An intelligent decision-making system based on a value network

Abstract

This application provides an intelligent decision-making system based on a value network, aiming to achieve optimized decision-making for complex systems through multi-module collaboration. The system models functional modules or business nodes as multi-dimensional attribute vectors through a node creation module; the node association module constructs multi-dimensional tensors based on the multi-dimensional attribute vectors to form a value network, describing the association relationships between nodes; the value calculation module calculates the actual contribution value of nodes through the multi-dimensional attribute vectors and tensors; the cost aggregation module aggregates the total system cost; the dynamic adjustment module accesses multi-source heterogeneous data streams in real time to dynamically adjust node attributes and association relationships; the optimization decision-making module generates an optimization plan based on the contribution value and the total cost, and predicts its usage effect. This system realizes intelligent decision-making optimization in complex systems through value network modeling and dynamic adjustment mechanisms, and is applicable to multi-domain business scenarios.

Description

Technical Field

[0001] This application relates to the field of intelligent decision-making technology, and particularly to an intelligent decision-making system based on a value network. Background Art

[0002] With the development of enterprise scale, correct enterprise decision-making is becoming increasingly important for enterprise development. However, the current enterprise decision-making system still has the following problems:

[0003] Traditional decision-making systems are mostly based on static index evaluation, and it is difficult to capture the dynamic influence relationship between business nodes; existing value evaluation models often only focus on direct business value and ignore the non-linear synergy effects of technical value and market value; multi-dimensional decision-making factors (such as value, cost, risk, etc.) are usually processed separately, lacking a unified quantitative framework; the decision-making process usually relies on manual experience judgment and it is difficult to adapt to the rapidly changing market environment and emergencies.

[0004] Therefore, there is a need for an intelligent decision-making system that can dynamically capture the complex associations between business nodes and integrate multi-dimensional factors to improve the scientificity, adaptability, and global optimization ability of enterprise decision-making. Summary of the Invention

[0005] In view of the above problems, this application provides an intelligent decision-making system based on a value network, which is used to provide interpretable and trustworthy decision-making suggestions for enterprises and achieve global value optimization in the enterprise decision-making process.

[0006] The specific solution of this application is as follows:

[0007] An intelligent decision-making system based on a value network, comprising:

[0008] A node creation module, configured to model each functional module or business node in the system as a multi-dimensional attribute vector , where represents value, represents cost, represents risk, represents technological advancement, represents market demand intensity;

[0009] A node association module, which constructs a multi-dimensional tensor based on the multi-dimensional attribute vector to describe the association relationship between nodes;

[0010] A value calculation module, which calculates the actual contribution value of each node in the network based on the multi-dimensional attribute vector and the multi-dimensional tensor ;

[0011] A cost aggregation module, configured to calculate the total system cost ;

[0012] A dynamic adjustment module for real-time access to multi-source heterogeneous data streams and dynamically adjusting relevant node attribute vectors and association relationships based on the data flow;

[0013] An optimization decision-making module, based on the actual contribution value and the total system cost to generate an optimized decision-making plan and predict the usage effect of the optimized decision-making plan.

[0014] Preferably, the system further includes an adaptive module, which dynamically adjusts relevant parameters and structures of the system, including the multi-dimensional attribute vectors and multi-dimensional tensors, by establishing a feedback mechanism.

[0015] The adaptive module dynamically adjusts relevant parameters and structures of the system (such as multi-dimensional attribute vectors and multi-dimensional tensors) through a feedback mechanism, enabling the system to automatically optimize according to the actual operating conditions and avoiding the lag and subjectivity of manual intervention. This adaptive ability enhances the flexibility and robustness of the system and can better cope with complex and changing business environments.

[0016] Preferably, the feedback mechanism specifically includes:

[0017] A short-cycle feedback for real-time monitoring of key indicators, including the value realization rate, cost deviation rate, and risk event frequency, and triggering an alarm when the deviation of the key indicators exceeds the first threshold;

[0018] A medium-cycle feedback for collecting the difference between the usage results of the actual optimized decision-making plan and the predicted usage effect of the optimized decision-making plan at preset time intervals, and introducing a Bayesian model to dynamically adjust relevant parameters of the system based on this difference;

[0019] A long-cycle feedback for collecting the achievement rate of the enterprise's annual assessment business strategic objectives and optimizing the structure of relevant tensors based on this achievement rate.

[0020] The short-cycle feedback can quickly detect problems and trigger an alarm by real-time monitoring of key indicators (such as the value realization rate, cost deviation rate, and risk event frequency), reducing potential losses. The medium-cycle feedback optimizes the system based on the difference between the actual and predicted values by dynamically adjusting parameters through a Bayesian model, improving the scientificity of decision-making. The long-cycle feedback optimizes the tensor structure through annual assessment to ensure that the system can adapt to the enterprise's strategic objectives in the long term and achieve continuous improvement.

[0021] Preferably, the data of the node attribute vectors is obtained from the enterprise internal system and external data interfaces.

[0022] By integrating the data of the enterprise's internal systems and external data interfaces, the system can obtain comprehensive and real-time information, ensuring the accuracy of the node attribute vectors. The access of such multi-source data enhances the data coverage and timeliness of the system, improving the quality of the basis for decision-making.

[0023] Preferably, the value calculation module calculates the actual contribution value of a node through the following formula :

[0024] ;

[0025] where is the number of iteration steps, and the upper limit of the total number of iterations is ;

[0026] is the attenuation factor ;

[0027] is the combination of technological advancement , market demand intensity , and risk dimension factor ;

[0028] is the initial contribution value of node ;

[0029] is the total number of nodes;

[0030] is the value gain coefficient between node i and node j.

[0031] By calculating the actual contribution value of a node through the above formula, multi-dimensional factors such as technological advancement, market demand intensity, and risk can be comprehensively considered, and the contribution weight of the node can be dynamically adjusted. This calculation method can more accurately reflect the actual value of the node in the network and avoid the one-sidedness of single-dimensional evaluation.

[0032] Preferably, the cost aggregation module calculates the total cost of the system based on the cost after collaborative discount , collaboration overhead and risk penalty term , and the specific formula is as follows:

[0033] ;

[0034] where is the cost after collaborative discount of node i;

[0035] is the direct cost of node ;

[0036] is the average value of the cost synergy coefficient between node i and other nodes;

[0037] is the discount function, and the specific expression is:

[0038] ;

[0039] where, is an adjustable parameter that controls the intensity of the synergy effect;

[0040] is the collaboration overhead of node i, ;

[0041] where, is the overall collaboration cost weight coefficient;

[0042] represents the intensity of the dependence relationship;

[0043] represents the intensity of risk conduction;

[0044] represents the weighted sum of the intensity of the dependence relationship and the intensity of risk conduction, and is specifically calculated using the following formula :

[0045] ;

[0046] ;

[0047] ;

[0048] where, , are hyperparameters that adjust the influence degree of different factors;

[0049] represents the dependence relationship;

[0050] represents the risk conduction coefficient.

[0051] is the risk penalty term of node i, λ is the risk penalty coefficient, is the cost of the node with the highest cost in the system.

[0052] Through the comprehensive calculation of the cost after collaborative discount, collaboration overhead, and risk penalty term, the system can comprehensively quantify the cost and consider the synergy effect and risk impact between nodes. This cost aggregation method can more realistically reflect the total cost of the system and provide a reliable basis for optimization decisions.

[0053] Preferably, the dynamic adjustment module includes:

[0054] A data stream access unit for accessing financial market APIs, supply chain monitoring systems, and policy analysis data;

[0055] A classification and response unit for constructing a mapping engine and using the accessed data to identify key events and trigger updates of relevant parameters;

[0056] A dynamic propagation unit for initiating a limited-depth propagation update when a key event affects a node.

[0057] By accessing financial market APIs, supply chain monitoring systems, and policy analysis data, the dynamic adjustment module can obtain real-time changes in the external environment. The classification and response unit identifies key events through the mapping engine and triggers parameter updates. The dynamic propagation unit initiates a limited-depth propagation update when a key event affects a node, ensuring that the system can quickly respond to external changes and improve real-time performance and adaptability.

[0058] Preferably, the dynamic propagation unit includes:

[0059] A direct update layer for directly correcting the attribute vector of the affected node;

[0060] A first-degree propagation layer for traversing all nodes with an association relationship with the affected node greater than a second threshold and updating their attribute vectors;

[0061] A second-degree propagation layer for performing a lightweight update on the nodes with an association relationship with the affected node greater than the second threshold, only adjusting the cost and risk-related parameters.

[0062] The direct update layer can quickly correct the attribute vector of the affected node. The first-degree propagation layer traverses the nodes with a relatively large association relationship and updates their attribute vectors. The second-degree propagation layer performs a lightweight update on the nodes with a relatively large association relationship. This hierarchical propagation mechanism can effectively control the update range, avoid unnecessary computational overhead, and ensure the timely adjustment of key nodes.

[0063] Preferably, the system further includes an anomaly detection module for discovering potential problems in advance. The anomaly detection module specifically includes:

[0064] A single-node detection unit for real-time monitoring of the attribute vectors of each node and identifying nodes that deviate from the normal pattern through the local outlier factor algorithm;

[0065] A relationship network detection unit for discovering mutations in the association relationship structure through graph embedding and graph anomaly detection algorithms.

[0066] The anomaly detection module can monitor the anomalies of node attribute vectors and associated relationship structures in real time through single-node detection and relationship network detection, and discover potential problems in advance. This mechanism can help enterprises take measures in a timely manner, avoid systemic risks, and improve the stability and reliability of the system.

[0067] Preferably, the system is provided with a decision system protection mechanism. When an abnormal pattern is detected, the system automatically degrades to a conservative decision-making mode, and starts an isolation impact assessment for the abnormal node.

[0068] This protection mechanism can effectively prevent the negative impact of abnormal situations on the overall operation of the system, and ensure the stability and security of the system in abnormal situations.

[0069] Compared with the prior art, the beneficial effects of this application are as follows:

[0070] Through multi-dimensional modeling and dynamic adjustment mechanisms, this application can comprehensively quantify multi-dimensional factors such as value, cost, and risk, break through the limitations of traditional fragmented processing, and achieve global optimization. The system introduces an event-driven mechanism to respond to external changes such as the market, technology, and policies in real time, dynamically adjust decision-making strategies, and significantly improve the timeliness and adaptability of decision-making. At the same time, by finely modeling non-linear cost factors such as collaborative discounts and collaborative overheads, the accuracy of cost prediction is improved. In addition, the system also constructs an anomaly detection mechanism to discover potential problems in advance and trigger early warnings to ensure the stable operation of the system. In short, the present invention provides an enterprise with a scientific, efficient, and reliable intelligent decision-making support solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present drawings or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present drawings. For those of ordinary skill in the art, other drawings can be obtained based on the structures shown in these drawings without creative efforts.

[0072] Figure 1 It is a schematic diagram of the system principle of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0073] In order to make the purpose, technical solutions and advantages of this application clearer, the following will describe and explain this application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application, and are not used to limit this application. Based on the embodiments provided by this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application.

[0074] As Figure 1As shown in the figure, this application provides an intelligent decision-making system based on a value network, specifically including the following six modules:

[0075] The node creation module is used to model each functional module or business node in the system as a multi-dimensional attribute vector , where represents value, which can include direct or indirect commercial value and user value; represents cost, including development, maintenance, manpower, funds, etc.; represents risk, which is a comprehensive measure of technical risk and market risk; represents technological advancement, such as technology barrier score, number of patents, etc.; represents the intensity of market demand, which is obtained from indicators such as user research or market growth rate.

[0076] For the technology industry, technological advancement can be comprehensively calculated from indicators such as technology barrier score and number of patents. For other industries, can be replaced with key influencing factors that conform to the characteristics of the industry.

[0077] The data of the node attribute vector is mainly obtained from the enterprise internal system and external data interfaces. The enterprise internal system obtains relevant data by docking cost data, user value data, technical attributes, and historical risk event libraries through APIs, and the external data interfaces integrate market research APIs to obtain the intensity of market demand in real time , and extracts industry risk indicators through the policy analysis interface.

[0078] Specifically, for example, a large e-commerce platform plans to develop multiple new functions in the next quarter, including payment system upgrade, personalized recommendation algorithm improvement, live streaming with goods function, cross-border logistics optimization, and membership points system revision. Due to limited resources, it is necessary to determine the optimal priority order for function development. The system can collect historical data of each functional module by docking with systems such as ERP and CRM through APIs, as shown in Table 1:

[0079]

[0080] The node association module constructs a multi-dimensional tensor based on the multi-dimensional attribute vector to describe the association relationship between nodes.

[0081] For example, constructing a three-dimensional tensor , the first and second dimensions (N×N) represent the relationship between node pairs, and the third dimension (5) represents the type or category of the relationship, is the total number of nodes, and is used to describe the influence or coefficient of node i and node j in the kth type of relationship, where .

[0082] The above tensor contains the following associations:

[0083] Value gain / loss (k=1): positive or negative value synergy between functions / businesses;

[0084] Cost synergy (k=2): cost reduction due to shared resources or economies of scale;

[0085] Risk transmission (k=3): The transmission coefficient of a node risk that may cause delays or failures in other nodes;

[0086] Dependency (k=4): Dependencies generated by API or interface calls between modules;

[0087] Demand correlation (k=5): The impact of demand changes or user growth at one node on other nodes.

[0088] The initial value of the above association relationship can be obtained based on the statistical analysis of historical data. For the value gain coefficient (k=1), A / B test is used to fit the cross-node synergy effect. For example, in an e-commerce scenario, if the GMV of the associated function B increases by 15% after function A is launched, then the initialization Or it can be obtained through the hybrid method of expert scoring and fuzzy logic. For the types of associations that lack data (such as risk transmission k=3), expert scoring rules are designed: first, experts score the intensity of risk transmission between nodes according to {none, weak, medium, strong}; then, the qualitative scores are converted into interval values through triangular fuzzy numbers, such as "weak" corresponds to (0.1, 0.2, 0.3); finally, defuzzification is used to generate the initial coefficients.

[0089] Specifically, the system analyzes historical A / B test data and identifies key correlations, such as:

[0090] Payment system and the value added of live streaming sales , indicating that the optimization of payment experience has significantly improved the conversion rate of live broadcast;

[0091] Cost synergy between personalized recommendations and membership points , indicating that joint development can save data processing costs;

[0092] Risk transmission in cross-border logistics and payment systems , indicating that logistics delays create chain risks in the payment process.

[0093] The value calculation module calculates the actual contribution value of each node in the network based on multi-dimensional attribute vectors and multi-dimensional tensors , the specific calculation formula is as follows:

[0094] ;

[0095] Among them is the number of iteration steps, and the upper limit of the total number of iterations is set to ;

[0096] is the attenuation factor , ensuring the convergence of value propagation;

[0097] When it terminates, is the third threshold set in advance;

[0098] is the technological advancement , the intensity of market demand , risk a combination of dimensional factors, , used to comprehensively calculate the comprehensive impact of technological advancement, market demand intensity, and risk on value propagation, represents the amplification or attenuation of technological advancement on the value transfer efficiency, represents the strengthening effect of market demand intensity on value diffusion, represents the negative impact of risk on value propagation;

[0099] is the initial contribution value of node ;

[0100] is the total number of nodes.

[0101] The cost aggregation module is used to calculate the total system cost .

[0102] When calculating the total system cost, on the basis of considering the costs of each node itself, it is also necessary to consider the cost reduction caused by the cooperation between modules and the additional costs caused by multi-module coupling, risk transfer, etc.

[0103] Specifically, first calculate through the collaborative discount of the single-node cost.

[0104] Introduce the discount function to reflect the cost synergy effect between nodes:

[0105] ;

[0106] Among them, is an adjustable parameter to control the intensity of the synergy effect;

[0107] is the node and the average value of other nodes in the cost synergy coefficient .

[0108] Based on this, the node 's cost after collaborative discount is expressed as: , is the direct cost of node .

[0109] For example, when the system calculates the cost after collaborative discount of personalized recommendation, adjust to 0.2, and the average value of the cost collaborative coefficient between personalized recommendation and other nodes is calculated as 0.35 on . The direct cost of personalized recommendation is 0.5 obtained from Table 1. Thus, the cost after collaborative discount of personalized recommendation can be calculated as:

[0110] .

[0111] Secondly, conduct collaborative overhead modeling.

[0112] Define the collaborative overhead of node as: ;

[0113] Among them, is the overall collaborative cost weight coefficient;

[0114] represents the strength of the dependency relationship;

[0115] represents the strength of risk conduction;

[0116] represents the weighted sum of the strength of the dependency relationship and the strength of risk conduction. The larger the value, the higher the additional cost caused by collaborative management, communication, integration, risk, etc. required. Specifically, it is calculated using the following formula :

[0117] ;

[0118] ;

[0119] ;

[0120] Among them, , are hyperparameters that adjust the influence degree of different factors. If a certain value is higher, it means that this factor has a greater impact on the collaborative overhead;

[0121] When , are both 0, , and no additional collaborative cost is added;

[0122] If any one of the factors increases, it will be even greater, indicating that the collaborative overhead increases accordingly;

[0123] indicating a dependency relationship;

[0124] indicating the risk conduction coefficient.

[0125] For example, set to 0.2, and adjust and to 2. The direct cost of cross-border logistics is 0.8 obtained from Table 1, and and are obtained through the node association module. From this, the collaborative overhead between cross-border logistics and the payment system can be calculated:

[0126] .

[0127] Finally, calculate the total system cost , and the specific calculation is carried out using the following formula:

[0128] ;

[0129] where is the risk penalty term for node , which is used to prevent a single node from having an excessively high cost and dragging down the whole. λ is the risk penalty coefficient, which is used to adjust the influence degree of the risk penalty term, is the cost of the node with the highest cost in the system.

[0130] The dynamic adjustment module is used to access multi-source heterogeneous data streams in real time and dynamically adjust the relevant node attribute vectors and association relationships based on this data flow.

[0131] Specifically, the dynamic adjustment module includes:

[0132] The data stream access unit is used to access the financial market API, the supply chain monitoring system, and policy analysis data, and capture events such as market value fluctuations, technological breakthroughs, supply chain interruptions, and policy mutations in real time;

[0133] The classification and response unit is used to build a mapping engine and use the accessed data to identify key events and trigger the update of relevant parameters; for example, build an "event - impact mapping engine" as shown in Table 2:

[0134]

[0135] The dynamic propagation unit is used to start a limited-depth propagation update when a key event affects a node, specifically including:

[0136] A direct update layer for directly correcting the attribute vectors of affected nodes;

[0137] A first-degree propagation layer for traversing all nodes whose association relationships with the affected nodes are greater than a second threshold and updating their attribute vectors;

[0138] A second-degree propagation layer for performing lightweight updates on the nodes whose association relationships with the affected nodes are greater than the second threshold, only adjusting the cost and risk-related parameters.

[0139] For example, when a strike breaks out at a cross-border logistics node, the risk attribute of the cross-border logistics node increases by 50%. The system will mark this node as high-risk and spread the risk along the conduction path of this node to the payment system node and the live streaming e-commerce node that depend on it, thereby triggering a recalculation of the collaboration overhead.

[0140] An optimization decision-making module, based on the actual contribution value and the total system cost to generate an optimized decision-making plan and predict the usage effect of the optimized decision-making plan.

[0141] Specifically, based on the ratio of the actual contribution value to the total system cost to determine the priority order of function development. For example, through the calculations of the above value calculation module and cost aggregation module, the data in Table 3 is obtained:

[0142]

[0143] Based on Table 3, suggestions for the function development priority can be obtained: develop the membership points, live streaming e-commerce, and personalized recommendation functions in sequence, and the remaining payment system and cross-border logistics functions can be flexibly arranged according to the actual resource situation.

[0144] Furthermore, the system also includes an adaptive module. The adaptive module dynamically adjusts the relevant parameters and structure of the system, including the multi-dimensional attribute vectors and multi-dimensional tensors, by establishing a feedback mechanism.

[0145] To enable the system to continuously self-optimize, three-layer feedback loops are established, including:

[0146] A short-cycle feedback for real-time monitoring of key indicators, including the value realization rate, cost deviation rate, and risk event frequency, and triggering an alarm when the deviation of the key indicators exceeds a first threshold;

[0147] A medium-cycle feedback for collecting the difference between the usage results of the actual optimized decision-making plan and the predicted usage effect of the optimized decision-making plan at preset time intervals, and introducing a Bayesian model to dynamically adjust the relevant parameters of the system based on this difference;

[0148] Long-loop feedback, collect the achievement rate of the enterprise's annual evaluation business strategic goals, and optimize the structure of relevant tensors based on this achievement rate.

[0149] Furthermore, the system also includes an anomaly detection module for early detection of potential problems. The anomaly detection module specifically includes:

[0150] A single-node detection unit, used to monitor the attribute vectors of each node in real time, and identify nodes deviating from the normal mode through the local outlier factor algorithm;

[0151] A relationship network detection unit, used to discover mutations in the associated relationship structure through graph embedding and graph anomaly detection algorithms. Typical anomaly patterns include the formation of isolated nodes, the breakage of propagation paths, and abnormal fluctuations in relationship strength.

[0152] The system is provided with a decision system protection mechanism. When an abnormal mode is detected, the system automatically degrades to a conservative decision-making mode, starts an isolation impact assessment for abnormal nodes, and avoids the spread of wrong decisions.

[0153] The intelligent decision-making system based on the value network proposed in this application realizes the global value optimization of the enterprise decision-making process through innovative technologies such as multi-dimensional attribute modeling, tensor correlation representation, two-way value engine, event-driven dynamic adjustment, and multi-modal decision support. The system can not only accurately capture the complex value associations between business nodes, but also dynamically respond to changes in the internal and external environment, and provide interpretable and trustworthy decision-making suggestions.

[0154] It should be noted that this application is not limited to the above-mentioned embodiments. The above-mentioned embodiments are only examples, and embodiments with the same composition and the same effect as the technical idea within the scope of the technical solution of this application are included in the technical scope of this application. In addition, within the scope of not departing from the main idea of this application, various deformations that can be thought of by those skilled in the art are imposed on the embodiments, and other ways constructed by combining some constituent elements of the embodiments are also included in the scope of this application.

Claims

1. An intelligent decision-making system based on a value network, characterized in that Including: A node creation module for modeling each functional module or business node in the system as a multi-dimensional attribute vector , where represents value, represents cost, represents risk, represents technological advancement, represents the intensity of market demand; A node association module that constructs a multi-dimensional tensor based on multi-dimensional attribute vectors to describe the association relationship between nodes; Value calculation module, calculating the actual contribution value of each node in the network based on the multi-dimensional attribute vector and the multi-dimensional tensor , calculating the actual contribution value of the node through the following formula :[[]]END]] ； wherein is the number of iteration steps, and the upper limit of the total number of iterations is ; is the attenuation factor ; For technological advancement , market demand intensity , risk dimension factor combination; is the initial contribution value of the node ; is the total number of nodes; is the value gain coefficient between node i and node j; Cost aggregation module, used to calculate the total system cost , the cost aggregation module calculates the total system cost based on the cost after collaborative discount , collaborative overhead and risk penalty term , and the specific formula is as follows: Specific formula is as follows: ； Among them is the cost after collaborative discount for node i; is a discount function; is the direct cost of node i; is the average value of the cost synergy coefficient between node i and other nodes; is the cooperation overhead for node i; is the risk penalty term for node i, λ is the risk penalty coefficient, is the cost of the node with the highest cost in the system; A dynamic adjustment module for real-time access to multi-source heterogeneous data streams and dynamically adjusting relevant node attribute vectors and association relationships based on the data flow; Optimization decision-making module, based on the actual contribution value and the total system cost Generate an optimized decision-making plan and predict the usage effect of the optimized decision-making plan.

2. The intelligent decision-making system according to claim 1, characterized in that The system further includes an adaptive module that dynamically adjusts relevant parameters and structures of the system, including the multi-dimensional attribute vectors and multi-dimensional tensors, by establishing a feedback mechanism.

3. The intelligent decision-making system according to claim 2, wherein The feedback mechanism specifically includes: Short-cycle feedback for real-time monitoring of key indicators, including value realization rate, cost deviation rate, and risk event frequency, and triggering an alarm when the deviation of the key indicators exceeds the first threshold; Medium-cycle feedback for collecting the difference between the usage results of the actual optimization decision plan and the usage effects of the predicted optimization decision plan at preset time intervals, and introducing a Bayesian model to dynamically adjust relevant parameters of the system based on the difference; Long-cycle feedback for collecting the achievement rate of the enterprise's annual assessment business strategic goals and optimizing the structure of relevant tensors based on the achievement rate.

4. The intelligent decision-making system according to claim 1, wherein The data of the node attribute vectors is obtained from the enterprise internal system and external data interfaces.

5. The intelligent decision-making system according to claim 1, wherein The dynamic adjustment module includes: A data stream access unit for accessing financial market APIs, supply chain monitoring systems, and policy analysis data; A classification and response unit for constructing a mapping engine and using the accessed data to identify key events and trigger updates of relevant parameters; A dynamic propagation unit for initiating a limited-depth propagation update when a key event affects a node.

6. The intelligent decision-making system according to claim 5, wherein The dynamic propagation unit includes: A direct update layer for directly correcting the attribute vectors of the affected nodes; A first-degree propagation layer for traversing all nodes with an association relationship with the affected node greater than a second threshold and updating their attribute vectors; A second-degree propagation layer for performing a lightweight update on the nodes with an association relationship with the affected node greater than the second threshold, only adjusting the cost and risk-related parameters.

7. The intelligent decision-making system according to claim 1, wherein The system further includes an anomaly detection module for early detection of potential problems. The anomaly detection module specifically includes: A single-node detection unit for real-time monitoring of the attribute vectors of each node and identifying nodes deviating from the normal pattern through the local outlier factor algorithm; A relationship network detection unit for discovering mutations in the association relationship structure through graph embedding and graph anomaly detection algorithms.

8. The intelligent decision-making system according to claim 7, wherein The system is provided with a decision system protection mechanism. When an abnormal pattern is detected, the system automatically degrades to a conservative decision-making mode and initiates an isolation impact assessment for abnormal nodes.

Images