Intelligent management system and method applied to evidence pollution platform

Abstract

The invention discloses an intelligent management system and method applied to an evidence pollution platform, and relates to the technical field of intelligent management.The method comprises the steps that historical data of the platform are collected and preprocessed, and then an evidence value evaluation model and a pollution risk evaluation model are constructed based on the historical data; the evidence value evaluation model is fused and combined with a PageRank algorithm and a weighted linear regression algorithm to generate a comprehensive evidence value score; the pollution risk assessment model is combined with a graph neural network algorithm and a random forest algorithm to output a comprehensive pollution risk score; the two scores are mapped to a two-dimensional coordinate system, the evidence value is taken as a horizontal axis, the pollution risk is taken as a longitudinal axis, four quadrants of high value-high risk, high value-low risk, low value-high risk and low value-low risk are divided, a dynamic evidence value-pollution risk double-coordinate decision-making mechanism is formed, and different processing is carried out.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to an intelligent management system and method applied to an evidence contamination platform. Background Art

[0002] The accuracy, reliability, and value assessment of evidence are crucial in many fields today. With the rapid development of information technology, evidence has become increasingly diverse, and the environments in which it is generated, disseminated, and used have become more complex. This has led to an increasing problem of evidence contamination, posing a severe challenge to evidence-based decision-making. How to effectively manage evidence contamination and ensure the integrity and reliability of the evidence chain has become a critical issue that needs to be addressed.

[0003] Traditional evidence value assessment techniques mostly rely on manual experience or simple indicators, which are highly subjective. It is difficult to quantify the true influence of evidence in a complex network environment and its propagation effect in citation relationships, and it cannot fully reflect the actual value of evidence. Pollution risk assessments are often based on simple judgments based on a few isolated features, lacking a systematic analysis of the propagation path, scope of impact, and potential hazards of pollution in complex association networks. This assessment method is not only difficult to accurately portray risks, but also lacks quantitative means, making risk assessment results often qualitative or rough, rather than precise quantitative scores. Existing technologies generally lack a systematic framework for integrating evidence value and risk information, making it difficult to formulate differentiated intelligent management strategies. Evidence processing processes are often unified or classified according to only a single dimension, failing to fully consider the coupling relationship between value and risk. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent management system and method applied to an evidence contamination platform to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solutions: In a first aspect, the present invention provides an intelligent management method applied to an evidence contamination platform, comprising: Collect historical data from the platform, including identified pollution incidents, frequency of evidence use, pollution source characteristics, pollution diffusion paths, correction effects, impact rankings, and citation counts in top journals, and pre-process the data; Based on preprocessed historical data, an evidence value assessment model and a pollution risk assessment model are constructed. The evidence value assessment model uses a weighted scoring fusion model algorithm, analyzes influence rankings and citation relationships through the PageRank algorithm, identifies high-impact evidence, extracts node importance, and uses a weighted linear regression algorithm to analyze the number of citations in top journals and the frequency of evidence use. A comprehensive evidence value score is calculated by combining the PageRank score and the linear regression weight score. The pollution risk assessment model constructs a graph data structure, uses the graph neural network algorithm (GNN) to extract risk features, and uses the random forest algorithm to establish a classification model for non-graph features. The GNN output and the classification model results are integrated to generate a comprehensive pollution risk score. The evidence value score and contamination risk score are mapped into a two-dimensional coordinate system, with the evidence value score as the horizontal axis and the contamination risk score as the vertical axis. A dual-coordinate decision-making mechanism of evidence value and contamination risk is established. Different risk areas and thresholds are set, and the quadrants are divided into high value-high risk quadrant, high value-low risk quadrant, low value-high risk quadrant and low value-low risk quadrant according to the order of update priority. Different processing strategies are assigned according to different quadrants.

[0006] In conjunction with the first aspect, in a first implementation of the first aspect of this application, the platform collects historical data, including identified pollution incidents, frequency of evidence use, pollution source characteristics, pollution diffusion paths, correction effects, influence rankings, and citation counts by top journals, and preprocesses the data, including: Collect historical data from the Evidence Pollution Platform, including identified pollution incidents, frequency of evidence use, pollution source characteristics, pollution diffusion paths, correction effects, impact rankings, and citation counts in top journals; Preprocess the collected platform historical data, fill missing values ​​with the mean or mode according to the data type and distribution, identify and process abnormal data points through the Z-score statistical method, delete duplicate records, and use regular expressions to standardize and denoise text data.

[0007] In conjunction with the first aspect, in the second implementation of the first aspect of this application, the evidence value assessment model uses a weighted scoring fusion model algorithm to analyze influence rankings and citation relationships through the PageRank algorithm, identify high-impact evidence, extract node importance, and analyze the number of citations in top journals and the frequency of use of evidence through a weighted linear regression algorithm, including: The PageRank algorithm is used to iteratively calculate the evidence nodes and their citation relationship network. Based on the quality and quantity of the node's inlinks, the relative influence of each evidence node in the network is evaluated and quantified, and a node importance score based on the network structure is generated. The calculation formula is: ; Where PR(A) is the PageRank score of evidence node A, representing the influence of evidence node A in the evidence network; d is the damping coefficient, representing the probability that the user continues to click on the link; 1-d is the complement of the damping coefficient, representing the probability that the user does not continue to click on the link; B(A) is the set of all evidence nodes pointing to evidence node A; PR(T) is the PageRank score of evidence node T, representing the influence of evidence node T in the evidence network; C(T) is the number of external links of evidence node T; Collect and organize the number of citations in top journals and the frequency of use within the platform for each piece of evidence using the following formula: ; Among them, Y is the evidence value score, X1 is the number of citations in top journals, X2 is the frequency of evidence use, β0 is the intercept, β1 and β2 are regression coefficients, indicating the degree of influence of each variable on the dependent variable. is the error term; A weighted linear regression model was constructed, with the value of evidence as the dependent variable and the number of citations in top journals and the frequency of evidence use as independent variables. Different weights were assigned according to the historical revision effect or influence ranking of the evidence. A regression equation was fitted to quantify these two factors and generate an evidence value score based on the statistical relationship. The formula is: ; w i is the weight of the i-th sample, which adjusts the importance of the sample in the regression model according to the historical correction effect or influence ranking of the evidence; Y i is the actual value of the i-th sample; is the predicted value of the i-th sample; n is the number of samples; the formula finds the regression coefficient and fits the regression equation by minimizing the weighted residual sum of squares; where the weighted linear regression score LR is equal to the predicted value of the regression model .

[0008] In combination with the first aspect, in a third implementation of the first aspect of the present application, the calculation of the comprehensive evidence value score by combining the PageRank score and the linear regression weight score includes: The PageRank score PR (A) and the weighted linear regression score LR are weighted and fused according to the preset weights to generate the final comprehensive evidence value score V. The formula is: ; Among them, V is the final generated comprehensive evidence value score, which represents the overall value of a certain evidence node; α is a weight coefficient between 0 and 1, which indicates the proportion of PageRank score PR (A) in the final score V; 1-α indicates the proportion of weighted linear regression score LR.

[0009] In combination with the first aspect, in a fourth implementation of the first aspect of the present application, the pollution risk assessment model constructs a graph data structure, uses a graph neural network algorithm (GNN) to extract risk features, and uses a random forest algorithm to establish a classification model for non-graph features, including: Evidence entities, users, and interaction relationships are abstracted into nodes and edges in a graph, forming graph data that can represent the flow and association of evidence. This constructed graph data is input into a graph neural network model. The GNN learns the representation of nodes in the graph structure layer by layer by aggregating the features of the node itself and the features of its neighboring nodes, thereby capturing risk patterns. Collect and process the non-graph structure features of evidence and train a random forest classifier; random forest classifier determines whether the evidence has contamination risk by constructing multiple decision trees and synthesizing the prediction results.

[0010] In combination with the first aspect, in a fifth implementation of the first aspect of this application, the fusion of the GNN output and the classification model results to generate a comprehensive pollution risk score includes: The structured risk features extracted by GNN are integrated with the non-graph features used by random forest to comprehensively judge the contamination risk or probability of evidence. The formula is: ; Among them, FRS is the final fused comprehensive pollution risk score; GS is the pollution risk score output by the graph neural network model; RS is the pollution risk score output by the non-graph feature model; θ is the weight coefficient, which is used to adjust the relative importance of GS and RS, with a value of 0 to 1.

[0011] In conjunction with the first aspect, in a sixth implementation of the first aspect of the present application, the evidence value score and the pollution risk score are mapped into a two-dimensional coordinate system, with the evidence value score as the horizontal axis and the pollution risk score as the vertical axis, to establish an evidence value-pollution risk dual-coordinate decision-making mechanism, including: The evidence value score and contamination risk score are mapped into a two-dimensional coordinate system. The horizontal X-axis represents the evidence value score, which reflects the importance, relevance, and probative force of the evidence to the case. The higher the score, the greater the potential role of the evidence in the case. The vertical Y-axis represents the contamination risk level score, which reflects the possibility or severity of evidence contamination. The higher the score, the lower the reliability of the evidence and the greater the risk of misleading the judgment of the case. By plotting the two scoring values ​​of each piece of evidence into the coordinate system, an evidence point is formed. The specific position of the evidence point in the coordinate system reflects the comprehensive status of the value and risk of the evidence.

[0012] In conjunction with the first aspect, in a seventh implementation of the first aspect of the present application, the setting of different risk areas and thresholds is divided into a high value-high risk quadrant, a high value-low risk quadrant, a low value-high risk quadrant, and a low value-low risk quadrant in order of update priority, including: According to the established two-dimensional coordinate system of evidence value and contamination risk, thresholds are set for the evidence value score and contamination risk score, and the four quadrants are set as high value-high risk quadrant, low value-high risk quadrant, low value-low risk quadrant and high value-low risk quadrant respectively; The high-value-high-risk quadrant is located in the upper right corner of the coordinate system, where the evidentiary value and contamination risk of the evidence are higher than their respective preset thresholds. This type of evidence has a great impact on the case, but its reliability is questionable. It is an area that requires the highest priority attention and processing; the high-value-low-risk quadrant is located in the lower right corner of the coordinate system, where the evidentiary value is higher than the preset evidentiary value threshold, and the contamination risk is lower than the preset contamination risk threshold. This type of evidence has a great impact on the case and a low contamination risk, and requires second priority identification and processing; the low-value-high-risk quadrant is located in the upper left corner of the coordinate system, where the evidentiary value is lower than the preset evidentiary value threshold, and the contamination risk is higher than the preset contamination risk threshold. This type of evidence does not interfere much, but is highly risky, and requires third priority identification and processing; the low-value-low-risk quadrant is located in the lower left corner of the coordinate system, where the evidentiary value and contamination risk are lower than their respective preset thresholds, and this type of evidence has the lowest priority for updating.

[0013] In conjunction with the first aspect, in an eighth implementation of the first aspect of the present application, allocating different processing strategies according to different quadrants includes: For evidence in the high-value-high-risk quadrant, when the frequency of use of the evidence exceeds the preset frequency threshold, the highest level of handling measures will be initiated; comprehensive pollution source tracking and feature analysis will be carried out, and this information will be correlated and compared with the platform's historical pollution event database to identify the pollution source and potential transmission mode; cross-disciplinary experts will be organized to assess the impact of the pollution, and the scope and depth of the pollution will be determined by referring to the correction effect records of similar pollution in low-value-high-risk evidence; mandatory pollution elimination or evidence isolation measures will be implemented, and the entire handling process will be recorded; For evidence in the high-value-low-risk quadrant, when the frequency of use of the evidence exceeds the preset frequency threshold, intermediate handling measures will be initiated; its low-risk status will be confirmed, and it will be prioritized in case analysis, with its utilization and correction effects recorded; it will be prioritized as key evidence, and its specific role and effect in the case advancement will be recorded; regular monitoring will be implemented, and the monitoring data will be compared and analyzed with the monitoring data of high-value-high-risk evidence to form a risk warning linkage; the need for additional protective measures to prevent future contamination will be assessed, and the processing process and effect records will be fed back to the high-value-high-risk quadrant for reference; For evidence in the low-value-high-risk quadrant, when its usage frequency exceeds a preset frequency threshold, basic treatment measures are initiated; risk technical assessment is conducted to confirm the contamination status and high-risk attributes; contamination removal is performed or marked as not adopted and excluded, with removal being prioritized to reduce risk; treatment results are archived and fed back into model updates, while the treatment strategy is used as a reference and linked to the decision-making process in the low-value-low-risk quadrant; For evidence in the low-value-low-risk quadrant, when the frequency of use of the evidence is lower than the preset frequency threshold, the minimum processing measures are initiated; after confirming the low risk, a standardized archiving process is adopted, a low-value label is added, and it is retrieved under specific retrieval requests, and its usage is monitored, and its processing process is fed back to the high-value-low-risk quadrant.

[0014] In a second aspect, the present invention provides an intelligent management system applied to an evidence contamination platform, comprising: Data collection and preprocessing module: includes a data collection unit and a data preprocessing unit; the data collection unit collects platform historical data; the data preprocessing unit preprocesses the collected platform historical data, identifies and processes missing values, detects and processes abnormal data points, deletes duplicate records, and standardizes and denoises text data; Evidence Value Assessment Module: This module includes an influence analysis unit, a statistical relationship analysis unit, and an evidence value scoring fusion unit. The influence analysis unit uses the PageRank algorithm to analyze evidence nodes and citation relationship networks and calculate the PageRank score of each evidence node. The statistical relationship analysis unit collects and organizes data on the number of times evidence is cited in top journals and the frequency of use within the platform, constructs a weighted linear regression model, analyzes the impact of these two factors on the value of evidence, and generates an evidence value score. The evidence value scoring fusion unit performs a weighted fusion of the PageRank score and the weighted linear regression score according to preset weights to generate a final comprehensive evidence value score. Pollution risk assessment module: includes a structured risk extraction unit, a non-graph feature processing unit, and a risk score fusion unit. The structured risk extraction unit abstracts evidence entities, users, and the interactions between them into nodes and edges in a graph data structure, forming graph data, which is input into the graph neural network (GNN) model to capture and output a risk feature score based on the graph structure. The non-graph feature processing unit collects and processes the non-graph structural features of the evidence, trains a random forest classifier, determines whether the evidence poses a pollution risk, and outputs a risk score based on the non-graph features. The risk score fusion unit fuses the structured risk score with the non-graph feature risk score to generate the final comprehensive pollution risk score. Evidence value-contamination risk coordinate system construction module: includes a coordinate mapping unit and a quadrant division unit. The coordinate mapping unit receives the evidence value score and the contamination risk score and maps each evidence point into a two-dimensional coordinate system, where the horizontal axis represents the evidence value score and the vertical axis represents the contamination risk score. The quadrant division unit divides the two-dimensional coordinate system into four quadrants based on a preset threshold, namely the high value-high risk quadrant, the high value-low risk quadrant, the low value-high risk quadrant, and the low value-low risk quadrant. Evidence processing strategy decision module: includes a priority and level determination unit, a threshold judgment and status confirmation unit, and a strategy matching and generation unit; among them, the priority and level determination unit determines the processing priority order and level of the evidence according to the quadrant where the evidence point is located in the coordinate system, in accordance with the preset priority rules and processing levels; the threshold judgment and status confirmation unit checks whether the specific attributes of the evidence in a specific quadrant meet the specified threshold conditions, and for the evidence that meets the conditions, confirms the specific status within the quadrant; the strategy matching and generation unit combines the quadrant where the evidence is located, the determined processing level and the results of the threshold judgment and status confirmation unit, accurately matches and generates corresponding processing strategies from the predefined strategy library, generates specific, executable operations or suggestions, and implements feedback and linkage between strategies.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This paper combines the PageRank algorithm and the weighted linear regression model to achieve a comprehensive quantitative scoring of the value of evidence. It uses graph neural networks to process structured risk features and combines them with random forests to process non-graph features, and then fuses the results of the two to generate a comprehensive pollution risk score.

[0016] 2. The present invention maps the quantified evidence value score and pollution risk score into a two-dimensional coordinate system to construct an evidence value-pollution risk dual-coordinate decision-making mechanism, and divides the evidence into four quadrants according to preset thresholds.

[0017] 3. The present invention designs clear priorities and differentiated processing strategies for evidence in different quadrants, taking into account the current status and dynamic conditions of the evidence. The processing flows and results of different quadrants feed back each other to form linkage and closed-loop optimization between strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of the steps of an intelligent management method applied to an evidence contamination platform according to the present invention; Figure 2 This is a system structure diagram of an intelligent management system applied to an evidence contamination platform of the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe 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.

[0020] Example: Figure 1-Figure 2 As shown, the present invention provides a technical solution. like Figure 1 As shown in a schematic diagram of the steps of an intelligent management method applied to an evidence contamination platform, the present invention provides an intelligent management method applied to an evidence contamination platform, comprising: Step S100: Collect historical data from the platform, including identified pollution incidents, frequency of evidence use, pollution source characteristics, pollution diffusion paths, correction effects, impact rankings, and citation counts in top journals, and pre-process the data; Specifically, historical data from the Evidence Pollution Platform is collected, including identified pollution incidents, frequency of evidence use, pollution source characteristics, pollution diffusion paths, correction effects, impact rankings, and citation counts in top journals; Preprocess the collected platform historical data, fill missing values ​​with the mean or mode according to the data type and distribution, identify and process abnormal data points through the Z-score statistical method, delete duplicate records, and use regular expressions to standardize and denoise text data.

[0021] In one specific example, raw logs and event records from January 2020 to December 2024 were exported from the evidence contamination platform's backend database, resulting in the collection of 237 identified contamination event records. Frequency data for 15,842 pieces of evidence on the platform was collected, revealing that evidence E-7821 was used 187 times throughout 2024, while evidence E-9534 was used only three times. Contamination event ID-105 was characterized as "Malicious script injection, targeting evidence E-7821." Records showed that evidence E-7821 was cited in three other articles, spreading the contamination to these three citing pieces of evidence. Correction effectiveness data, including correction records for contamination event ID-105, showed that the accuracy of evidence E-7821 improved from 72% to 95% after correction. Impact ranking data, derived from the platform's internal evaluation model, ranked evidence E-7821 12th. In terms of citations in top journals, evidence E-7821 received eight citations. During the preprocessing phase, it was discovered that the pollution source characteristic field for evidence E-4567 was missing. Since this field was categorical data, it was filled in using the mode "error label." When using the Z-score method to process the frequency of use data, it was discovered that evidence E-7821's 187 uses far exceeded the average of 45, with a Z-score greater than 3, identifying it as an outlier. Verification confirmed that its high frequency of use was correlated with the importance of the evidence, so this data point was retained. However, other obviously erroneous records with Z-scores greater than 3 were corrected or deleted. Three completely duplicate evidence records due to system errors were deleted, and regular expressions were used to clean and standardize excess spaces and special symbols in text fields.

[0022] Step S200: Based on the pre-processed historical data, an evidence value assessment model and a contamination risk assessment model are constructed. The evidence value assessment model uses a weighted scoring fusion model algorithm to analyze influence rankings and citation relationships using the PageRank algorithm, identify high-impact evidence, extract node importance, and analyze the number of citations in top journals and the frequency of use of evidence using a weighted linear regression algorithm. The PageRank score and linear regression weight score are combined to calculate a comprehensive evidence value score. Specifically, the PageRank algorithm is used to iteratively calculate the evidence nodes and their citation relationship network. Based on the quality and quantity of the node's inlinks, the relative influence of each evidence node in the network is evaluated and quantified, and a node importance score based on the network structure is generated. The calculation formula is: ; Where PR(A) is the PageRank score of evidence node A, representing the influence of evidence node A in the evidence network; d is the damping coefficient, representing the probability that the user continues to click on the link; 1-d is the complement of the damping coefficient, representing the probability that the user does not continue to click on the link; B(A) is the set of all evidence nodes pointing to evidence node A; PR(T) is the PageRank score of evidence node T, representing the influence of evidence node T in the evidence network; C(T) is the number of external links of evidence node T; Collect and organize the number of citations in top journals and the frequency of use within the platform for each piece of evidence using the following formula: ; Among them, Y is the evidence value score, X1 is the number of citations in top journals, X2 is the frequency of evidence use, β0 is the intercept, β1 and β2 are regression coefficients, indicating the degree of influence of each variable on the dependent variable. is the error term; A weighted linear regression model was constructed, with the value of evidence as the dependent variable and the number of citations in top journals and the frequency of evidence use as independent variables. Different weights were assigned according to the historical revision effect or influence ranking of the evidence. A regression equation was fitted to quantify these two factors and generate an evidence value score based on the statistical relationship. The formula is: ; w i is the weight of the i-th sample, which adjusts the importance of the sample in the regression model according to the historical correction effect or influence ranking of the evidence; Y i is the actual value of the i-th sample; is the predicted value of the i-th sample; n is the number of samples; the formula finds the regression coefficient and fits the regression equation by minimizing the weighted residual sum of squares; where the weighted linear regression score LR is equal to the predicted value of the regression model .

[0023] Furthermore, the PageRank score PR (A) and the weighted linear regression score LR are weighted and fused according to the preset weights to generate the final comprehensive evidence value score V. The formula is: ; Among them, V is the final generated comprehensive evidence value score, which represents the overall value of a certain evidence node; α is a weight coefficient between 0 and 1, which indicates the proportion of PageRank score PR (A) in the final score V; 1-α indicates the proportion of weighted linear regression score LR.

[0024] In a specific embodiment, two models are constructed using pre-processed historical data. For the evidence value assessment model, the PageRank algorithm is applied to analyze the citation relationship network between evidence. Evidence E-7821 has a high number and quality of incoming links in the network. After multiple iterative calculations, its PageRank score PR(A) finally converges to 0.087. At the same time, it is collected that the number of times the evidence was cited by top journals during the statistical period is 8 times, and the frequency of use within the platform is X2, which is 187 times. Construct a weighted linear regression model. According to the significant improvement in accuracy after correction and the 12th place in influence, a higher weight w is assigned to evidence E-7821. i is 1.5. The regression equation obtained after model fitting is Y=0.35X1+0.12X2+0.5, where β0=0.5, β1=0.35, and β2=0.12. Substituting X1=8 and X2=187, the weighted linear regression prediction score Ŷi of the evidence is 25.74. The PageRank score PR(A)=0.087 and the weighted linear regression score LR=25.74 are weighted and fused. The preset weight coefficient α is set to 0.3, indicating that the influence of the network structure accounts for 30%, then 1-α=0.7. The comprehensive evidence value score V of evidence E-7821 is ≈18.044. Through similar calculations, a comprehensive value score V can be calculated for all evidence on the platform.

[0025] Step S300: The pollution risk assessment model constructs a graph data structure, uses the graph neural network algorithm (GNN) to extract risk features, and uses the random forest algorithm to build a classification model for non-graph features; the GNN output and the classification model results are integrated to generate a comprehensive pollution risk score; Specifically, evidence entities, users, and interaction relationships are abstracted into nodes and edges in a graph, forming graph data that can represent the flow of evidence and associations. This constructed graph data is then fed into a graph neural network model. The GNN learns the representation of nodes in the graph structure layer by layer by aggregating the features of the nodes themselves and those of their neighbors, thereby capturing risk patterns. Collect and process the non-graph structure features of evidence and train a random forest classifier; random forest classifier determines whether the evidence has contamination risk by constructing multiple decision trees and synthesizing the prediction results.

[0026] Furthermore, the structured risk features extracted by GNN are integrated with the non-graph features used by random forest to comprehensively judge the contamination risk or probability of evidence. The formula is: ; Among them, FRS is the final fused comprehensive pollution risk score; GS is the pollution risk score output by the graph neural network model; RS is the pollution risk score output by the non-graph feature model; θ is the weight coefficient, which is used to adjust the relative importance of GS and RS, with a value of 0 to 1.

[0027] In one specific embodiment, the evidence items, users, and interactions between them in the evidence contamination platform are constructed as a graph data structure. Evidence E-7821 is represented as a node, whose features include type, creation time, and source. User U-1024 downloads the evidence, and an edge is established between the user U-1024 node and the evidence E-7821 node, with the interaction type marked as download. The graph data, consisting of approximately 15,842 evidence nodes, 10,000 user nodes, and approximately 200,000 interaction edges between them, is input into a graph neural network (GNN) model. This GNN model undergoes three-layer training, aggregating the node's own features and those of its neighboring nodes to learn and output a risk representation for each node. For evidence E-7821, the GNN model outputs a risk score (GS) of 0.72. Furthermore, non-graph structural features of evidence E-7821 are collected, including its 187 usage frequencies, 8 citations in top journals, and a PageRank score of 0.087. A random forest classifier was trained using these features. The model outputs a probability, or score (RS), representing the contamination risk. The random forest model predicted a contamination risk score of 0.65 for evidence E-7821. The structured risk feature score (GS) from the GNN was fused with the non-graph feature score (RS) from the random forest. The weight coefficient θ was set to 0.6 to prioritize graph structure information. The calculated comprehensive contamination risk score (FRS) for evidence E-7821 was 0.692. This method allows a comprehensive contamination risk score (FRS) to be calculated for all evidence within the platform.

[0028] Step S400: Map the evidence value score and the contamination risk score into a two-dimensional coordinate system, with the evidence value score as the horizontal axis and the contamination risk score as the vertical axis, to establish a dual-coordinate decision-making mechanism for evidence value and contamination risk. Different risk areas and thresholds are set, and the quadrants are divided into high value-high risk quadrant, high value-low risk quadrant, low value-high risk quadrant, and low value-low risk quadrant in order of update priority. Specifically, the evidence value score and contamination risk score are mapped into a two-dimensional coordinate system. The horizontal axis (X) represents the evidence value score, which reflects the importance, relevance, and probative force of the evidence to the case. The higher the score, the greater the potential role of the evidence in the case. The vertical axis (Y) represents the contamination risk level score, which reflects the possibility or severity of evidence contamination. The higher the score, the lower the reliability of the evidence and the greater the risk of misleading the judgment of the case. By plotting the two scoring values ​​of each piece of evidence into the coordinate system, an evidence point is formed. The specific position of the evidence point in the coordinate system reflects the comprehensive status of the value and risk of the evidence.

[0029] Furthermore, based on the established two-dimensional coordinate system of evidence value and contamination risk, thresholds are set for the evidence value score and the contamination risk score, and the four quadrants are set as high value-high risk quadrant, low value-high risk quadrant, low value-low risk quadrant and high value-low risk quadrant respectively; The high-value-high-risk quadrant is located in the upper right corner of the coordinate system, where the evidentiary value and contamination risk of the evidence are higher than their respective preset thresholds. This type of evidence has a great impact on the case, but its reliability is questionable. It is an area that requires the highest priority attention and processing; the high-value-low-risk quadrant is located in the lower right corner of the coordinate system, where the evidentiary value is higher than the preset evidentiary value threshold, and the contamination risk is lower than the preset contamination risk threshold. This type of evidence has a great impact on the case and a low contamination risk, and requires second priority identification and processing; the low-value-high-risk quadrant is located in the upper left corner of the coordinate system, where the evidentiary value is lower than the preset evidentiary value threshold, and the contamination risk is higher than the preset contamination risk threshold. This type of evidence does not interfere much, but is highly risky, and requires third priority identification and processing; the low-value-low-risk quadrant is located in the lower left corner of the coordinate system, where the evidentiary value and contamination risk are lower than their respective preset thresholds, and this type of evidence has the lowest priority for updating.

[0030] In a specific embodiment, the threshold value of the evidence value score V is set to 20, and the threshold value of the contamination risk score FRS is set to 0.6. The comprehensive evidence value score V = 18.044 and the comprehensive contamination risk score FRS = 0.692 of evidence E-7821 are mapped to a two-dimensional coordinate system. Since V = 18.0441 is lower than the threshold value of 20, and FRS = 0.692 is higher than the threshold value of 0.6, the point of evidence E-7821 is drawn in the upper left corner area of ​​the coordinate system. According to the preset quadrant division rule, this area corresponds to the low value-high risk quadrant. This means that although the value of evidence E-7821 to the case is relatively low, its contamination risk is relatively high. According to the priority setting of this quadrant, evidence E-7821 is classified as evidence that requires the third priority to be identified and processed. Evidence E-1234 with an evidence value score of V=25.5 and a contamination risk score of FRS=0.55 will fall into the high value-low risk quadrant, and evidence E-5678 with an evidence value score of V=15.2 and a contamination risk score of FRS=0.7 will fall into the low value-high risk quadrant. They will be given different processing priorities.

[0031] In this way, all evidence on the platform is positioned in the coordinate system according to its evidence value score and contamination risk score, and clearly divided into four different quadrants, laying the foundation for the subsequent allocation of intelligent management strategies.

[0032] Step S500: Allocate different processing strategies according to different quadrants.

[0033] Specifically, for evidence in the high-value-high-risk quadrant, when the frequency of use of the evidence exceeds the preset frequency threshold, the highest level of handling measures will be initiated; comprehensive pollution source tracking and feature analysis will be carried out, and this information will be correlated and compared with the platform's historical pollution event database to identify the pollution source and potential transmission mode; cross-disciplinary experts will be organized to assess the impact of the pollution, and the scope and depth of the pollution will be determined by referring to the correction effect records of similar pollution in low-value-high-risk evidence; compulsory pollution elimination or evidence isolation measures will be implemented, and the entire handling process will be recorded; For evidence in the high-value-low-risk quadrant, when the frequency of use of the evidence exceeds the preset frequency threshold, intermediate handling measures will be initiated; its low-risk status will be confirmed, and it will be prioritized in case analysis, with its utilization and correction effects recorded; it will be prioritized as key evidence, and its specific role and effect in the case advancement will be recorded; regular monitoring will be implemented, and the monitoring data will be compared and analyzed with the monitoring data of high-value-high-risk evidence to form a risk warning linkage; the need for additional protective measures to prevent future contamination will be assessed, and the processing process and effect records will be fed back to the high-value-high-risk quadrant for reference; For evidence in the low-value-high-risk quadrant, when its usage frequency exceeds a preset frequency threshold, basic treatment measures are initiated; risk technical assessment is conducted to confirm the contamination status and high-risk attributes; contamination removal is performed or marked as not adopted and excluded, with removal being prioritized to reduce risk; treatment results are archived and fed back into model updates, while the treatment strategy is used as a reference and linked to the decision-making process in the low-value-low-risk quadrant; For evidence in the low-value-low-risk quadrant, when the frequency of use of the evidence is lower than the preset frequency threshold, the minimum processing measures are initiated; after confirming the low risk, a standardized archiving process is adopted, a low-value label is added, and it is retrieved under specific retrieval requests, and its usage is monitored, and its processing process is fed back to the high-value-low-risk quadrant.

[0034] In a specific embodiment, the value score V of evidence E-7821 is 18.0441, which is lower than the threshold of 20, and the risk score FRS is 0.692, which is higher than the threshold of 0.6, and is judged to be in the low value-high risk quadrant. Checking its attributes, it was found that the frequency of use was 210 times, which was higher than the preset frequency threshold of 150 times. According to the strategy, basic processing measures were initiated, and risk technical identification was carried out to confirm that it originated from a known high contamination risk source and that there were traces of data tampering, confirming its high-risk attributes; pollution elimination measures were implemented to remove the relevant contaminated data fragments, and the evidence was marked as "corrected, but for reference only"; the processing results were archived and fed back to the model update database, and its processing strategy was recorded as a reference for future processing of similar low value-low risk evidence decision-making processes.

[0035] Evidence E-1234, with a V=25.5, exceeding the threshold of 20, and an FRS=0.55, below the threshold of 0.6, is located in the high-value-low-risk quadrant. Its frequency of use was 180 times, exceeding the pre-set frequency threshold of 150. Based on the strategy, intermediate handling measures were initiated: its low-risk status was confirmed; it was prioritized for inclusion in the core analysis of the current complex case, with detailed documentation of its use to identify key facts, as well as minor modifications made after its use and their effects. This evidence was prioritized as key evidence in reporting and presentation, and its specific role in advancing the case was systematically documented. Simultaneously, regular monitoring was implemented, and its monitoring data was compared and analyzed with that of high-value-high-risk evidence to provide a reference for risk trends. Finally, the assessment determined that additional protection measures were necessary, restricting direct modification permissions at the system level. The entire handling process and results were fed back to the high-value-high-risk quadrant's handling strategy library, providing a reference for correction effects and monitoring models for future handling of similar high-value-low-risk but frequently used evidence.

[0036] like Figure 2 As shown in the system structure diagram of an intelligent management system applied to an evidence contamination platform, the present invention provides an intelligent management system applied to an evidence contamination platform, including: Data collection and preprocessing module: includes a data collection unit and a data preprocessing unit; the data collection unit collects platform historical data; the data preprocessing unit preprocesses the collected platform historical data, identifies and processes missing values, detects and processes abnormal data points, deletes duplicate records, and standardizes and denoises text data; Evidence Value Assessment Module: This module includes an influence analysis unit, a statistical relationship analysis unit, and an evidence value scoring fusion unit. The influence analysis unit uses the PageRank algorithm to analyze evidence nodes and citation relationship networks and calculate the PageRank score of each evidence node. The statistical relationship analysis unit collects and organizes data on the number of times evidence is cited in top journals and the frequency of use within the platform, constructs a weighted linear regression model, analyzes the impact of these two factors on the value of evidence, and generates an evidence value score. The evidence value scoring fusion unit performs a weighted fusion of the PageRank score and the weighted linear regression score according to preset weights to generate a final comprehensive evidence value score. Pollution risk assessment module: includes a structured risk extraction unit, a non-graph feature processing unit, and a risk score fusion unit. The structured risk extraction unit abstracts evidence entities, users, and the interactions between them into nodes and edges in a graph data structure, forming graph data, which is input into the graph neural network (GNN) model to capture and output a risk feature score based on the graph structure. The non-graph feature processing unit collects and processes the non-graph structural features of the evidence, trains a random forest classifier, determines whether the evidence poses a pollution risk, and outputs a risk score based on the non-graph features. The risk score fusion unit fuses the structured risk score with the non-graph feature risk score to generate the final comprehensive pollution risk score. Evidence value-contamination risk coordinate system construction module: includes a coordinate mapping unit and a quadrant division unit. The coordinate mapping unit receives the evidence value score and the contamination risk score and maps each evidence point into a two-dimensional coordinate system, where the horizontal axis represents the evidence value score and the vertical axis represents the contamination risk score. The quadrant division unit divides the two-dimensional coordinate system into four quadrants based on a preset threshold, namely the high value-high risk quadrant, the high value-low risk quadrant, the low value-high risk quadrant, and the low value-low risk quadrant. Evidence processing strategy decision module: includes a priority and level determination unit, a threshold judgment and status confirmation unit, and a strategy matching and generation unit; among them, the priority and level determination unit determines the processing priority order and level of the evidence according to the quadrant where the evidence point is located in the coordinate system, in accordance with the preset priority rules and processing levels; the threshold judgment and status confirmation unit checks whether the specific attributes of the evidence in a specific quadrant meet the specified threshold conditions, and for the evidence that meets the conditions, confirms the specific status within the quadrant; the strategy matching and generation unit combines the quadrant where the evidence is located, the determined processing level and the results of the threshold judgment and status confirmation unit, accurately matches and generates corresponding processing strategies from the predefined strategy library, generates specific, executable operations or suggestions, and implements feedback and linkage between strategies.

[0037] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. An intelligent management method applied to an evidence contamination platform, characterized in that: include: Collect historical data from the platform, including identified pollution incidents, frequency of evidence use, pollution source characteristics, pollution diffusion paths, correction effects, impact rankings, and citation counts in top journals, and pre-process the data; Based on preprocessed historical data, an evidence value assessment model and a pollution risk assessment model are constructed. The evidence value assessment model uses a weighted scoring fusion model algorithm, analyzes influence rankings and citation relationships through the PageRank algorithm, identifies high-impact evidence, extracts node importance, and uses a weighted linear regression algorithm to analyze the number of citations in top journals and the frequency of evidence use. A comprehensive evidence value score is calculated by combining the PageRank score and the linear regression weight score. The pollution risk assessment model constructs a graph data structure, uses the graph neural network algorithm (GNN) to extract risk features, and uses the random forest algorithm to establish a classification model for non-graph features. The GNN output and the classification model results are integrated to generate a comprehensive pollution risk score. The evidence value score and contamination risk score are mapped into a two-dimensional coordinate system, with the evidence value score as the horizontal axis and the contamination risk score as the vertical axis. A dual-coordinate decision-making mechanism of evidence value and contamination risk is established. Different risk areas and thresholds are set, and the quadrants are divided into high value-high risk quadrant, high value-low risk quadrant, low value-high risk quadrant and low value-low risk quadrant according to the order of update priority. Different processing strategies are assigned according to different quadrants.

2. The intelligent management method for evidence contamination platform according to claim 1, characterized in that: The platform collects historical data, including identified pollution incidents, frequency of evidence use, pollution source characteristics, pollution diffusion paths, correction effects, impact rankings, and citation counts in top journals. The data is pre-processed, including: Collect historical data from the Evidence Pollution Platform, including identified pollution incidents, frequency of evidence use, pollution source characteristics, pollution diffusion paths, correction effects, impact rankings, and citation counts in top journals; Preprocess the collected platform historical data, fill missing values ​​with the mean or mode according to the data type and distribution, identify and process abnormal data points through the Z-score statistical method, delete duplicate records, and use regular expressions to standardize and denoise text data.

3. The intelligent management method for evidence contamination platform according to claim 1, characterized in that: The evidence value assessment model uses a weighted scoring fusion model algorithm to analyze influence rankings and citation relationships through the PageRank algorithm, identify high-impact evidence, extract node importance, and analyze the number of citations in top journals and the frequency of evidence use through a weighted linear regression algorithm, including: The PageRank algorithm is used to iteratively calculate the evidence nodes and their citation relationship network. Based on the quality and quantity of the node's inlinks, the relative influence of each evidence node in the network is evaluated and quantified, and a node importance score based on the network structure is generated. The calculation formula is: ； Where PR(A) is the PageRank score of evidence node A, representing the influence of evidence node A in the evidence network; d is the damping coefficient, representing the probability that the user continues to click on the link; 1-d is the complement of the damping coefficient, representing the probability that the user does not continue to click on the link; B(A) is the set of all evidence nodes pointing to evidence node A; PR(T) is the PageRank score of evidence node T, representing the influence of evidence node T in the evidence network; C(T) is the number of external links of evidence node T; Collect and organize the number of citations in top journals and the frequency of use within the platform for each piece of evidence using the following formula: ； Among them, Y is the evidence value score, X1 is the number of citations in top journals, X2 is the frequency of evidence use, β0 is the intercept, β1 and β2 are regression coefficients, indicating the degree of influence of each variable on the dependent variable. is the error term; A weighted linear regression model was constructed, with the value of evidence as the dependent variable and the number of citations in top journals and the frequency of evidence use as independent variables. Different weights were assigned according to the historical revision effect or influence ranking of the evidence. A regression equation was fitted to quantify these two factors and generate an evidence value score based on the statistical relationship. The formula is: ； w i is the weight of the i-th sample, which adjusts the importance of the sample in the regression model according to the historical correction effect or influence ranking of the evidence; Y i is the actual value of the i-th sample; is the predicted value of the i-th sample; n is the number of samples; the formula finds the regression coefficient and fits the regression equation by minimizing the weighted residual sum of squares; where the weighted linear regression score LR is equal to the predicted value of the regression model .

4. The intelligent management method for evidence contamination platform according to claim 1, characterized in that: The PageRank score and the linear regression weight score are combined to calculate the comprehensive evidence value score, including: The PageRank score PR (A) and the weighted linear regression score LR are weighted and fused according to the preset weights to generate the final comprehensive evidence value score V. The formula is: ； Among them, V is the final generated comprehensive evidence value score, which represents the overall value of a certain evidence node; α is a weight coefficient between 0 and 1, which indicates the proportion of PageRank score PR (A) in the final score V; 1-α indicates the proportion of weighted linear regression score LR.

5. The intelligent management method for evidence contamination platform according to claim 1 is characterized in that: The pollution risk assessment model constructs a graph data structure, uses the graph neural network algorithm GNN to extract risk features, and uses the random forest algorithm to build a classification model for non-graph features, including: Evidence entities, users, and interaction relationships are abstracted into nodes and edges in a graph, forming graph data that can represent the flow and association of evidence. This constructed graph data is input into a graph neural network model. The GNN learns the representation of nodes in the graph structure layer by layer by aggregating the features of the node itself and the features of its neighboring nodes, thereby capturing risk patterns. Collect and process the non-graph structure features of evidence and train a random forest classifier; random forest classifier determines whether the evidence has contamination risk by constructing multiple decision trees and synthesizing the prediction results.

6. The intelligent management method for evidence contamination platform according to claim 1 is characterized in that: The fusion GNN output and classification model results generate a comprehensive pollution risk score, including: The structured risk features extracted by GNN are integrated with the non-graph features used by random forest to comprehensively judge the contamination risk or probability of evidence. The formula is: ； Among them, FRS is the final fused comprehensive pollution risk score; GS is the pollution risk score output by the graph neural network model; RS is the pollution risk score output by the non-graph feature model; θ is the weight coefficient, which is used to adjust the relative importance of GS and RS, with a value of 0 to 1.

7. The intelligent management method for evidence contamination platform according to claim 1 is characterized in that: The evidence value score and the pollution risk score are mapped into a two-dimensional coordinate system, with the evidence value score as the horizontal axis and the pollution risk score as the vertical axis, to establish an evidence value-pollution risk dual-coordinate decision-making mechanism, including: The evidence value score and contamination risk score are mapped into a two-dimensional coordinate system. The horizontal X-axis represents the evidence value score, which reflects the importance, relevance, and probative force of the evidence to the case. The higher the score, the greater the potential role of the evidence in the case. The vertical Y-axis represents the contamination risk level score, which reflects the possibility or severity of evidence contamination. The higher the score, the lower the reliability of the evidence and the greater the risk of misleading the judgment of the case. By plotting the two scoring values ​​of each piece of evidence into the coordinate system, an evidence point is formed. The specific position of the evidence point in the coordinate system reflects the comprehensive status of the value and risk of the evidence.

8. The intelligent management method for evidence contamination platform according to claim 1 is characterized in that: The aforementioned setting of different risk areas and thresholds is divided into high value-high risk quadrant, high value-low risk quadrant, low value-high risk quadrant and low value-low risk quadrant in the order of update priority, including: According to the established two-dimensional coordinate system of evidence value and contamination risk, thresholds are set for the evidence value score and contamination risk score, and the four quadrants are set as high value-high risk quadrant, low value-high risk quadrant, low value-low risk quadrant and high value-low risk quadrant respectively; The high-value-high-risk quadrant is located in the upper right corner of the coordinate system, where the evidentiary value and contamination risk of the evidence are higher than their respective preset thresholds. This type of evidence has a great impact on the case, but its reliability is questionable. It is an area that requires the highest priority attention and processing; the high-value-low-risk quadrant is located in the lower right corner of the coordinate system, where the evidentiary value is higher than the preset evidentiary value threshold, and the contamination risk is lower than the preset contamination risk threshold. This type of evidence has a great impact on the case and a low contamination risk, and requires second priority identification and processing; the low-value-high-risk quadrant is located in the upper left corner of the coordinate system, where the evidentiary value is lower than the preset evidentiary value threshold, and the contamination risk is higher than the preset contamination risk threshold. This type of evidence does not interfere much, but is highly risky, and requires third priority identification and processing; the low-value-low-risk quadrant is located in the lower left corner of the coordinate system, where the evidentiary value and contamination risk are lower than their respective preset thresholds, and this type of evidence has the lowest priority for updating.

9. The intelligent management method for evidence contamination platform according to claim 1 is characterized in that: The different processing strategies assigned to different quadrants include: For evidence in the high-value-high-risk quadrant, when the frequency of use of the evidence exceeds the preset frequency threshold, the highest level of handling measures will be initiated; comprehensive pollution source tracking and feature analysis will be carried out, and this information will be correlated and compared with the platform's historical pollution event database to identify the pollution source and potential transmission mode; cross-disciplinary experts will be organized to assess the impact of the pollution, and the scope and depth of the pollution will be determined by referring to the correction effect records of similar pollution in low-value-high-risk evidence; mandatory pollution elimination or evidence isolation measures will be implemented, and the entire handling process will be recorded; For evidence in the high-value-low-risk quadrant, when the frequency of use of the evidence exceeds the preset frequency threshold, intermediate handling measures will be initiated; its low-risk status will be confirmed, and it will be prioritized in case analysis, with its utilization and correction effects recorded; it will be prioritized as key evidence, and its specific role and effect in the case advancement will be recorded; regular monitoring will be implemented, and the monitoring data will be compared and analyzed with the monitoring data of high-value-high-risk evidence to form a risk warning linkage; the need for additional protective measures to prevent future contamination will be assessed, and the processing process and effect records will be fed back to the high-value-high-risk quadrant for reference; For evidence in the low-value-high-risk quadrant, when its usage frequency exceeds a preset frequency threshold, basic treatment measures are initiated; risk technical assessment is conducted to confirm the contamination status and high-risk attributes; contamination removal is performed or marked as not adopted and excluded, with removal being prioritized to reduce risk; treatment results are archived and fed back into model updates, while the treatment strategy is used as a reference and linked to the decision-making process in the low-value-low-risk quadrant; For evidence in the low-value-low-risk quadrant, when the frequency of use of the evidence is lower than the preset frequency threshold, the minimum processing measures are initiated; after confirming the low risk, a standardized archiving process is adopted, a low-value label is added, and it is retrieved under specific retrieval requests, and its usage is monitored, and its processing process is fed back to the high-value-low-risk quadrant.

10. An intelligent management system applied to an evidence contamination platform, using an intelligent management method applied to an evidence contamination platform according to any one of claims 1 to 9, characterized in that: include: Data collection and preprocessing module: includes a data collection unit and a data preprocessing unit; the data collection unit collects platform historical data; the data preprocessing unit preprocesses the collected platform historical data, identifies and processes missing values, detects and processes abnormal data points, deletes duplicate records, and standardizes and denoises text data; Evidence Value Assessment Module: This module includes an influence analysis unit, a statistical relationship analysis unit, and an evidence value scoring fusion unit. The influence analysis unit uses the PageRank algorithm to analyze evidence nodes and citation relationship networks and calculate the PageRank score of each evidence node. The statistical relationship analysis unit collects and organizes data on the number of times evidence is cited in top journals and the frequency of use within the platform, constructs a weighted linear regression model, analyzes the impact of these two factors on the value of evidence, and generates an evidence value score. The evidence value scoring fusion unit performs a weighted fusion of the PageRank score and the weighted linear regression score according to preset weights to generate a final comprehensive evidence value score. Pollution risk assessment module: includes a structured risk extraction unit, a non-graph feature processing unit, and a risk score fusion unit. The structured risk extraction unit abstracts evidence entities, users, and the interactions between them into nodes and edges in a graph data structure, forming graph data, which is input into the graph neural network (GNN) model to capture and output a risk feature score based on the graph structure. The non-graph feature processing unit collects and processes the non-graph structural features of the evidence, trains a random forest classifier, determines whether the evidence poses a pollution risk, and outputs a risk score based on the non-graph features. The risk score fusion unit fuses the structured risk score with the non-graph feature risk score to generate the final comprehensive pollution risk score. Evidence value-contamination risk coordinate system construction module: includes a coordinate mapping unit and a quadrant division unit. The coordinate mapping unit receives the evidence value score and the contamination risk score and maps each evidence point into a two-dimensional coordinate system, where the horizontal axis represents the evidence value score and the vertical axis represents the contamination risk score. The quadrant division unit divides the two-dimensional coordinate system into four quadrants based on a preset threshold, namely the high value-high risk quadrant, the high value-low risk quadrant, the low value-high risk quadrant, and the low value-low risk quadrant. Evidence processing strategy decision module: includes a priority and level determination unit, a threshold judgment and status confirmation unit, and a strategy matching and generation unit; among them, the priority and level determination unit determines the processing priority order and level of the evidence according to the quadrant where the evidence point is located in the coordinate system, in accordance with the preset priority rules and processing levels; the threshold judgment and status confirmation unit checks whether the specific attributes of the evidence in a specific quadrant meet the specified threshold conditions, and for the evidence that meets the conditions, confirms the specific status within the quadrant; the strategy matching and generation unit combines the quadrant where the evidence is located, the determined processing level and the results of the threshold judgment and status confirmation unit, accurately matches and generates corresponding processing strategies from the predefined strategy library, generates specific, executable operations or suggestions, and implements feedback and linkage between strategies.

Images