deviation of the processing time for each node in this tensor. To identify efficiency anomalies in the approval process, the system introduces a time fluctuation indicator associated with the node, that is, the ratio of the standard deviation of the processing time of a node to the standard deviation of the processing time of its adjacent nodes. If this ratio exceeds the set percentage threshold, it means that the processing time of the node has significant fluctuations relative to other links, which is a potential bottleneck or abnormal approval behavior.

[0065] When either the structural anomaly or temporal fluctuation conditions are met, the system marks the process instance as "process behavior anomaly" and writes this identification value into the anomaly record list for subsequent process anomaly index modeling. This approach enables the process monitoring module to monitor both structural rationality and efficiency stability, providing powerful process feature input for the subsequent risk assessment and intervention mechanisms of this invention.

[0066] The editing tracking module further includes an editing behavior encoding submodule and a collaborative interaction matrix generation submodule. The former serializes and encodes the operations of each user to generate an editing behavior vector; the latter forms a user interaction density matrix by establishing an editing cross-relationship table between users. If more than q users have high-frequency interleaved editing behaviors in adjacent areas within a certain time window, it is identified as a conflict editing risk. All encoded data and matrix data enter the content conflict index construction model to provide input for the subsequent conflict intensity quantification. High-frequency interleaved editing behavior refers to the editing update frequency exceeding the preset editing threshold.

[0067] In the present invention, in order to achieve high-precision identification and risk modeling of multi-person collaborative editing behaviors, the editing tracking module further includes an editing behavior encoding submodule and a collaborative interaction matrix generation submodule, which are used to characterize behavioral patterns from three dimensions: time, location, and user relationship of editing operations, and are used for input generation of subsequent content conflict index models.

[0068] The editing behavior encoding submodule is used to collect the operational data of each contract editing user and convert it into a structured behavioral coding sequence. Specifically, each user operation records the following fields: user ID, operation timestamp, start and end positions of the edited content block (expressed as character offset or paragraph number), operation type (such as insert, delete, replace), and device terminal information. The system combines these fields into a multidimensional vector sequence representing the user's editing trajectory within a unit time window and arranges them in chronological order to form their personal editing behavior vector. This encoding not only preserves the temporal characteristics of the behavior, but also the spatial location of the content, facilitating subsequent cross-behavior detection.

[0069] The collaborative interaction matrix generation submodule constructs a collaborative cross-relationship table between users based on the behavior vectors of multiple users. According to the preset time window, the system compares the editing operations of all users within the time window in pairs to determine whether there is spatial overlap in their editing content areas, that is, whether two users edit adjacent or overlapping paragraphs within the time window. If there is an intersection, the corresponding position in the user cross-relationship table is marked as one; otherwise, it is marked as zero. Based on this table, a user interaction density matrix is further generated. Each row of the matrix represents a user, and each column represents the intensity of editing interaction between it and other users within the time window. The intensity value is the product of the total character length of the overlapping area between users and the time overlap ratio, reflecting the possibility of conflict in collaborative behavior.

[0070] "High-frequency interleaved editing" occurs when the system detects that, within a certain time window, there are more than a preset threshold number of users (denoted as a constant q), their editing areas have a high degree of overlap in content structure, and the frequency of these users' edits exceeds the system-set editing threshold. The edit update frequency is calculated by dividing the number of effective edits per user per unit time by the length of the time window. If this frequency continuously exceeds the preset editing threshold, the edit density in the area is significant and it is considered a high-risk area.

[0071] Once the above behavioral patterns are detected, the system flags them as conflict editing risk events. These event flags, along with the interaction density matrix, are fed into the content conflict index calculation module, which assesses the conflict intensity and potential error risk of the current contract during the multi-person editing phase. This approach closes the loop from low-level editing action collection, structured coding, relationship modeling, and risk event identification, providing stable and reliable data support for subsequent risk response.

[0072] The risk sign detection module adopts a combination rule judgment method to identify the continuous occurrence of preset event patterns. When the corresponding event pattern appears, it is marked as 1, and when it does not appear, it is marked as 0, and an event combination data string composed of 1 and 0 is obtained. If 1 appears in the event combination data string, a risk calculation trigger signal is output, triggering the subsequent data analysis module to enter the calculation state.

[0073] In this invention, the Risk Sign Detection Module determines whether there are potential anomalies in the current electronic contract approval process and multi-person editing process that require initiating a risk assessment. To accurately capture risk signals with low latency, this module employs a recognition mechanism based on combined rule judgments, combining structured data input from the Process Monitoring Module and the Edit Tracking Module to monitor and identify a set of pre-defined event patterns.

[0074] "Event patterns" are a collection of risk indicators predefined by the system during the modeling phase. Each event pattern corresponds to a local characteristic that could lead to process anomalies or content conflicts. For example, event patterns might include: "Two consecutive transfer failures at a certain approval node," "The same contract version is overwritten by three or more users within five minutes," "Processing time fluctuation exceeds a threshold percentage of previous and next nodes," and "The number of characters in the overlapping edit area exceeds a set threshold." The system will test these event patterns one by one during each time period.

[0075] During actual operation, the system assigns a location to each event pattern according to chronological order and logical numbering, and Boolean codes them based on the detection results. If an event pattern occurs within the current detection cycle, its corresponding location is marked as "1"; if it is not detected, it is marked as "0". The judgment results of multiple event patterns are arranged in bit sequence to form a fixed-length event combination data string. For example, a detection window containing six event patterns may produce a data string of "010010".

[0076] The system performs rule matching on the data string to determine whether any bit is "1." If one or more event patterns are activated, meaning a "1" appears in the data string, the system identifies a risk indicator in the current approval or editing process and immediately outputs a risk calculation trigger signal. This signal acts as a control signal, sending a task instruction to the data analysis module, initiating the calculation of the process anomaly index and content conflict index.

[0077] The calculation method of the process anomaly index in the data analysis module is:

[0078] The approval process is modeled as a directed graph structure, where nodes represent approval operations and edges represent flow directions. The graph structure is vectorized using a graph embedding algorithm. Then, the abnormal subpath vectors and the standard process vectors are extracted. The process abnormality index FI is defined as the distance between the two: ; Embedding vector i-th dimension component of the current approval process diagram, is the i-th dimension component of the embedding vector of the standard approval flowchart, is the impact factor corresponding to the process structure of the i-th dimension, indicating the importance weight assigned to this dimension in the approval process diagram, which is pre-set by the system based on the training data. It is a preset smoothing factor used to avoid the denominator being zero in the calculation. The value is a positive real number less than 1 (such as 0.01). It is often set to a constant to avoid division by zero errors. n is the dimension of the embedding vector.

[0079] In the present invention, the process anomaly index (FI) is used to measure the degree of structural deviation between the currently executed approval process and the preset standard process. This index compares the high-dimensional representation of the embedded paths in the graph structure, quantifies the differences between the two in terms of structural form, path logic, or node layout, and thus reflects whether the process has deviated from the standard execution track. The larger the FI value, the more significant the structural difference between the current process and the standard process, and the higher the potential anomaly risk. When the FI value approaches zero, it indicates that the process operation status is highly consistent with the standard path and is within the normal range.

[0080] FI calculation is based on modeling the entire approval process as a graph structure. Using a graph embedding algorithm, the entire process is encoded into a multidimensional vector. Each dimension in this vector, i-th dimension, represents information about the flowchart along a specific structural feature dimension. Each i represents an interpretable process feature, such as the relative position of a node type in the flowchart, branch depth, path closure, node aggregation, cross-layer jump probability, and loop nesting level. These dimensions collectively constitute the embedding space of the process structure, representing the geometric characteristics of the process in a high-dimensional semantic space.

[0081] For example, if one dimension, i, corresponds to the concentration of conditional branch nodes in a flowchart, then this dimension can be used to measure whether the flowchart contains excessive nonlinear paths or redundant judgment logic. Another dimension might correspond to the density of parallel nodes, reflecting the presence of unusual multi-role concurrent execution paths within the process. Another dimension might reflect the average length of jump paths, thus detecting structural jumps or excessive path compression. When the current process's values on these dimensions differ significantly from the standard process, the distance value in the corresponding dimension will be amplified, ultimately driving an increase in the overall FI value and prompting the system to alert or intervene in the execution status of the process.

[0082] FI not only provides a comprehensive quantitative score of process behavior anomalies, but also offers interpretable internal structure. Each process structural feature represented by the i-dimension is mapped from the actual flow diagram structure through graph embedding and data modeling, ensuring FI's data-driven nature and consistency with business semantics. This index, a core component of the risk identification model used in this invention, provides a clear, quantitative, and traceable basis for subsequent risk level reasoning and response strategy decisions.

[0083] The calculation method of the content conflict index in the data analysis module is:

[0084] Within the unit time window T, extract the set of content blocks edited by all users, record the editing status of each content block, and construct the editing density function: ; Same document location Edit frequency, For the The document location corresponding to the editing operation, is the document position index point currently being evaluated, m is the total number of all editing operations within the time window, is the content distribution diffusion coefficient, which indicates the degree of discreteness of editing behavior on the document. The calculated document position index point The corresponding edit density value; ; ; is the average value of all edit positions;

[0085] Introducing content crossover rate : ; Indicates the number of content segments where multi-user editing occurs. Indicates the total number of content segments;

[0086] The maximum editing density value is recorded as , and content crossover rate Combined content conflict index: ; Indicates the content conflict index.

[0087] In this paper, the Content Conflict Index (CI) is used to measure the high-risk phenomenon of agglomeration of editing activities within a content area and cross-editing activities by multiple users during the collaborative editing of a contract document. This index reflects the intensity of concentrated modification of a document within a specific time window, as well as the probability of conflicts that may arise from frequent editing by multiple users in the same area. Higher CI values indicate greater overlap in editing within the current collaborative environment, higher cross-editing frequency, and a higher risk of issues such as missigning, erroneous changes, and lost coverage.

[0088] The system constructs an editing density function to obtain the editing concentration of the contract content area within a unit time window, determine whether there are obvious hot spots, and calculate the content cross-editing rate by counting the proportion of content segments that actually undergo multi-user cross-editing. The core significance of CI lies in the fusion modeling of two types of risks: spatial density and collaborative cross-editing, thereby achieving a quantifiable assessment of the degree of chaos in collaborative editing. In the exponential function, the square term of the content distribution diffusion coefficient is treated as a protective additive constant to avoid gradient explosion or numerical instability caused by an excessively large exponential function. CI, as a key indicator in the system to support content conflict identification and response, can achieve pre-judgment of risky behaviors and ensure the stability and controllability of the contract editing stage.

[0089] The maximum edit density value represents the document location with the most concentrated editing behavior within the current time window, which is the "high-risk area" where version conflicts or edit conflicts are most likely to occur. By using the maximum value rather than the mean, the system can capture extreme collaborative editing risks more sensitively and promptly, thereby effectively triggering the system's early warning and response mechanism. The maximum edit density value will be combined with the content intersection rate to form the content conflict index, which is used to quantify the intensity of collaborative conflicts that may arise during the multi-person editing process. The content conflict index CI can not only be used to determine whether the current collaborative operation requires permission adjustment or behavior throttling, but can also be used as one of the important input variables for judging the joint risk level in fuzzy reasoning, thereby ensuring the content integrity, version clarity and signing accuracy during the contract editing stage, and improving the quality of contract collaboration and the overall stability of the contract management system.

[0090] The joint identification module performs fuzzy reasoning based on the combined results of the process anomaly index FI and the content conflict index CI. FI and CI are divided into three levels: "low", "medium" and "high" according to the preset fuzzy membership function. For example, interval mapping is achieved through a triangular membership function. The reasoning rule is as follows: if FI is "high" and CI is "high", the reasoning result is "serious risk";

[0091] If FI is "medium" and CI is "high", the inference result is "heavier risk";

[0092] If FI is "high" and CI is "medium", the inference result is "medium risk";

[0093] If both are “low”, the inference result is “normal risk”;

[0094] The inference results are quantified into four levels of output signals, with corresponding values of 0, 1, 2, and 3, representing normal, moderate, severe, and serious risks, respectively.

[0095] To avoid unclear response strategies caused by the fuzzy boundaries of risk indices, this system introduces a joint risk level determination mechanism based on fuzzy set theory. This mechanism no longer uses absolute numerical values for rigid classification. Instead, it uses fuzzy logic to map the two input risk indices to three levels: low, medium, and high. Based on the combined relationship between the two, an overall joint risk level is derived.

[0096] The system uses the process anomaly index and content conflict index as two-dimensional inputs, defining their fuzzy membership relationships on the numerical axis. By establishing three sets of membership functions, the original numerical values are mapped to membership degrees. Each membership degree represents the likelihood that the index belongs to a certain risk level. The system then matches the combination of the two inputs in the fuzzy space with the four joint risk levels based on a predefined rule table, outputting a final risk level signal that guides the response module in selecting the appropriate intervention strategy.

[0097] To implement numerical processing of fuzzy logic inputs, the system constructs three sets of fuzzy membership functions for each of the two risk indices, corresponding to the "low," "medium," and "high" levels. The membership functions are modeled using symmetrical trigonometric functions, with adjustable control points and easy-to-implement numerical solutions. Each function has a maximum membership at its center, with linearly descending boundaries extending to the left and right.

[0098] For example, the trigonometric function for a given input at a "medium" level has a symmetrical peak range, with the left and right boundaries set to the average of the index's low and high thresholds. This trigonometric function construction ensures a smooth transition between boundaries, effectively avoiding misjudgments of critical values. Furthermore, the fuzzy processing for the process anomaly index and the content conflict index are independent, facilitating separate modeling and maintenance. Within the two-dimensional fuzzy space, the system uses a matrix-based approach to evaluate nine combinations, corresponding to four output risk levels: normal, medium, severe, and critical.

[0099] The system has several pre-set basic rules in its fuzzy rule base. For example, if both the process anomaly index and the content conflict index are high, the system outputs a "serious risk" signal; if the process anomaly index is medium and the content conflict index is high, the system outputs a "heavy risk" signal; if the process anomaly index is high and the content conflict index is medium, the system outputs a "medium risk" signal; and if both are low, the system outputs a "normal risk" signal.

[0100] The final risk level is determined by the maximum membership value calculated by the fuzzy inference engine. The output risk level is mapped into a fourth-order discrete control signal corresponding to four policy levels. This signal is input into the response module, which determines whether to perform actions such as path reconstruction, permission restriction, logging, or manual intervention. Through the fuzzy inference mechanism, the system automatically converts fuzzy data into clear response strategies, making risk assessment more stable and adaptable in uncertain environments.

[0101] The response decision module includes the following strategy selection mechanisms:

[0102] If the risk level is severe, the approval process is suspended, all editing permissions are locked, and administrator intervention is mandatory. If the fuzzy reasoning module determines the current joint risk level is severe, indicating that the approval process structure deviates significantly from the standard path and that multiple edits in the same area overlap significantly, posing a serious risk of overstepping authority, skipped reviews, or incorrect version signing, the response decision module immediately triggers the system's highest-level intervention mechanism. The system first suspends the entire approval process for the current contract, freezing the approval status and preventing further progress. It also locks all editing permissions for the current document, preventing any user from making changes. The system then sends a high-priority intervention notification to the designated administrator or contract owner, requiring manual intervention. This notification includes the contract number, trigger time, two index values, and diagnostic recommendations. The administrator must repair the process structure or review and confirm the document content before the lock can be lifted and the process reactivated. This level of response ensures that even in high-risk scenarios, the system can immediately control the spread of risk, safeguarding the legality of the contract and data security.

[0103] If the risk level is severe, multiple users are restricted from editing and conflicting nodes in the approval path are rebuilt. When the system determines the joint risk level is severe, it typically indicates process configuration anomalies, such as unusually frequent node jumps, an increased likelihood of path interruption, and, while multiple edits may not completely overlap, a significant crossover in adjacent content areas. While these risks are not uncontrollable, they can easily escalate into severe issues without timely intervention. Therefore, the system automatically implements moderate intervention measures. These measures include dynamically restricting collaborative editing permissions on documents, allowing only one user to make changes within critical content areas, while other users enter read-only or delayed editing mode to prevent escalating conflicts. Furthermore, the system identifies problematic nodes in the approval path with frequent, unusual jumps or duplicate node processing, reconstructs local paths, and updates the exception boundaries within the flowchart structure. The system also records interventions and sets a monitoring period. If several pre-emptive actions are invalid or the risk increases again, the process automatically escalates to a severe level. This strategy combines automatic prevention and control with manual intervention to ensure that escalating risk trends are promptly suppressed within a manageable range.

[0104] If the risk level is medium, an alert is issued and a risk log is recorded. When the system identifies a medium combined risk level, it indicates that the process structure and content collaboration are generally within control, with only minor fluctuations in some indicators. For example, there may be local anomalies in approval processing time or overlap in editing behavior in certain sections, but not to the point of conflict. In this case, the system adopts a low-intensity response mechanism, primarily an alert. The response module generates a comprehensive risk alert log, including process structure deviations, user editing behavior trends, triggered event pattern types, and the estimated impact. This log is stored in the risk profile area of the contract management platform, and a notification is simultaneously sent to the contract collaboration group or responsible individual's email address, prompting attention to the current risky behavior. If the user subsequently makes proactive adjustments or the behavior naturally stabilizes, the system automatically lifts the alert. If the risk index increases, the system enters a more severe level of processing. This mechanism demonstrates the system's flexible judgment capability, avoiding unnecessary interference with the normal collaborative process while maintaining a full audit record.

[0105] If the risk level is normal, no intervention is made but the behavior data is archived. When the joint risk level is judged to be normal, it means that the current contract approval process structure is highly consistent with the standard template, no abnormal path behavior has been detected, and there is no high-frequency interleaving or content aggregation risk in the collaborative editing process. In this scenario, the system does not actively perform any intervention operations, and contract approval and editing behaviors can proceed normally. However, to support subsequent behavior analysis and strategy optimization, the system will package and archive the current approval process and collaborative behavior data, and store them in the data training library of the risk identification module for updating risk models and indicator weights. This type of "normal sample" will be compared with subsequent risk events to enhance the system's risk identification capabilities and the adaptability of fuzzy rules, thereby continuously optimizing model performance. This mechanism ensures business efficiency while achieving long-term evolution and self-optimization of system performance.

[0106] The response decision module also includes a supervision mechanism:

[0107] After each risk response is triggered, the following three indicators are recorded: process repair success rate, conflict reduction rate, and approval acceleration. These three indicators are then subjected to polynomial regression modeling. Based on the output data of the polynomial regression modeling, namely the improvement value, the least squares method is used to fit a fitting straight line between the improvement value and the response time. The slope of the fitting straight line is compared with the preset standard slope. If the slope of the fitting straight line is greater than or equal to the preset standard slope, the current response is valid. If the slope of the fitting straight line is less than the preset standard slope, the current response is invalid, and the manual intervention window mode is entered, forcing the administrator to intervene.

[0108] The process repair success rate measures whether the system successfully restores the abnormal process to a complete closed-loop state after executing the risk response strategy. The system tracks the process status after each triggered response. If the contract process successfully reaches the termination point (e.g., the contract is signed, the approval process is fully completed), the response is counted as "successful," otherwise it is counted as "failed." During the statistical period, the number of successes divided by the total number of responses yields the process repair success rate for that strategy. This metric primarily reflects the strategy's ability to recover from structural anomalies and is a key dimension in measuring the effectiveness of process stability repairs.

[0109] The conflict reduction rate reflects whether the response policy significantly reduces content conflicts caused by multiple editors before and after policy execution. The system collects the number of editing conflicts per unit time before and after policy execution. For example, repeated overwriting or cross-editing of paragraph content by different users within a short period of time is recorded as a conflict event. The conflict reduction rate compares the data collected twice, specifically the reduction in the number of conflicts divided by the total number of conflicts collected before. This metric is used to evaluate the policy's effectiveness in controlling content editing consistency and version security.

[0110] The Approval Acceleration metric measures whether the response strategy has improved the efficiency of the overall approval process after implementation. The system calculates the total time taken for contract approval from process initiation to completion and averages this across multiple contract instances. The average approval time before and after the response is compared to determine the Approval Acceleration metric. This metric measures the strategy's contribution to improving approval efficiency and is particularly useful for assessing issues such as process congestion and node delays.

[0111] The core objective of the monitoring mechanism is to determine a strategy's ability to continuously improve in real-world applications. The system constructs a polynomial regression model to fit the response effect and, using the least squares method, calculates the slope of a trend curve showing the evolution of the improvement value with the number of responses. This allows the system to determine whether the strategy has positive optimization potential. If the fitted trend slope is higher than or equal to the preset evaluation standard, it indicates that the strategy is gradually producing positive results over multiple consecutive executions, and the system marks it as "effective." If the slope is lower than the standard, it indicates that the strategy's effectiveness is unstable or ineffective over a long period of time. The system will suspend automatic responses and force the system into a manual intervention window, requiring the administrator to reassess the process and document status.

[0112] Implementation method 1: Cross-departmental contract collaborative approval scenario for large enterprises:

[0113] In a large enterprise with multiple business units, electronic contracts often involve collaborative approvals from multiple business departments. The process levels are complex, there are many roles, and there is a high risk of path configuration conflicts and approval interruptions. The implementation method of this system in this type of scenario is: through the process monitoring module, a global node map is established, and the graph neural structure is used to extract the logical jump relationship between the nodes of each department; combined with the time matrix analysis, the system can find that there are problems such as cross-department transfer interruptions or large fluctuations in approval response time in the approval nodes. During the operation of the system, once abnormal behaviors such as role duplication, path loops, or continuous timeouts of approval actions are identified in the approval path, the risk symptom detection module triggers a risk calculation signal, and then quantifies the risk level through the process anomaly index model. For serious levels, the system will suspend the current process and execute the node reconstruction strategy, and notify the relevant business person in charge to confirm the path, so as to ensure that the contract approval can be completed in an online closed loop.

[0114] Implementation Method 2: Multi-person contract editing scenario in a remote office environment:

[0115] In an enterprise's remote work model, multiple employees may edit the same draft contract simultaneously at different times and locations, which can easily lead to version confusion and incorrect signatures. The system's implementation in this scenario involves: activating the behavior encoding submodule within the edit tracking module to record the editing action sequences of all online users, including editing time, location, and paragraph content; Simultaneously, a collaborative interaction matrix is constructed to analyze whether multiple users frequently and alternately edit adjacent paragraphs within a short period of time. When high-frequency interleaved editing behavior is identified within a unit time window, the system marks this as a content conflict risk and initiates a content conflict index calculation mechanism, combining the diffusion coefficient and crossover rate to determine the degree of conflict. If the risk level is determined to be medium or above, the response decision module automatically locks the key area being operated by multiple users, retaining only the priority editor's permissions. It also sends collaborative editing reminders to encourage users to avoid editing conflicts. Finally, a regression mechanism is used to evaluate whether the intervention has achieved collaborative stability.

[0116] Implementation Method 3: Automatic Strategy Evolution Scenario Driven by Contract Approval Efficiency Optimization:

[0117] In business scenarios where approval efficiency is crucial, such as the procurement contract signing process within the supply chain, companies focus not only on approval success but also on approval speed and editing stability. Our system's implementation in these scenarios is as follows: The system's risk identification and response mechanisms are enabled by default, but with a greater emphasis on the effectiveness and self-optimization capabilities of intervention strategies. After each response action (such as limited editing, node reconstruction, and permission constraints), the system records three feedback metrics: process repair success rate, conflict reduction rate, and approval acceleration. These metrics are used as input to construct a polynomial regression prediction model, fitting a trend curve between the score output and the number of responses. The system then calculates the slope of this trend and compares it with pre-set criteria to determine the effectiveness of the current strategy. If the trend is positive and the growth rate is good, the system automatically records the strategy as a recommended path. If the trend slope continues to decline, the manual intervention module is triggered, allowing the administrator to evaluate the applicability of the current strategy and support strategy replacement or response plan adjustment, thus establishing data-driven risk response self-optimization capabilities.

[0118] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0119] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0120] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0121] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0122] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An electronic contract approval management system, characterized in that: include: The process monitoring module is used to obtain dynamic behavior data in the electronic contract approval process, including approval path flow, processing duration, and transfer failure events; The edit tracking module is used to collect editing trajectory data of contract documents in multi-person editing scenarios, including editing time distribution, content coverage area, and behavioral interaction sequences between concurrent users; The risk sign detection module is used to analyze process behavior data and editing trajectory data, and output a risk calculation trigger signal after detecting a combination of abnormal events; The data analysis module responds to risk trigger signals, constructs a multidimensional data set, and calculates two core indices for joint risk identification: the process anomaly index and the content conflict index, which are then used by downstream modules. The joint identification module performs fuzzy reasoning based on the process anomaly index and content conflict index to classify the joint risk level; The response decision module performs differentiated interventions based on risk level results, including process corrections, permission constraints, notification push, and log archiving; The calculation method of the content conflict index in the data analysis module is: Within the unit time window T, extract the set of content blocks edited by all users, record the editing status of each content block, and construct the editing density function: ; Same document location Edit frequency, For the The document location corresponding to the editing operation, is the document position index point currently being evaluated, m is the total number of all editing operations within the time window, is the content distribution diffusion coefficient, which indicates the degree of discreteness of editing behavior on the document. The calculated document position index point The corresponding edit density value; ; ; is the average value of all edit positions; Introducing content crossover rate : ; Indicates the number of content segments where multi-user editing occurs. Indicates the total number of content segments; The maximum editing density value is recorded as , and content crossover rate Combined content conflict index: ; Indicates the content conflict index.

2. An electronic contract approval management system according to claim 1, characterized in that: The process monitoring module further includes a node graph construction submodule and a time matrix analysis submodule. The node graph construction submodule abstracts the approval process into a node-edge data structure based on the graph neural structure, identifies disconnected segments and abnormal transfer paths, and the time matrix analysis submodule records the average residence time and fluctuation range of each node by constructing a time-node two-dimensional tensor structure. If the path jump probability exceeds the preset jump threshold, or the processing time standard deviation of a node exceeds the preset ratio threshold of the average processing time standard deviation of its adjacent nodes, it is determined to be an abnormal process behavior event.

3. An electronic contract approval management system according to claim 2, characterized in that: The editing tracking module further includes an editing behavior encoding submodule and a collaborative interaction matrix generation submodule. The former serializes and encodes the operations of each user to generate an editing behavior vector; the latter forms a user interaction density matrix by establishing an editing cross-relationship table between users. If more than q users have high-frequency interleaved editing behaviors in adjacent areas within a certain time window, it is identified as a conflict editing risk. All encoded data and matrix data enter the content conflict index construction model to provide input for the subsequent conflict intensity quantification. High-frequency interleaved editing behavior refers to the editing update frequency exceeding the preset editing threshold.

4. An electronic contract approval management system according to claim 3, characterized in that: The risk sign detection module adopts a combination rule judgment method to identify the continuous occurrence of preset event patterns. When the corresponding event pattern appears, it is marked as 1, and when it does not appear, it is marked as 0, and an event combination data string composed of 1 and 0 is obtained. If 1 appears in the event combination data string, a risk calculation trigger signal is output, triggering the subsequent data analysis module to enter the calculation state.

5. An electronic contract approval management system according to claim 4, characterized in that: The calculation method of the process anomaly index in the data analysis module is: The approval process is modeled as a directed graph structure, where nodes represent approval operations and edges represent flow directions. The graph structure is vectorized using a graph embedding algorithm. Then, the abnormal subpath vectors and the standard process vectors are extracted. The process abnormality index FI is defined as the distance between the two: ; Embedding vector i-th dimension component of the current approval process diagram, is the i-th dimension component of the embedding vector of the standard approval flowchart, is the impact factor corresponding to the process structure of the i-th dimension, indicating the importance weight assigned to this dimension in the approval process diagram. is a preset smoothing factor used to avoid the denominator being zero in the calculation, and n is the dimension of the embedding vector.

6. An electronic contract approval management system according to claim 5, characterized in that: The joint identification module performs fuzzy reasoning based on the combined results of the process anomaly index FI and the content conflict index CI. FI and CI are divided into three levels: "low", "medium", and "high" according to the preset fuzzy membership function. The reasoning rules are as follows: If FI is "High" and CI is "High", the inference result is "Serious Risk"; If FI is "medium" and CI is "high", the inference result is "heavier risk"; If FI is "high" and CI is "medium", the inference result is "medium risk"; If both are "low", the inference result is "normal risk"; The inference results are quantified into four levels of output signals, with corresponding values of 0, 1, 2, and 3, representing normal, moderate, severe, and serious risks, respectively.

7. An electronic contract approval management system according to claim 6, characterized in that: The response decision module includes the following strategy selection mechanisms: If the risk level is severe, the approval process is suspended, all editing permissions are locked, and administrator intervention is forced; If the risk level is high, restrict multiple people from editing and rebuilding conflicting nodes in the approval path; If the risk level is medium, issue an early warning and record a risk log; If the risk level is normal, no intervention is performed but the behavioral data is archived.

8. An electronic contract approval management system according to claim 7, characterized in that: The response decision module also includes a supervision mechanism: After each risk response is triggered, the following three indicators are recorded: process repair success rate, conflict reduction rate, and approval acceleration. These three indicators are then subjected to polynomial regression modeling. Based on the output data of the polynomial regression modeling, namely the improvement value, the least squares method is used to fit a fitting straight line between the improvement value and the response time. The slope of the fitting straight line is compared with the preset standard slope. If the slope of the fitting straight line is greater than or equal to the preset standard slope, the current response is valid. If the slope of the fitting straight line is less than the preset standard slope, the current response is invalid, and the manual intervention window mode is entered, forcing the administrator to intervene.

Images