Internet-based supply chain dynamic real-time management system and method

Through data analysis technology based on artificial intelligence, real-time analysis of logistics transport truck location and cargo storage environment data, the problem of information lag in traditional supply chain management is solved, the efficiency of monitoring and decision-making of cargo transportation status is improved, and economic losses are reduced.

CN118966975AInactive Publication Date: 2024-11-15广州希樱科技有限公司
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411156247.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-22
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In traditional supply chain management, there is information lag in the cargo logistics and transportation link, which leads to supply chain managers being passive when transportation abnormalities, increasing economic losses.

Method used

Using artificial intelligence-based data analysis technology, the location data of logistics transport vehicles and cargo storage environment data are analyzed in real time, and the temperature, humidity and position data at multiple time points are obtained and processed, and the characteristic vector of cargo logistics transportation monitoring is generated to judge. Is the transportation status abnormal?

Benefits of technology

The precise and rapid grasp of the state of cargo transportation is achieved, and supply chain managers can make timely and effective decisions to reduce potential economic losses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118966975A_ABST
    Figure CN118966975A_ABST
Patent Text Reader

Abstract

The invention provides a supply chain dynamic real-time management system and method based on the Internet, relates to the field of supply chain logistics management, and adopts a data analysis technology based on artificial intelligence. The position data of the logistics transport vehicle and the storage environment data of the goods on the logistics transport vehicle are analyzed in real time to judge whether the logistics transport state of the goods is abnormal or not. Thus, through accurate and rapid cargo logistics transportation data processing, a supply chain manager can better master the real-time state of cargo transportation, so that a more timely and effective decision is made, and potential economic losses are reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of supply chain logistics management, and more specifically, to an Internet-based supply chain dynamic real-time management system and method. Background Art

[0002] Supply chain management is an indispensable and important part of business operations. It covers multiple links from raw material procurement, production and manufacturing to final product distribution, and is directly related to the competitiveness and business benefits of the enterprise. In supply chain management, the risk of cargo logistics and transportation is a key factor. The traditional method relies too much on the feedback of cargo transportation arriving at a specific logistics and transportation node, which has the problem of information lag, so that supply chain managers are often in a passive state when facing transportation anomalies, which is likely to increase the economic losses caused by cargo damage, delays and other problems to a large extent.

[0003] Therefore, an optimized supply chain dynamic real-time management solution is needed. Summary of the invention

[0004] In order to solve the above technical problems, this application is proposed. The embodiment of this application provides an Internet-based supply chain dynamic real-time management system and method, which uses artificial intelligence-based data analysis technology to determine whether the cargo logistics transportation status is abnormal by performing real-time analysis on the location data of the logistics transport vehicle and the cargo storage environment data on the logistics transport vehicle. In this way, through accurate and rapid cargo logistics transportation data processing, supply chain managers can better grasp the real-time status of cargo transportation, thereby making more timely and effective decisions, thereby reducing potential economic losses.

[0005] According to one aspect of the present application, there is provided an Internet-based supply chain dynamic real-time management system, which includes: The cargo logistics and transportation related data collection module is used to obtain the temperature and humidity values ​​of the cargo storage environment in the logistics transportation vehicle at multiple predetermined time points within a predetermined time period and the location data of the logistics transportation vehicle at the multiple predetermined time points; A cargo logistics transportation related data encoding module is used to perform feature encoding processing and feature fusion processing on the temperature value and humidity value of the cargo storage environment in the logistics transportation vehicle at the plurality of predetermined time points and the position data of the logistics transportation vehicle at the plurality of predetermined time points to obtain a cargo logistics transportation monitoring feature vector; The cargo logistics transportation status monitoring result generation module is used to obtain a monitoring result of whether the cargo logistics transportation status is abnormal based on the cargo logistics transportation monitoring feature vector.

[0006] According to another aspect of the present application, a method for dynamic real-time management of a supply chain based on the Internet is provided, comprising: Acquire temperature values ​​and humidity values ​​of the cargo storage environment in the logistics transport vehicle at multiple predetermined time points within a predetermined time period, and position data of the logistics transport vehicle at the multiple predetermined time points; Performing feature coding and feature fusion processing on the temperature and humidity values ​​of the cargo storage environment in the logistics transport vehicle at the plurality of predetermined time points and the position data of the logistics transport vehicle at the plurality of predetermined time points to obtain a cargo logistics transport monitoring feature vector; Based on the cargo logistics transportation monitoring feature vector, a monitoring result of whether the cargo logistics transportation status is abnormal is obtained.

[0007] Compared with the prior art, the Internet-based supply chain dynamic real-time management system and method provided by the present application adopts artificial intelligence-based data analysis technology to determine whether the cargo logistics transportation status is abnormal by real-time analysis of the location data of the logistics transport vehicle and the cargo storage environment data on the logistics transport vehicle. In this way, through accurate and fast cargo logistics transportation data processing, supply chain managers can better grasp the real-time status of cargo transportation, thereby making more timely and effective decisions, thereby reducing potential economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0009] Figure 1 4 is a system block diagram of an Internet-based supply chain dynamic real-time management system according to an embodiment of the present application.

[0010] Figure 2 It is a block diagram of a cargo logistics and transportation related data encoding module in an Internet-based supply chain dynamic real-time management system according to an embodiment of the present application.

[0011] Figure 3 It is a block diagram of a unit for extracting characteristics of the storage environment of logistics and transportation goods in a dynamic real-time supply chain management system based on the Internet according to an embodiment of the present application.

[0012] Figure 4 It is a block diagram of a logistics transportation cargo location feature extraction unit in an Internet-based supply chain dynamic real-time management system according to an embodiment of the present application.

[0013] Figure 5It is a block diagram of a cargo logistics transportation status monitoring result generation module in an Internet-based supply chain dynamic real-time management system according to an embodiment of the present application.

[0014] Figure 6 The flowchart is a method for dynamic real-time management of supply chains based on the Internet according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0016] In today's complex and ever-changing business environment, supply chain management plays a vital role as a key part of corporate operations. Its scope is wide, covering many links from initial raw material procurement, through intermediate production and manufacturing, to final product distribution. Each link is closely connected and directly related to the company's competitiveness in the market and overall business benefits.

[0017] Among the many links in supply chain management, the cargo logistics and transportation link undoubtedly carries huge risks. Traditional cargo logistics and transportation management methods have always had significant drawbacks, mainly manifested in over-reliance on cargo transportation feedback information obtained when arriving at a specific logistics and transportation node. This method leads to a serious lag in information, which often puts supply chain managers in an unfavorable situation of passive response when encountering abnormal transportation conditions. For example, when goods are damaged or transportation is delayed, it is difficult for managers to take effective remedial measures in time due to untimely information acquisition, which greatly increases the economic losses caused by these problems to the company. Therefore, an optimized supply chain dynamic real-time management solution is expected.

[0018] In recent years, deep learning and neural networks have been widely used in computer vision, natural language processing, text signal processing and other fields. In addition, deep learning and neural networks have also demonstrated a level close to or even beyond that of humans in image classification, object detection, semantic segmentation, text translation and other fields. The development of deep learning and neural networks provides new solutions and solutions for dynamic real-time management of supply chains based on the Internet.

[0019] Figure 1 FIG. 1 is a system block diagram of a supply chain dynamic real-time management system based on the Internet according to an embodiment of the present application. Figure 1As shown, in the Internet-based supply chain dynamic real-time management system 100, it includes: a cargo logistics and transportation related data acquisition module 110, which is used to obtain the temperature value, humidity value of the cargo storage environment in the logistics transportation vehicle at multiple predetermined time points within a predetermined time period, and the position data of the logistics transportation vehicle at the multiple predetermined time points; a cargo logistics and transportation related data encoding module 120, which is used to perform feature encoding processing and feature fusion processing on the temperature value, humidity value of the cargo storage environment in the logistics transportation vehicle at the multiple predetermined time points, and the position data of the logistics transportation vehicle at the multiple predetermined time points to obtain a cargo logistics and transportation monitoring feature vector; a cargo logistics and transportation status monitoring result generation module 130, which is used to obtain a monitoring result of whether the cargo logistics and transportation status is abnormal based on the cargo logistics and transportation monitoring feature vector.

[0020] Specifically, in the technical solution of the present application, it is first necessary to obtain the temperature value and humidity value of the cargo storage environment in the logistics transport vehicle at multiple predetermined time points within a predetermined time period and the location data of the logistics transport vehicle at the multiple predetermined time points. It should be understood that many goods (such as food, medicine, etc.) transported by supply chain logistics are very sensitive to temperature and humidity. Temperature and humidity beyond a specific range will cause the goods to deteriorate and be damaged. By monitoring the changes in temperature and humidity, abnormal conditions can be identified, which helps to determine whether the transportation status of the goods is normal. The location data can reflect the driving path and status of the logistics transport vehicle in real time. If the vehicle deviates from the predetermined route, it will cause delays or increase the risk of damage to the goods. By analyzing the location data, the efficiency and timeliness of transportation can be evaluated, possible sources of delays can be identified, and corresponding corrective measures can be taken. In general, the environmental conditions and location of the goods will change over time during transportation. Obtaining data at multiple time points can help analyze the trend of these data changes, so as to more accurately determine whether there is an abnormality in the transportation status of the goods.

[0021] Figure 2 FIG. 1 is a block diagram of a data encoding module for cargo logistics and transportation in a dynamic real-time supply chain management system based on the Internet according to an embodiment of the present application. Figure 2As shown, the logistics transportation related data encoding module 120 includes: a logistics transportation cargo storage environment feature extraction unit 121, which is used to perform associated time series feature extraction on the temperature value and humidity value of the cargo storage environment in the logistics transportation vehicle at the multiple predetermined time points to obtain a logistics transportation cargo storage environment time series feature vector; a logistics transportation cargo position feature extraction unit 122, which is used to perform time series feature extraction on the position data of the logistics transportation vehicle at the multiple predetermined time points to obtain a logistics transportation vehicle position change associated time series feature vector; a cargo logistics transportation monitoring feature generation unit 123, which is used to fuse the logistics transportation vehicle position change associated time series feature vector and the logistics transportation cargo storage environment time series feature vector to obtain the cargo logistics transportation monitoring feature vector.

[0022] Figure 3 FIG. 1 is a block diagram of a unit for extracting characteristics of a storage environment of goods for logistics transportation in a real-time supply chain dynamic management system based on the Internet according to an embodiment of the present application. Figure 3 As shown, the logistics transportation cargo storage environment feature extraction unit 121 includes: a logistics transportation cargo storage environment data structuring subunit 1211, which is used to arrange the temperature values ​​and humidity values ​​of the cargo storage environment in the logistics transportation vehicle at the multiple predetermined time points according to the time dimension into a logistics transportation cargo storage environment time series input matrix; a logistics transportation cargo storage environment time series feature generation subunit 1212, which is used to pass the logistics transportation cargo storage environment time series input matrix through a logistics transportation cargo storage environment time series feature encoder to obtain a logistics transportation cargo storage environment time series feature matrix; a feature matrix expansion subunit 1213, which is used to expand the logistics transportation cargo storage environment time series feature matrix into the logistics transportation cargo storage environment time series feature vector.

[0023] The temperature and humidity of the cargo storage environment are not always fixed. Under normal circumstances, they change dynamically within a small range. In order to clearly capture the dynamic changes of the cargo storage environment and help analyze the trend and pattern of storage environment changes, in the technical solution of the present application, the temperature and humidity values ​​of the cargo storage environment in the logistics transport vehicle at the multiple predetermined time points are arranged according to the time dimension as a logistics transport cargo storage environment time series input matrix. It should be understood that the temperature and humidity parameters in the current storage environment state are not only affected by the current environmental factors, but also by the past state. By arranging the data according to the time dimension, it can help the model capture the time dependence of the storage environment parameters, and thus better identify the anomalies of the logistics transportation storage environment.

[0024] The original time series input matrix contains a large amount of temperature and humidity data. In order to extract the periodic changes in temperature and humidity and possible sudden abnormal conditions from the original matrix data, it is necessary to pass the logistics and transportation cargo storage environment time series input matrix through the logistics and transportation cargo storage environment time series feature encoder to obtain the logistics and transportation cargo storage environment time series feature matrix. In this application, the logistics and transportation cargo storage environment time series feature encoder is a convolutional neural network model that uses mutually transposed convolution kernels in adjacent layers. The use of mutually transposed convolution kernels can achieve two-way information capture in the process of feature extraction of the logistics and transportation cargo storage environment time series input matrix. This structure allows the network to take into account the correlation between the previous and next time points when extracting features, which enhances the model's understanding of the original time series input matrix.

[0025] In an embodiment of the present application, a possible implementation method of passing the logistics and transportation cargo storage environment time series input matrix through a logistics and transportation cargo storage environment time series feature encoder to obtain a logistics and transportation cargo storage environment time series feature matrix may be: each layer of the logistics and transportation cargo storage environment time series feature encoder performs the following on the input data in the forward pass of the layer: performing convolution processing, pooling processing and nonlinear processing based on a first two-dimensional convolution kernel on the input data to obtain a first activation feature map; performing convolution processing, pooling processing and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed of each other; wherein the input of the first layer of the logistics and transportation cargo storage environment time series feature encoder is the logistics and transportation cargo storage environment time series input matrix, and the output of the last layer of the logistics and transportation cargo storage environment time series feature encoder is the logistics and transportation cargo storage environment time series feature matrix.

[0026] In order to effectively reduce the dimension of the data and make subsequent processing and analysis simpler and more efficient, the technical solution of the present application can expand the time series feature matrix of the logistics transportation cargo storage environment into a time series feature vector of the logistics transportation cargo storage environment. After the feature matrix is ​​expanded into a vector, it is easier to combine the storage environment features at different times and integrate them with the features of data from other sources to improve the accuracy and robustness of the model in judging the abnormal state of cargo transportation.

[0027] Figure 4 FIG. 1 is a block diagram of a logistics transport cargo location feature extraction unit in an Internet-based supply chain dynamic real-time management system according to an embodiment of the present application. Figure 4As shown, the logistics transportation cargo position feature extraction unit 122 includes: a logistics transportation vehicle position data structuring subunit 1221, which is used to arrange the position data of the logistics transportation vehicle at the multiple predetermined time points according to the time dimension to obtain the logistics transportation vehicle position timing input vector; a logistics transportation vehicle position timing feature generation subunit 1222, which is used to pass the logistics transportation vehicle position timing input vector through the transportation vehicle position change associated timing feature encoder to obtain the logistics transportation vehicle position change associated timing feature vector.

[0028] The location data of logistics transport vehicles is essentially time series data. In order to capture the location changes of logistics transport vehicles at different time points, it is necessary to arrange the location data of the logistics transport vehicles at the multiple predetermined time points according to the time dimension to obtain the logistics transport vehicle location time series input vector. The arrangement of the location data in the time dimension makes real-time monitoring possible, and the location changes of the vehicle can be tracked in time to ensure the safety and efficiency of the cargo logistics transportation process.

[0029] Next, the logistics transport vehicle position time series input vector is passed through the transport vehicle position change associated time series feature encoder to obtain the logistics transport vehicle position change associated time series feature vector. In the present application, the transport vehicle position change associated time series feature encoder is a convolutional neural network model comprising a first convolution layer and a second convolution layer, wherein the first convolution layer uses a one-dimensional convolution kernel of a first scale, and the second convolution layer uses a one-dimensional convolution kernel of a second scale, and the first scale is different from the second scale. It should be understood that the use of one-dimensional convolution kernels of different scales can capture short-term and long-term time series features at the same time. The convolution kernel of the first scale can identify subtle changes in the short term (such as changes in instantaneous position), while the convolution kernel of the second scale can capture trends over a longer time range (such as changes in the overall driving path). Through one-dimensional convolution kernels of different scales, the transport vehicle position change associated time series feature encoder can learn richer feature representations, making the understanding of complex time series data more comprehensive. This multi-level feature learning can improve the encoder's sensitivity and accuracy to position changes.

[0030] The position change of the logistics transport vehicle and the cargo storage environment can reflect the transportation status of the cargo from one perspective. In order to integrate the position change and environmental characteristics, the transportation status of the cargo can be more comprehensively monitored and the misjudgment caused by single-dimensional information can be reduced. In the technical solution of the present application, the time series feature vector associated with the position change of the logistics transport vehicle and the time series feature vector of the logistics transport cargo storage environment are fused to obtain the cargo logistics transport monitoring feature vector. The fused feature vector can identify more complex abnormal patterns. For example, if the transport vehicle stays at a specific location for too long and the environmental conditions (such as temperature or humidity) are also outside the normal range, this indicates that there is a risk of transportation delays for the cargo.

[0031] In an embodiment of the present application, a possible implementation method of fusing the time series feature vector associated with the position change of the logistics transport vehicle and the time series feature vector of the logistics transport cargo storage environment to obtain the cargo logistics transport monitoring feature vector may be: the time series feature vector associated with the position change of the logistics transport vehicle and the time series feature vector of the logistics transport cargo storage environment are associated with the following fusion formula to obtain the cargo logistics transport monitoring feature vector; wherein the fusion formula is:

[0032] in, is the cargo logistics transportation monitoring feature vector, is the time series feature vector associated with the position change of the logistics transport vehicle, is the time series feature vector of the logistics transportation cargo storage environment, " represents the addition of the elements at the corresponding positions of the time series feature vector associated with the position change of the logistics transport vehicle and the time series feature vector of the logistics transport cargo storage environment, and It is a weighted parameter for controlling the balance between the time series feature vector associated with the position change of the logistics transport vehicle in the cargo logistics transport monitoring feature vector and the time series feature vector of the logistics transport cargo storage environment.

[0033] Figure 5 FIG. 1 is a block diagram of a module for generating monitoring results of the cargo logistics transportation status in a dynamic real-time supply chain management system based on the Internet according to an embodiment of the present application. Figure 5 As shown, the cargo logistics transportation status monitoring result generation module 130 includes: a feature optimization unit 131, which is used to perform back-propagation expression correction on the cargo logistics operation monitoring feature vector based on category distance learning to obtain an optimized cargo logistics operation monitoring feature vector; a feature vector classification unit 132, which is used to pass the optimized cargo logistics operation monitoring feature vector through a cargo transportation status classifier to obtain a classification result, and the classification result is used to indicate whether the cargo logistics transportation status at the current time point is abnormal.

[0034] In particular, in the technical solution of the present application, it is considered that if the temperature value, humidity value or position data is missing or wrong during the collection process, it may lead to incompleteness of the time series input matrix, thereby affecting the accuracy of the subsequent feature matrix. Environmental changes in the logistics transportation process may have nonlinear characteristics. If the time series feature encoder cannot effectively capture these nonlinear changes, the feature vector may not accurately reflect the actual environmental state. The logistics transportation cargo storage environment time series feature encoder and the transport vehicle position change associated time series feature encoder may not be able to fully capture all relevant features, or may ignore some important details during the encoding process. When fusing the position change associated time series feature vector and the cargo storage environment time series feature vector, if the weight distribution is improper or the fusion method is not appropriate, it may lead to abnormal distribution of the feature vector. However, the cargo logistics operation monitoring feature vector has a local abnormal distribution, which causes it to have a class outlier offset relative to the predetermined class label of the cargo transportation state classifier when it is generated and judged by the cargo transportation state classifier, affecting the iteration effect. Based on this, it is necessary to perform a backward propagation expression correction based on class distance learning on the cargo logistics operation monitoring feature vector to obtain an optimized cargo logistics operation monitoring feature vector.

[0035] In an embodiment of the present application, the cargo logistics operation monitoring feature vector is modified by back-propagation expression based on category distance learning to obtain an optimized cargo logistics operation monitoring feature vector, including: determining a classification weight matrix of the cargo transportation status classifier; performing matrix decoupling on the classification weight matrix in units of row vectors to obtain a set of classification weight vectors; calculating the metric learning loss information item between each classification weight vector in the set of classification weight vectors and the cargo logistics operation monitoring feature vector to obtain a metric learning compensation representation vector; inputting the metric learning compensation representation vector into an activation function to obtain a probabilistic metric learning compensation weight vector; calculating the positional point multiplication of the probabilistic metric learning compensation weight vector and the cargo logistics operation monitoring feature vector to obtain a point product feature vector, and calculating the weighted sum of the point product feature vector and the cargo logistics operation monitoring feature vector to obtain the optimized cargo logistics operation monitoring feature vector.

[0036] More specifically, in an embodiment of the present application, calculating the metric learning loss information item between each classification weight vector in the set of classification weight vectors and the cargo logistics operation monitoring feature vector to obtain a metric learning compensation representation vector includes: calculating the metric learning loss information item between each classification weight vector in the set of classification weight vectors and the cargo logistics operation monitoring feature vector using the following formula; wherein the formula is:

[0037] in, Represents the first in the set of classification weight vectors The classification weight vector The eigenvalues ​​at the positions, The first character of the cargo logistics operation monitoring feature vector is represented by The eigenvalues ​​at the positions, represents the length of the feature vector, represents the metric learning compensation representation vector The eigenvalues ​​at the positions, Represents a logarithmic function.

[0038] That is, the cargo logistics operation monitoring feature vector is modified by back propagation expression based on category distance learning, which first determines the classification weight matrix of the cargo transportation status classifier to understand the cargo transportation status classifier distinguishing different category features. Subsequently, the classification weight matrix is ​​decoupled by row vector to obtain a set of classification weight vectors to allow the model to independently analyze the weight of each category and provide more refined control for feature compensation. Next, the metric learning loss information item is calculated. This process involves quantitative analysis of the interaction between each category weight vector and the cargo logistics operation monitoring feature vector. Through the calculation of a specific loss function, the inconsistency between the feature vector and the category weight is captured, providing a quantitative indicator for compensation. Next, the metric learning compensation representation vector is input into the activation function, nonlinearly transformed, and converted into a probabilistic form. The application of the activation function introduces nonlinearity, enhances the model's ability to interpret the compensation weight, and makes the compensation weight more consistent with the actual distribution characteristics. Then, the probabilistic metric learning compensation weight vector is calculated using the metric learning compensation representation vector processed by the activation function. This step provides probabilistic guidance for the adjustment of the feature vector in a probabilistic form, making the optimization process more consistent with statistical characteristics, thereby enhancing the accuracy of the model for feature adjustment. Finally, by calculating the dot product of the probabilistic metric learning compensation weight vector and the cargo logistics operation monitoring feature vector, and then calculating the weighted sum with the original cargo logistics operation monitoring feature vector, the optimized cargo logistics operation monitoring feature vector is obtained. This step combines the original feature information and compensation information to generate an adjusted feature vector, reducing the impact of abnormal distribution and improving the accuracy of classification.

[0039] Finally, the optimized cargo logistics operation monitoring feature vector is passed through the cargo transportation status classifier to obtain a classification result, and the classification result is used to indicate whether the cargo logistics transportation status at the current time point is abnormal. The optimized cargo logistics operation monitoring feature vector includes the characteristics of the position change of the transport vehicle and the storage environment characteristics of the logistics transport vehicle, but these characteristics do not directly correspond to the results of the cargo transportation status, so it is necessary to pass the optimized cargo logistics operation monitoring feature vector through the cargo transportation status classifier. The cargo transportation status classifier is usually a model based on machine learning, which can analyze and judge according to the input data and map it to different categories. Through the cargo transportation status classifier, it can be clearly indicated whether the current transportation status is "normal" or "abnormal", which helps supply chain managers to quickly understand the situation and then notify relevant personnel to deal with it in time, thereby reducing possible economic losses.

[0040] In an embodiment of the present application, the optimized cargo logistics operation monitoring feature vector is passed through a cargo transportation state classifier to obtain a classification result, and the classification result is used to indicate whether the cargo logistics transportation state at the current time point is abnormal. One possible implementation method may be: using the cargo transportation state classifier to process the optimized cargo logistics operation monitoring feature vector using the following classification formula to generate the classification result; wherein the classification formula is:

[0041] in is the classification result, represents the optimized cargo logistics operation monitoring feature vector, is the weight matrix of the fully connected layer, represents the bias vector of the fully connected layer, is the normalized exponential function.

[0042] In summary, the Internet-based supply chain dynamic real-time management system 100 according to the embodiment of the present application is explained, which uses artificial intelligence-based data analysis technology to determine whether the cargo logistics transportation status is abnormal by performing real-time analysis on the location data of the logistics transport vehicle and the cargo storage environment data on the logistics transport vehicle. In this way, through accurate and fast cargo logistics transportation data processing, supply chain managers can better grasp the real-time status of cargo transportation, thereby making more timely and effective decisions, thereby reducing potential economic losses.

[0043] As described above, the Internet-based supply chain dynamic real-time management system 100 according to the embodiment of the present application can be implemented in various terminal devices, such as a server for Internet-based supply chain dynamic real-time management. In one example, the Internet-based supply chain dynamic real-time management system 100 according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the Internet-based supply chain dynamic real-time management system 100 can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the Internet-based supply chain dynamic real-time management system 100 can also be one of the many hardware modules of the terminal device.

[0044] Alternatively, in another example, the Internet-based supply chain dynamic real-time management system 100 and the terminal device may also be separate devices, and the Internet-based supply chain dynamic real-time management system 100 may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0045] Figure 6 FIG. 1 is a flow chart of a method for dynamic real-time management of a supply chain based on the Internet according to an embodiment of the present application. Figure 6 As shown, in the Internet-based dynamic real-time management method for supply chain, it includes: S110, obtaining the temperature value, humidity value of the cargo storage environment in the logistics transport vehicle at multiple predetermined time points within a predetermined time period and the position data of the logistics transport vehicle at the multiple predetermined time points; S120, performing feature coding processing and feature fusion processing on the temperature value, humidity value of the cargo storage environment in the logistics transport vehicle at the multiple predetermined time points and the position data of the logistics transport vehicle at the multiple predetermined time points to obtain a cargo logistics transportation monitoring feature vector; S130, based on the cargo logistics transportation monitoring feature vector, obtaining a monitoring result of whether the cargo logistics transportation status is abnormal.

[0046] Here, those skilled in the art will appreciate that the specific operations of each step in the above-mentioned Internet-based supply chain dynamic real-time management method have been described in the above reference. Figures 1 to 5 The description of the Internet-based supply chain dynamic real-time management system has been introduced in detail, and therefore, its repeated description will be omitted.

[0047] In summary, the Internet-based dynamic real-time supply chain management method based on the embodiment of the present application is explained, which uses artificial intelligence-based data analysis technology to determine whether the cargo logistics transportation status is abnormal by real-time analysis of the location data of the logistics transport vehicle and the cargo storage environment data on the logistics transport vehicle. In this way, through accurate and rapid cargo logistics transportation data processing, supply chain managers can better grasp the real-time status of cargo transportation, thereby making more timely and effective decisions, thereby reducing potential economic losses.

[0048] Finally, the present application also relates to a computer-readable storage medium for implementing a dynamic real-time management method for a supply chain based on the Internet according to one or more embodiments of the present application. The computer-readable storage medium mentioned herein includes various types of computer storage media, which can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, a computer-readable storage medium may include RAM, ROM, EPROM, E2PROM, registers, hard disks, removable disks, CD-ROMs or other optical disk storage, disk storage or other magnetic storage devices, or any other temporary or non-temporary medium that can be used to carry or store desired program code units in the form of instructions or data structures and can be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. The description of the computer-readable storage medium according to the present application can refer to the explanation of the dynamic real-time management method for a supply chain based on the Internet according to the present application, and no further description will be given.

[0049] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details of the above application are only for the purpose of illustration and ease of understanding, rather than limitation, and the above details do not limit the present application to the use of the above specific details to be implemented.

[0050] In this application, words such as "including", "comprising", "having", etc. are open words, meaning "including but not limited to", and can be used interchangeably therewith. The words "or" and "and" used herein mean the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably therewith.

[0051] It should also be noted that in the system and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0052] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features of the present application.

[0053] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A dynamic real-time supply chain management system based on the Internet, characterized in that: include: The cargo logistics and transportation related data collection module is used to obtain the temperature and humidity values ​​of the cargo storage environment in the logistics transportation vehicle at multiple predetermined time points within a predetermined time period and the location data of the logistics transportation vehicle at the multiple predetermined time points; A cargo logistics transportation related data encoding module is used to perform feature encoding processing and feature fusion processing on the temperature value and humidity value of the cargo storage environment in the logistics transportation vehicle at the plurality of predetermined time points and the position data of the logistics transportation vehicle at the plurality of predetermined time points to obtain a cargo logistics transportation monitoring feature vector; The cargo logistics transportation status monitoring result generation module is used to obtain a monitoring result of whether the cargo logistics transportation status is abnormal based on the cargo logistics transportation monitoring feature vector.

2. The Internet-based supply chain dynamic real-time management system according to claim 1 is characterized in that: The cargo logistics and transportation related data encoding module includes: A logistics transportation cargo storage environment feature extraction unit is used to extract the associated time series features of the temperature values ​​and humidity values ​​of the cargo storage environment in the logistics transportation vehicle at the plurality of predetermined time points to obtain a logistics transportation cargo storage environment time series feature vector; A logistics transport cargo position feature extraction unit, used to extract time series features from the position data of the logistics transport vehicle at the plurality of predetermined time points to obtain a time series feature vector associated with the position change of the logistics transport vehicle; The cargo logistics transportation monitoring feature generation unit is used to fuse the time series feature vector associated with the position change of the logistics transportation vehicle and the time series feature vector of the logistics transportation cargo storage environment to obtain the cargo logistics transportation monitoring feature vector.

3. The Internet-based supply chain dynamic real-time management system according to claim 2 is characterized in that: The logistics transportation cargo storage environment feature extraction unit comprises: The logistics transportation cargo storage environment data structuring subunit is used to arrange the temperature values ​​and humidity values ​​of the cargo storage environment in the logistics transportation vehicle at the plurality of predetermined time points according to the time dimension into a logistics transportation cargo storage environment time series input matrix; A logistics transportation cargo storage environment time series feature generating subunit, used for passing the logistics transportation cargo storage environment time series input matrix through the logistics transportation cargo storage environment time series feature encoder to obtain the logistics transportation cargo storage environment time series feature matrix; The feature matrix expansion subunit is used to expand the time series feature matrix of the logistics transportation cargo storage environment into the time series feature vector of the logistics transportation cargo storage environment.

4. The Internet-based supply chain dynamic real-time management system according to claim 3 is characterized in that: The logistics transportation cargo location feature extraction unit comprises: The logistics transport vehicle position data structuring subunit is used to arrange the position data of the logistics transport vehicles at the plurality of predetermined time points according to the time dimension to obtain a logistics transport vehicle position time series input vector; The logistics transport vehicle position timing feature generation subunit is used to pass the logistics transport vehicle position timing input vector through the transport vehicle position change associated timing feature encoder to obtain the logistics transport vehicle position change associated timing feature vector.

5. The Internet-based supply chain dynamic real-time management system according to claim 4 is characterized in that: The logistics transportation cargo storage environment temporal feature encoder is a convolutional neural network model in which adjacent layers use mutually transposed convolution kernels, and the transport vehicle position change associated temporal feature encoder is a convolutional neural network model comprising a first convolution layer and a second convolution layer, wherein the first convolution layer uses a one-dimensional convolution kernel of a first scale, and the second convolution layer uses a one-dimensional convolution kernel of a second scale, and the first scale is different from the second scale.

6. The Internet-based supply chain dynamic real-time management system according to claim 5 is characterized in that: The cargo logistics transportation status monitoring result generation module includes: A feature optimization unit, used for performing back propagation expression correction on the cargo logistics operation monitoring feature vector based on category distance learning to obtain an optimized cargo logistics operation monitoring feature vector; The feature vector classification unit is used to pass the optimized cargo logistics operation monitoring feature vector through a cargo transportation status classifier to obtain a classification result, and the classification result is used to indicate whether the cargo logistics transportation status at the current time point is abnormal.

7. The Internet-based supply chain dynamic real-time management system according to claim 6 is characterized in that: The feature optimization unit is used to: Determining a classification weight matrix of the cargo transportation status classifier; Decoupling the classification weight matrix in units of row vectors to obtain a set of classification weight vectors; Calculating a metric learning loss information item between each classification weight vector in the set of classification weight vectors and the cargo logistics operation monitoring feature vector to obtain a metric learning compensation representation vector; Inputting the metric learning compensation representation vector into an activation function to obtain a probabilistic metric learning compensation weight vector; Calculate the positional point multiplication of the probabilistic metric learning compensation weight vector and the cargo logistics operation monitoring feature vector to obtain a point product feature vector, and calculate the weighted sum of the point product feature vector and the cargo logistics operation monitoring feature vector to obtain the optimized cargo logistics operation monitoring feature vector.

8. A dynamic real-time management method for supply chain based on the Internet, characterized in that: include: Acquire temperature values ​​and humidity values ​​of the cargo storage environment in the logistics transport vehicle at multiple predetermined time points within a predetermined time period, and position data of the logistics transport vehicle at the multiple predetermined time points; Performing feature coding and feature fusion processing on the temperature and humidity values ​​of the cargo storage environment in the logistics transport vehicle at the plurality of predetermined time points and the position data of the logistics transport vehicle at the plurality of predetermined time points to obtain a cargo logistics transport monitoring feature vector; Based on the cargo logistics transportation monitoring feature vector, a monitoring result of whether the cargo logistics transportation status is abnormal is obtained.

9. The Internet-based supply chain dynamic real-time management method according to claim 8 is characterized in that: The temperature and humidity values ​​of the cargo storage environment in the logistics transport vehicle at the plurality of predetermined time points and the position data of the logistics transport vehicle at the plurality of predetermined time points are subjected to feature coding processing and feature fusion processing to obtain a cargo logistics transport monitoring feature vector, including: Extracting the associated time series features of the temperature and humidity values ​​of the cargo storage environment in the logistics transportation vehicle at the plurality of predetermined time points to obtain a time series feature vector of the logistics transportation cargo storage environment; Extracting time series features from the position data of the logistics transport vehicle at the plurality of predetermined time points to obtain a time series feature vector associated with the position change of the logistics transport vehicle; The logistics transport vehicle position change associated time series feature vector and the logistics transport cargo storage environment time series feature vector are integrated to obtain the cargo logistics transport monitoring feature vector.

10. The Internet-based supply chain dynamic real-time management method according to claim 9, characterized in that: Based on the cargo logistics transportation monitoring feature vector, a monitoring result of whether the cargo logistics transportation state is abnormal is obtained, including: Performing back propagation expression correction based on class distance learning on the cargo logistics operation monitoring feature vector to obtain an optimized cargo logistics operation monitoring feature vector; The optimized cargo logistics operation monitoring feature vector is passed through a cargo transportation status classifier to obtain a classification result, and the classification result is used to indicate whether the cargo logistics transportation status at the current time point is abnormal.

Citation Information

Cited By

  • Cloud baking raw material supply chain optimization management system

    CN119312991A