Visual prediction method and system for lower-level supply chain risks based on visual technology

Abstract

The present invention discloses a visual prediction method and system for lower-level supply chain risks based on visual technology, which belongs to the technical field of supply chain risk assessment. The method specifically includes: obtaining relevant data of the lower-level supply chain and preprocessing it to obtain first monitoring data, constructing a target recognition model, identifying and extracting the spatiotemporal characteristics and time series characteristics of the first monitoring data, constructing a multi-level risk assessment model, evaluating the comprehensive risk score of the lower-level supply chain, and predicting future risks; by extracting and identifying features of the collected multimodal data, the key elements in the supply chain can be accurately located, and combined with the risk assessment model, potential risk factors can be effectively identified and the comprehensive risk value can be evaluated, and then visualized.

Description

Technical Field

[0001] The present invention belongs to the technical field of supply chain risk assessment, and in particular to a method and system for visually predicting lower-level supply chain risks based on visual technology. Background Art

[0002] The supply chain has evolved from a simple linear chain into a complex network structure with numerous levels and links. The lower-level supply chain, as the basic level that directly supports the production and operation of core enterprises, covers many key nodes such as raw material suppliers, parts manufacturers, and logistics subcontractors. The stability of its operation plays a vital role in the stable operation of the entire supply chain.

[0003] Traditional supply chain risk prediction methods primarily rely on statistical analysis of historical transaction data, constructing regression and time series models to predict common risks such as raw material price fluctuations and supplier delivery delays. However, this reliance on historical data has numerous drawbacks. On the one hand, historical data only reflects past market conditions and operational conditions; on the other hand, questionnaires and manual judgment are also commonly used risk assessment methods. These questionnaires are cumbersome, time-consuming, and subject to high subjective responses.

[0004] Supply chain risk management based on visual technology is still in the exploratory stage. Although there have been some attempts, most applications are still concentrated on the static visual analysis and item identification level, and are unable to fully integrate multimodal data and dynamically changing information for efficient risk prediction and visualization. Therefore, the proposal of a lower-level supply chain risk visualization prediction method based on visual technology aims to overcome the limitations of traditional supply chain risk management methods, combine modern visual technology with big data analysis, and provide a risk assessment and prediction method based on multimodal fusion, dynamic update, and real-time feedback of visual data. Summary of the Invention

[0005] In response to the shortcomings of existing technologies, the present invention proposes a visual prediction method and system for lower-level supply chain risks based on visual technology, which conducts comprehensive analysis of multimodal data, real-time updates and dynamic feedback, and intelligent decision-making support, and can improve the risk prediction accuracy and response speed of supply chain finance.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The visual prediction method for lower-level supply chain risks based on visual technology includes:

[0008] Obtain relevant data of the lower supply chain and perform preprocessing to obtain first monitoring data;

[0009] Constructing a target recognition model to identify and extract the spatiotemporal features and time series features of the first monitoring data;

[0010] Construct a multi-level risk assessment model to evaluate the comprehensive risk score of the lower-level supply chain and predict future risks.

[0011] Specifically, the target recognition model is constructed to identify and extract the spatiotemporal features and time series features of the first monitoring data, including:

[0012] Constructing a target recognition model and training the target recognition model to obtain a trained target recognition model;

[0013] The first monitoring data is input into the trained target recognition model to extract the spatiotemporal features and time series features of the image in the first monitoring data.

[0014] Specifically, the target recognition model is constructed and trained, including:

[0015] Based on the characteristics and scenarios of the lower-level supply chain, select CNN and LSTM networks to build the target recognition model, and configure the number, order, and parameters of convolutional layers, pooling layers, and fully connected layers;

[0016] The labeled public dataset is divided into a training set, a validation set, and a test set. The target recognition model is trained using the training set. The parameters of the target recognition model are adjusted using the backpropagation algorithm and the optimizer. The loss function is set and the target recognition model is trained until the loss function converges and remains unchanged. The training is then stopped.

[0017] After the training is completed, the target recognition model is finally evaluated using the test set. The accuracy, recall rate, and F1 value are calculated to measure the performance of the target recognition model. If the model performance meets the expected requirements, a trained target recognition model is obtained. If the model performance does not meet the expected requirements, the target recognition model is optimized to obtain a trained target recognition model.

[0018] Specifically, extracting the spatiotemporal features and temporal features of the image in the first monitoring data includes:

[0019] Input the first monitoring data into the trained target recognition model, and set the pixel coordinates in a window of any image in the first monitoring data to , in time and The grayscale values are and , Represents a unit time interval, Indicates the change in the horizontal axis within a unit time interval. Represent the change of the vertical coordinate within a unit time interval and establish the optical flow constraint equation;

[0020] Establish an optical flow constraint equation for multiple pixel points in a window of any image in the first monitoring data, solve the overdetermined equation group, that is, multiple optical flow constraint equations, and calculate the optical flow vector , determining the speed and direction of movement of an object in any image in the first monitoring data, and obtaining the spatiotemporal characteristics of the image in the first monitoring data;

[0021] The long-term dependency and dynamic changes of the video in the first monitoring data are captured, and the temporal features in the video are extracted.

[0022] Specifically, the multi-level risk assessment model is constructed to evaluate the comprehensive risk score of the lower-level supply chain and predict future risks, including:

[0023] Construct a multi-level risk assessment model, including first-level assessment, second-level assessment and third-level assessment;

[0024] Calculate the comprehensive risk score of the lower-level supply chain based on the results of the first-level assessment, the second-level assessment, and the third-level assessment;

[0025] Predict future risks in the downstream supply chain and identify potential high-risk areas.

[0026] Specifically, the multi-level risk assessment model is constructed, including first-level assessment, second-level assessment and third-level assessment, including:

[0027] In the first level of assessment, the extracted spatiotemporal features and time series features are preliminarily identified to obtain the risk prediction labels of each data sample in the first monitoring data, including: no risk and risky;

[0028] In the second-tier assessment, anomaly detection and classification are performed on the spatiotemporal and temporal features corresponding to the risky data samples in the first-tier assessment, identifying and classifying potential abnormal behaviors or problem areas.

[0029] In the third assessment, the outputs of the first and second level assessments are integrated to quantitatively score the risks using a multi-level risk scoring model;

[0030] By locally training a multi-level risk assessment model, introducing differential privacy technology, sharing model parameters through a federated aggregation mechanism, and utilizing adaptive multi-model weighted aggregation, the first weight is dynamically assigned according to the performance indicators of each model on the local data set. Based on the differences in the models, the same data nodes or adjacent data nodes are used for training to obtain the model performance indicators, and the second weight is dynamically assigned. The model parameters corresponding to the first weight and the model parameters corresponding to the second weight are weightedly summed to obtain the model shared parameters.

[0031] Specifically, the future risks of the lower-level supply chain are predicted and potential high-risk areas are identified, including:

[0032] Using a clustering algorithm, different links in the lower supply chain are clustered according to risk scores. The center point of each cluster represents the average risk level of the area corresponding to the center point.

[0033] Based on the average risk level of each area, a risk heat map is generated to identify potential high-risk areas.

[0034] Specifically, the relevant data of the lower-level supply chain includes: production environment monitoring data, warehouse site monitoring data, financial data and logistics and transportation monitoring data.

[0035] A visual prediction system for lower-level supply chain risks based on visual technology, used to implement the visual prediction method for lower-level supply chain risks based on visual technology, comprising: a data processing module, a feature extraction module, and a risk assessment and prediction module;

[0036] The data processing module is used to obtain relevant data of the lower supply chain and perform preprocessing to obtain first monitoring data;

[0037] The feature extraction module is used to build a target recognition model to identify and extract the spatiotemporal features and time series features of the first monitoring data;

[0038] The risk assessment and prediction module is used to build a multi-level risk assessment model, evaluate the comprehensive risk score of the lower-level supply chain, and predict future risks.

[0039] Specifically, the risk assessment and prediction module includes: a first assessment unit, a second assessment unit, a third assessment unit, a comprehensive assessment unit and a prediction unit;

[0040] The first evaluation unit is configured to preliminarily identify a risk prediction label for each data sample in the first monitoring data;

[0041] The second evaluation unit is used to detect and classify anomalies on the spatiotemporal features and time series features corresponding to the risky data samples in the first layer evaluation;

[0042] The third assessment unit is used to integrate the outputs of the first and second level assessments and use a multi-level risk scoring model to quantitatively score the risk;

[0043] The comprehensive assessment unit is used to comprehensively calculate the risks of the lower-level supply chain;

[0044] The prediction unit is used to predict future risks of the lower-level supply chain and identify potential high-risk areas.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] 1. The present invention proposes a visual prediction method for lower-level supply chain risks based on visual technology. By extracting and identifying features from the collected multimodal data, it can accurately locate key elements in the supply chain. Combined with the risk assessment model, it can effectively identify potential risk factors and assess the comprehensive risk value.

[0047] 2. The present invention proposes a visual prediction method for lower-level supply chain risks based on visual technology. By combining data from different modalities, it can conduct a comprehensive analysis of supply chain risks from multiple dimensions, so that the risk assessment model can more comprehensively assess risks, identify potential correlation factors, and further improve the accuracy of risk prediction.

[0048] 3. The present invention proposes a visual prediction method and system for lower-level supply chain risks based on visual technology, which can present complex risk assessment results to decision makers in a graphical and visual manner. Through intuitive methods such as charts, heat maps, and risk maps, potential risk areas in the supply chain can be quickly understood, providing strong support for decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flow chart of the visual prediction method for lower-level supply chain risks based on visual technology provided by the present invention;

[0050] Figure 2 A schematic diagram of model parameter sharing provided by the present invention;

[0051] Figure 3 This is an architecture diagram of the lower-level supply chain risk visualization prediction system based on visual technology provided by the present invention. DETAILED DESCRIPTION

[0052] The present application is described in detail below with reference to specific embodiments. The following embodiments will help those skilled in the art to further understand the present application, but are not intended to limit the present application in any form. It should be noted that those skilled in the art may make several variations and improvements without departing from the scope of the present application. These all fall within the scope of protection of the present application.

[0053] In the present invention, unless otherwise specified, all parts and percentages are by weight. The equipment and raw materials used are commercially available or commonly used in the art. The methods in the following embodiments, unless otherwise specified, are conventional methods in the art. The components or equipment in the following embodiments, unless otherwise specified, are all universal standard parts or components known to those skilled in the art. Their structures and principles are known to those skilled in the art through technical manuals or routine experimental methods.

[0054] The following detailed description of the embodiments of the present invention is made in conjunction with the accompanying drawings. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present invention. However, one or more embodiments may be implemented by those skilled in the art without these specific details.

[0055] Example 1

[0056] In this application, the visual prediction method for lower-level supply chain risks based on visual technology is specifically applied to the visual prediction of lower-level supply chain financial risks. The lower-level supply chain is composed of core enterprises, core agents and distributors. The core enterprises sell to core agents through financing. The core agents need to pay advance payments before delivery. After the core agents receive the goods, they sell them to distributors. There are financial risks during the process.

[0057] See also Figure 1-Figure 2 The present invention provides an embodiment of a visual prediction method for lower-level supply chain risks based on visual technology, comprising the following specific steps:

[0058] Step S1: Obtain relevant data of the lower supply chain, including: production environment monitoring data, warehouse site monitoring data, financial data and logistics and transportation monitoring data, and pre-process it to obtain first monitoring data;

[0059] The production environment monitoring data in step S1 includes: by deploying high-definition cameras and industrial cameras, capturing the status of the production line in real time, collecting the operation status of production equipment, images of production items, abnormal pauses or failures of the production line, storage environment, physical conditions in the production environment, etc.;

[0060] Warehouse site monitoring data includes obtaining information such as the type, quantity, and storage location of goods in the warehouse through the deployment of RFID (radio frequency identification) devices and cameras;

[0061] Financial data includes: transaction data, invoice information, credit ratings, etc. Transaction data includes order records, payment records, supplier and customer credit records, product procurement and delivery history data, revenue, expenditure, balance sheet, cash flow, etc.

[0062] Logistics and transportation monitoring data includes: vehicle location, transportation route, driver status, and vehicle status through vehicle-mounted cameras and GPS positioning systems;

[0063] The preprocessing includes: data cleaning, removing noisy and redundant data; image denoising, using an adaptive median filter algorithm to remove noise caused by light interference, equipment electronic noise, etc., to improve image clarity; image enhancement, using an improved algorithm based on histogram equalization to stretch the image contrast to make the details in the image more prominent, and performing statistical analysis on the image grayscale histogram to redistribute pixel grayscale values and enhance the distinction between different areas; multimodal data fusion, including temporal and spatial synchronization, using methods such as Kalman filtering and particle filtering to fuse data from different sources;

[0064] The principle of the adaptive median filtering algorithm is: if the minimum value of a pixel at a certain point in the window is less than the median value and the median value is less than the maximum value, then the pixel value of the output image at that point is the median value of the pixel values in the window; otherwise, the pixel value of the output image at that point is the pixel value of the input image at that point;

[0065] Time synchronization: Since different types of data may have different collection times, all data need to be synchronized through timestamps. By using high-precision clocks (such as GPS-synchronized clocks) to accurately timestamp various devices, the time consistency between data sources is ensured, allowing multimodal data to be accurately connected on the time axis. Spatial synchronization:

[0066] Step S2: constructing a target recognition model to identify and extract the spatiotemporal features and time series features of the first monitoring data;

[0067] The specific steps of step S2 are:

[0068] Step S201: constructing a target recognition model and training the target recognition model to obtain a trained target recognition model;

[0069] Step S202: input the first monitoring data into the trained target recognition model to extract the spatiotemporal features and temporal sequence features of the image in the first monitoring data.

[0070] The specific steps of step S201 include:

[0071] Step S211: Based on the characteristics and scenarios of the lower-level supply chain, select CNN and LSTM networks to build a target recognition model, and configure the number, order, and parameters of convolutional layers, pooling layers, and fully connected layers;

[0072] In this example, for example, for more complex tasks like identifying the operating status of equipment, a deeper network structure may be required to fully learn the subtle features and complex patterns of the equipment. However, for identifying raw material inventory quantities, a relatively shallow network structure may be sufficient. During the design process, the model's computational complexity and training time must also be considered to ensure efficient operation in real-world applications.

[0073] Step S2012: Divide the annotated public dataset into a training set, a validation set, and a test set, use the training set to train the target recognition model, adjust the parameters of the target recognition model through the back propagation algorithm and the optimizer, set the loss function, and train the target recognition model until the loss function converges and remains unchanged, then stop training;

[0074] In this embodiment, during the training process, a validation set is used to monitor the performance of the model to prevent overfitting. Overfitting refers to the model performing well on the training set but performing poorly on new, unseen data (the test set). By evaluating the performance on the validation set, the model's hyperparameters (such as the learning rate and regularization parameters) can be adjusted in a timely manner to optimize the model's generalization ability.

[0075] Step S2013: After the training is completed, the target recognition model is finally evaluated using the test set, and the accuracy, recall rate, and F1 value are calculated to measure the performance of the target recognition model. If the model performance meets the expected requirements, a trained target recognition model is obtained. If the model performance does not meet the expected requirements, the target recognition model is optimized to obtain a trained target recognition model.

[0076] Preferably, the optimization method includes adjusting the model architecture, increasing training data, adopting data enhancement techniques (such as rotating, flipping, and scaling images), adjusting hyperparameters, etc., so that the model can accurately and stably identify key elements of the supply chain through continuous iterative optimization.

[0077] The specific steps of step S202 include:

[0078] Step S2021: Input the first monitoring data into the trained target recognition model, and set the pixel coordinates in a window of any image in the first monitoring data as , in time and The grayscale values are and , Represents a unit time interval, Indicates the change in the horizontal axis within a unit time interval. Represents the change in the ordinate within a unit time interval, and establishes the optical flow constraint equation. The specific formula is:

[0079] ;

[0080] in, represents the grayscale gradient of any image in the first monitoring data in the horizontal axis direction, represents the grayscale gradient of any image in the first monitoring data in the vertical direction, u represents the component of the optical flow in the horizontal direction, and v represents the component of the optical flow in the vertical direction. represents the time gradient;

[0081] In this embodiment, optical flow refers to the motion vector of a pixel point in an image on the image plane over time. The optical flow constraint equation is derived based on several basic assumptions: the constant brightness assumption and the small motion assumption. The constant brightness assumption specifically states that within a short time interval, the brightness of a point on the surface of an object remains unchanged during the motion process. That is, the pixel grayscale values corresponding to the same object point in images at different times are the same. For example, in a continuously shot video, the grayscale value of a specific point on a moving car in two adjacent frames will not change immediately due to the movement of the car. The small motion assumption specifically states that the object moves little between adjacent frames. 、 and They are all very small quantities, and we can use Taylor series to calculate Expand it and set the brightness constant assumption to obtain the optical flow constraint equation;

[0082] Step S2022: Establish an optical flow constraint equation for multiple pixel points in a window of any image in the first monitoring data, solve the overdetermined equation group, that is, multiple optical flow constraint equations, and calculate the optical flow vector , determining the speed and direction of movement of an object in any image in the first monitoring data, and obtaining the spatiotemporal characteristics of the image in the first monitoring data;

[0083] In this embodiment, the optical flow constraint equation is essentially a linear equation in two variables. It is impossible to uniquely determine the two unknowns u and v by only one equation. Multiple optical flow constraint equations are required to solve the equation. The solution method of the optical flow equation is as follows: 1) Lucas-Kanade method: Assume that the optical flow is constant in a small spatial neighborhood, that is, in a small window centered on a certain pixel point, all pixels have the same optical flow vector , within this small window, an optical flow constraint equation can be established for each pixel point, thus obtaining an overdetermined set of equations (because the number of pixels in the window is usually much larger than the number of unknowns); 2) Horn-Schunck method: Based on the optical flow constraint equation, a smoothness constraint condition is introduced, assuming that the optical flows of adjacent pixels should be similar, that is, the optical flow field should be smooth, and the optical flow is solved by minimizing an energy function containing optical flow constraint terms and smoothness constraint terms; these solution methods are all based on the optical flow constraint equation, combined with different assumptions and constraints, to more accurately calculate the optical flow vector of the pixel points in the image, thereby obtaining the motion information of the object.

[0084] Step S2023: Capture the long-term dependency and dynamic changes of the video in the first monitoring data, and extract the temporal features in the video.

[0085] For example, abnormal changes in the transportation process or abnormal pauses in the production line can be learned from continuous video frames.

[0086] Step S3: Construct a multi-level risk assessment model to evaluate the comprehensive risk score of the lower-level supply chain and predict future risks.

[0087] The specific steps of step S3 are:

[0088] Step S301: construct a multi-level risk assessment model, including first-level assessment, second-level assessment, and third-level assessment, and train the multi-level risk assessment model locally;

[0089] Step S302: Calculate the comprehensive risk score of the lower-level supply chain based on the results of the first-level assessment, the second-level assessment, and the third-level assessment. The specific formula is:

[0090] ;

[0091] Among them, R represents the comprehensive risk score of the lower supply chain, n represents the total number of risks, represents the score of the i-th risk, represents the weight of the i-th risk;

[0092] Step S303: predict the future risks of the lower-level supply chain and identify potential high-risk areas.

[0093] The specific steps of step S301 are:

[0094] Step S3011: In the first level assessment, the extracted spatiotemporal features and time series features are preliminarily identified to obtain a risk prediction label for each data sample in the first monitoring data, including: no risk and risk;

[0095] In this embodiment, the extracted spatiotemporal features and time series features are preliminarily classified using algorithms such as support vector machines (SVMs) and random forests. The output of the classification model is usually a preliminary risk identification, such as no risk or risk. A risk prediction label of no risk indicates that the area or behavior is judged to be normal and no action is required. A risk prediction label of risk indicates that a potential risk has been identified and requires further processing. The specific processing method is to enter the next stage of risk identification and problem location, that is, the second-level assessment.

[0096] Step S3012: In the second-level assessment, anomaly detection and classification are performed on the spatiotemporal features and time series features corresponding to the risky data samples in the first-level assessment, potential abnormal behaviors or problem areas are identified, and the abnormal behaviors or problem areas are classified;

[0097] In this embodiment, anomaly detection methods include Isolation Forest, DBSCAN, One-Class SVM, etc. Classification models typically include Support Vector Machine, Random Forest, etc. Through mid-level risk identification and classification models, potential risk areas in the supply chain can be preliminarily identified. These potential risk areas may include: irregular stacking of items in the warehouse, abnormal transportation routes, supplier credit risk, etc.

[0098] Step S3013: In the third assessment, the outputs of the first and second level assessments are integrated to quantitatively score the risk using a multi-level risk scoring model;

[0099] Step S3014: Through local training of a multi-level risk assessment model, differential privacy technology is introduced, model parameters are shared through a federated aggregation mechanism, and adaptive multi-model weighted aggregation is used to dynamically assign a first weight based on the performance indicators of each model on the local data set. Based on the differences in the models, the same data nodes or adjacent data nodes are used for training to obtain model performance indicators, and a second weight is dynamically assigned. The model parameters corresponding to the first weight and the model parameters corresponding to the second weight are weighted summed to obtain the model shared parameters.

[0100] like Figure 2 As shown, the same data is data contained in the first layer, the second layer, and the third layer. Adjacent data are common data points of the first layer and the second layer, and the same data are eliminated.

[0101] In this embodiment, the data used in supply chain risk assessment contains a large amount of sensitive information. Differential privacy technology ensures that even if a data entry is deleted or changed in the dataset, the final analysis results are not affected, thus avoiding the risk of individual information leakage. The basic principle of differential privacy is that if a data entry is deleted or changed in a dataset, the final analysis results should be almost unaffected. Regardless of whether any data item appears in the dataset, it should not significantly change the results. This design ensures the protection of individual privacy.

[0102] In the supply chain scenario, three layers of assessment are used for risk scoring. Due to different data distributions, different models may converge slowly or not at all during the aggregation process. Model parameters are shared through a federated aggregation mechanism. The specific steps are as follows: 1) Preparation phase: prepare the multi-level risk assessment model and collected data; 2) Upload phase: use blockchain and differential privacy technology to upload data to a local or central server; 3) Aggregation calculation phase: verify the uploaded data, and use an adaptive aggregation algorithm (improved FedProx to solve the Non-IID problem) to aggregate and calculate the parameters of the multi-level risk assessment model, and process abnormal nodes (if the node times out and does not respond (>30s), use the previous round of parameters to participate in aggregation); 4) Distribution phase: generate a global model based on the global model parameters obtained by aggregation calculation, and transmit the global model to the designated server to obtain a trained multi-level risk assessment model, so that the model can learn a wider range of features and patterns.

[0103] Risk scoring models quantify risk based on a weighted average of various features or a machine learning model. Risk scores typically range from 0 to 1, with 0 indicating no risk and 1 indicating the highest risk. For example, in warehouse management, a risk score can be calculated based on multiple factors such as inventory change rate and inventory condition.

[0104] The specific steps of step S303 are:

[0105] Step S3031: Using a clustering algorithm, cluster different links of the lower supply chain according to risk scores. The center point of each cluster represents the average risk level of the area corresponding to the center point.

[0106] Step S3032: Generate a risk heat map based on the average risk level of each area to identify potential high-risk areas.

[0107] In this embodiment, darker colors in the risk heat map indicate higher risk scores. By analyzing the risk score distribution of each region, regions with higher risk scores, i.e., potential high-risk regions, are identified. Specifically, those skilled in the art can set a risk score threshold to identify potential high-risk regions.

[0108] Example 2

[0109] See also Figure 3 ,Another embodiment provided by the present invention: A visual prediction system for lower-level supply chain risks based on visual technology, comprising: a data processing module, a feature extraction module and a risk assessment and prediction module;

[0110] The data processing module is used to obtain relevant data of the lower supply chain and perform preprocessing to obtain first monitoring data;

[0111] The feature extraction module is used to build a target recognition model to identify and extract the spatiotemporal features and time series features of the first monitoring data;

[0112] The risk assessment and prediction module is used to build a multi-level risk assessment model, evaluate the comprehensive risk score of the lower-level supply chain, and predict future risks.

[0113] Risk assessment and prediction module, including: first assessment unit, second assessment unit, third assessment unit, comprehensive assessment unit and prediction unit;

[0114] The first evaluation unit is configured to preliminarily identify a risk prediction label for each data sample in the first monitoring data;

[0115] The second evaluation unit is used to detect and classify anomalies on the spatiotemporal features and time series features corresponding to the risky data samples in the first layer evaluation;

[0116] The third assessment unit is used to integrate the outputs of the first and second level assessments and use a multi-level risk scoring model to quantitatively score the risk;

[0117] The comprehensive assessment unit is used to comprehensively calculate the risks of the lower-level supply chain;

[0118] The prediction unit is used to predict future risks of the lower-level supply chain and identify potential high-risk areas.

[0119] In addition, the parts of the above technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0120] The above-described specific embodiments further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above description is merely a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A visual prediction method for lower-level supply chain risks based on visual technology, characterized by: include: Obtaining relevant data of the lower supply chain and preprocessing it to obtain first monitoring data, wherein the relevant data includes production environment monitoring data, warehouse site monitoring data, financial data, and logistics and transportation monitoring data; Constructing a target recognition model to identify and extract the spatiotemporal features and time series features of the first monitoring data; Build a multi-level risk assessment model to evaluate the comprehensive risk score of the lower-level supply chain and predict future risks; The target recognition model is constructed to identify and extract the spatiotemporal features and time series features of the first monitoring data, including: Constructing a target recognition model and training the target recognition model to obtain a trained target recognition model; The target recognition model is constructed and trained, including: Based on the characteristics and scenarios of the lower-level supply chain, select CNN and LSTM networks to build the target recognition model, and configure the number, order, and parameters of convolutional layers, pooling layers, and fully connected layers; The labeled public dataset is divided into a training set, a validation set, and a test set. The target recognition model is trained using the training set. The parameters of the target recognition model are adjusted using the backpropagation algorithm and the optimizer. The loss function is set and the target recognition model is trained until the loss function converges and remains unchanged. The training is then stopped. After training is completed, the target recognition model is finally evaluated using the test set. The accuracy, recall rate, and F1 value are calculated to measure the performance of the target recognition model. If the model performance meets the expected requirements, the trained target recognition model is obtained. If the model performance does not meet the expected requirements, the target recognition model is optimized to obtain the trained target recognition model. Inputting the first monitoring data into the trained target recognition model to extract spatiotemporal features and temporal sequence features of the image in the first monitoring data; The multi-level risk assessment model is constructed to evaluate the comprehensive risk score of the lower-level supply chain and predict future risks, including: Construct a multi-level risk assessment model, including first-level assessment, second-level assessment and third-level assessment; Calculate the comprehensive risk score of the lower-level supply chain based on the results of the first-level assessment, the second-level assessment, and the third-level assessment; Predict future risks in the downstream supply chain and identify potential high-risk areas; The multi-level risk assessment model is constructed, including first-level assessment, second-level assessment and third-level assessment, including: In the first level of assessment, the extracted spatiotemporal features and time series features are preliminarily identified to obtain the risk prediction labels of each data sample in the first monitoring data, including: no risk and risky; In the second-tier assessment, anomaly detection and classification are performed on the spatiotemporal and temporal features corresponding to the risky data samples in the first-tier assessment, identifying and classifying potential abnormal behaviors or problem areas. In the third assessment, the outputs of the first and second level assessments are integrated to quantitatively score the risks using a multi-level risk scoring model; By locally training a multi-level risk assessment model, introducing differential privacy technology, sharing model parameters through a federated aggregation mechanism, and utilizing adaptive multi-model weighted aggregation, the first weight is dynamically assigned based on the performance indicators of each model on the local data set. Based on the differences in the models, the same data nodes or adjacent data nodes are used for training to obtain the model performance indicators, and the second weight is dynamically assigned. The model parameters corresponding to the first weight and the model parameters corresponding to the second weight are weightedly summed to obtain the model shared parameters.

2. The visual prediction method for lower-level supply chain risks based on visual technology according to claim 1, characterized in that: The extracting of spatiotemporal features and temporal features of the image in the first monitoring data includes: Input the first monitoring data into the trained target recognition model, and set the pixel coordinates in a window of any image in the first monitoring data to , in time and The grayscale values are and , Represents a unit time interval, Indicates the change in the horizontal axis within a unit time interval. Represent the change of the vertical coordinate within a unit time interval and establish the optical flow constraint equation; Establish an optical flow constraint equation for multiple pixel points in a window of any image in the first monitoring data, solve the overdetermined equation group, that is, multiple optical flow constraint equations, and calculate the optical flow vector , determining the speed and direction of movement of an object in any image in the first monitoring data, and obtaining the spatiotemporal characteristics of the image in the first monitoring data; The long-term dependency and dynamic changes of the video in the first monitoring data are captured, and the temporal features in the video are extracted.

3. The visual prediction method for lower-level supply chain risks based on visual technology according to claim 2, characterized in that: The above-mentioned prediction of future risks of the lower-level supply chain and identification of potential high-risk areas include: Using a clustering algorithm, different links in the lower supply chain are clustered according to risk scores. The center point of each cluster represents the average risk level of the area corresponding to the center point. Based on the average risk level of each area, a risk heat map is generated to identify potential high-risk areas.

4. The visual prediction method for lower-level supply chain risks based on visual technology according to claim 3, characterized in that: The relevant data of the lower-level supply chain includes: production environment monitoring data, warehouse site monitoring data, financial data and logistics and transportation monitoring data.

5. A visual prediction system for lower-level supply chain risks based on visual technology, used to implement the visual prediction method for lower-level supply chain risks based on visual technology according to any one of claims 1 to 4, characterized in that: include: Data processing module, feature extraction module and risk assessment and prediction module; The data processing module is used to obtain relevant data of the lower supply chain and perform preprocessing to obtain first monitoring data; The feature extraction module is used to build a target recognition model to identify and extract the spatiotemporal features and time series features of the first monitoring data; The risk assessment and prediction module is used to build a multi-level risk assessment model, evaluate the comprehensive risk score of the lower-level supply chain, and predict future risks.

6. The visual prediction system for lower-level supply chain risks based on visual technology according to claim 5, characterized in that: The risk assessment and prediction module includes: a first assessment unit, a second assessment unit, a third assessment unit, a comprehensive assessment unit and a prediction unit; The first evaluation unit is configured to preliminarily identify a risk prediction label for each data sample in the first monitoring data; The second evaluation unit is used to detect and classify anomalies on the spatiotemporal features and time series features corresponding to the risky data samples in the first layer evaluation; The third assessment unit is used to integrate the outputs of the first and second level assessments and use a multi-level risk scoring model to quantitatively score the risk; The comprehensive assessment unit is used to comprehensively calculate the risks of the lower-level supply chain; The prediction unit is used to predict future risks of the lower-level supply chain and identify potential high-risk areas.

Images