Multimodal transport digital logistics management method based on AI algorithm and big data analysis

Abstract

The invention relates to the field of logistics transportation, in particular to a multimodal transportation digital logistics management method based on an AI algorithm and big data analysis. The method comprises the steps of performing feature extraction on historical data of different transportation modes, constructing a transportation task feature data set, and calculating similarity and distribution density between data points; and based on the similarity and the distribution density between the data points, updating the positions of the data points of the transportation task, comprehensively evaluating the path, and selecting an optimal path. The problems that resource allocation is unreasonable and path selection is inaccurate in the transportation process due to the fact that a traditional transportation management method cannot comprehensively coordinate and optimize multiple transportation modes are solved; decision delay and information lagging exist, emergency or sudden transportation task changes are difficult to deal with effectively, multi-dimensional comprehensive analysis means are lacked, and the actual benefits of a path cannot be evaluated accurately. And the problem that the global optimization of path selection and resource scheduling cannot be realized due to the lack of path optimization capability based on big data and AI technologies is solved.

Description

Technical Field

[0001] The present invention relates to the field of logistics and transportation, and in particular to a multimodal digital logistics management method based on AI algorithm and big data analysis. Background Art

[0002] With the rapid development of global trade and e-commerce, the logistics industry is facing increasingly complex transportation tasks, especially the increasing demand for multimodal transport (such as road, rail, air and water transport). Traditional logistics and transportation management systems usually only focus on a single mode of transportation and fail to fully consider the coordination and optimization between multiple modes of transportation, resulting in low transportation efficiency, serious waste of resources and high costs. At the same time, due to the rapid development of information technology, a large amount of transportation data is generated, but the traditional logistics and transportation management system fails to effectively integrate this information, especially when dynamically adjusting transportation routes and scheduling, it is difficult to make full use of real-time data for intelligent decision-making, which in turn affects the execution efficiency and accuracy of transportation tasks.

[0003] In addition, as transportation needs become increasingly diversified, customers have put forward higher requirements for the timeliness, reliability and transparency of logistics and transportation, which makes it difficult for traditional transportation scheduling methods to meet the needs of the modern transportation industry. How to reasonably allocate limited transportation resources, optimize transportation routes, and reduce transportation costs while ensuring transportation safety and improving transportation efficiency has become an important issue that needs to be urgently addressed in the logistics and transportation industry.

[0004] The above-mentioned technologies have the following technical problems: lack of comprehensive coordination and optimization of various modes of transportation, resulting in unreasonable resource allocation and inaccurate path selection during transportation, which in turn increases transportation costs and time; there are problems of decision-making delays and information lags, making it difficult to effectively respond to urgent or sudden changes in transportation tasks, lack of multi-dimensional comprehensive analysis methods, and inability to accurately evaluate the actual benefits of the path; lack of path optimization capabilities based on big data and AI technology, and inability to achieve global optimization of path selection and resource scheduling, resulting in great limitations in the efficiency and accuracy of system operation. Summary of the invention

[0005] The present invention provides a multimodal digital logistics management method based on AI algorithm and big data analysis to solve the problems that traditional transportation management methods lack comprehensive coordination and optimization of multiple transportation modes, resulting in unreasonable resource allocation and inaccurate path selection during transportation, thereby increasing transportation costs and time; there are problems of decision-making delays and information lags, making it difficult to effectively respond to urgent or sudden changes in transportation tasks, lack of multi-dimensional comprehensive analysis methods, and inability to accurately evaluate the actual benefits of the path; lack of path optimization capabilities based on big data and AI technology, and inability to achieve global optimization of path selection and resource scheduling, resulting in great limitations in the efficiency and accuracy of system operation.

[0006] The present invention provides a multimodal digital logistics management method based on AI algorithm and big data analysis, which specifically includes the following technical solutions: A multimodal digital logistics management method based on AI algorithm and big data analysis, comprising the following steps: S1. Extract features from historical data of different transportation modes, construct a transportation task feature data set, and calculate the similarity between data points; perform density calculation based on the similarity between data points to obtain the distribution density of data points; S2. Based on the similarity and distribution density between data points, update the data point location of the transportation task, conduct a comprehensive evaluation of the path, and select the optimal path.

[0007] Preferably, the S1 specifically includes: Based on the transport task feature dataset, the straight-line distance and inner product between data points are calculated to obtain the similarity between data points.

[0008] Preferably, the S1 specifically includes: Based on the similarity between data points, weighted factors of distance and inner product are introduced to obtain the distribution density of data points.

[0009] Preferably, the S2 specifically includes: Based on the similarity between data points, external disturbances and current distribution density, the data point positions are updated; the data point position update formula is:

[0010] in, It is Data points In time The position of indicates the updated data point position; It is Data points In time location; is the learning rate; Represents the first Data points and Data points The similarity between It is Data points In time location; It is Data points The external disturbance vector of is the adjustment coefficient of external disturbance; is the adjustment coefficient; It is Data points The distribution density of is the number of data points contained in the transportation task feature dataset.

[0011] Preferably, the S2 specifically includes: A weight calculation model for multimodal transport paths is introduced to calculate the path weight based on the distribution density of data points and the updated data point positions.

[0012] Preferably, the S2 specifically includes: The weight calculation model of the multimodal transport path introduces the time-space inversion factor and combines the distance, transportation time and historical reliability of the path to calculate the path weight; the calculation formula of the path weight is:

[0013]

[0014] in, Is the path In time The weight on Is the path distance; Is the path In time Transportation time on Is the path historical reliability; Is the path In time The space-time inversion factor on ; , , , , , is the weight coefficient; is the time decay factor; is the adjustment coefficient; is the spatial attenuation factor; is the length of the time window; is the time-integrated variable; Is the path In time The weight on .

[0015] Preferably, the S2 specifically includes: Based on the path weight, combined with the path distance, transportation time, historical reliability of the path, and time-space inversion factors, the objective function is constructed, and the globally optimal path selection scheme is selected to obtain the optimal path.

[0016] Preferably, the S2 specifically includes: Connect the optimal route with the logistics management system, convert the route plan and time schedule into route instructions, and send them to various logistics operation systems to achieve real-time data sharing and scheduling of various transportation modes.

[0017] The beneficial effects of the technical solution of the present invention are: 1. By combining AI algorithms and big data analysis, the present invention can achieve real-time path optimization and resource scheduling in a dynamically changing logistics environment; optimize the transportation path through a dynamic evolution mechanism, and introduce a weight calculation model for multimodal transport paths, which comprehensively considers multiple factors such as path distance, transportation time, and historical reliability of different modes of transportation, significantly reducing the additional costs caused by improper route selection or resource scheduling errors during transportation, and improving overall transportation efficiency.

[0018] 2. Based on the density analysis and similarity evaluation of big data, the present invention can monitor and respond to complex changes in transportation tasks in real time, such as environmental factors, market demand fluctuations, etc., and dynamically adjust resources according to real-time data and historical data to ensure that each link in multimodal transport can be accurately connected, further enhancing the flexibility and adaptability of the logistics management system.

[0019] 3. Through the accumulation and analysis of historical transportation data, the present invention can assign a reliability index to each transportation route, reflecting the performance of each route in past transportation tasks, which helps to evaluate the stability and safety of the route, so that the route selection not only depends on real-time data, but also fully considers historical performance, further improving the accuracy and safety of route selection.

[0020] 4. The present invention integrates multiple modes of transportation such as road, rail, water and aviation, giving full play to the advantages of each mode of transportation, and realizing real-time data sharing and scheduling between various modes of transportation through a digital platform, which not only optimizes the route selection, but also ensures the smooth connection of each transportation link, thereby improving the overall logistics efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flow chart of the multimodal digital logistics management method based on AI algorithm and big data analysis described in the present invention. DETAILED DESCRIPTION

[0022] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0024] The following is a detailed description of a multimodal digital logistics management method based on AI algorithm and big data analysis provided by the present invention in conjunction with the accompanying drawings.

[0025] Specifically, as an embodiment, a multimodal digital logistics management method based on AI algorithm and big data analysis is as follows: First, we collect comprehensive data on all transportation tasks, including but not limited to the starting location, end location, task load, required resource type, transportation time requirements, and historical transportation data of each transportation task; at the same time, we use big data technology to extract features from historical data of different transportation modes and build a transportation task feature data set. , is the number of data points contained in the transport task feature dataset; based on the transport task feature dataset, the similarity between the data points is calculated, and the distribution density of each data point in space is evaluated; Then, the position of each data point is dynamically evolved, and the position of the data point is accurately updated based on the similarity between the data points, external disturbances, and the current distribution density. The data point position update formula is:

[0026] in, It is Data points In time The position of , that is, the updated data point position; It is Data points In time The position of , that is, the position of the data point before the update; is the learning rate, which is used to control the step size of the data point position update and is obtained through experiments; Represents the first Data points and Data points The similarity between It is Data points In time location; It is Data points The external disturbance vector acts on Data points External factors that influence is the adjustment coefficient of external disturbance, which is used to control the influence of external factors on position update and is obtained through experiments; is the adjustment coefficient, which is used to control the effect of distribution density on position update and is obtained through experiments; It is Data points The distribution density reflects the degree of aggregation of data points in space; Furthermore, a weight calculation model for multimodal transport paths is designed to calculate path weights based on the distribution density of data points and the updated data point positions. The calculation formula for path weights is:

[0027]

[0028] in, Is the path In time The weight on indicates the quality of the path; Is the path distance; Is the path In time Transportation time on Is the path Historical reliability, based on the path In time The deviation between the actual time experienced and the expected time is calculated; Is the path In time The spatiotemporal inversion factor on is used to reflect the spatiotemporal variability of the path; , , , , , is the weight coefficient, which is used to adjust the contribution of each factor to the path weight calculation and is obtained through experiments; is the time decay factor, which is used to control the effect of path changes over time and is obtained experimentally; is the adjustment coefficient, which is used to control the smoothness of the spatiotemporal inversion factor and is obtained through experiments; is the spatial attenuation factor, which is used to control the effect of the path distance on the space-time inversion factor and is obtained through experiments; is the length of the time window, which is used to determine the calculation period of the spatiotemporal inversion factor; is the time-integrated variable; Is the path In time The weight on Finally, according to the path weight, combined with the path distance, transportation time, historical reliability of the path, and time-space inversion factors, an objective function is constructed to select the optimal path; the construction of the objective function uses existing technology and is not elaborated here; the optimal path is connected to the logistics management system, and the specific path plan and time schedule are converted into path instructions, which are sent to various logistics operation systems to realize real-time data sharing and scheduling of various transportation modes, ensuring the smooth connection of each transportation link.

[0029] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods; As an example, refer to the attached Figure 1 , which shows a flow chart of a multimodal digital logistics management method based on AI algorithm and big data analysis provided by an embodiment of the present invention, the method comprising the following steps: S1. Extract features from historical data of different transportation modes, construct a transportation task feature data set, and calculate the similarity between data points; perform density calculation based on the similarity between data points to obtain the distribution density of data points; Comprehensive data collection is conducted on all transport tasks, including but not limited to the starting location, ending location, task load, required resource type, transport time requirements, and historical transport data of each transport task. Through sensor networks and GPS positioning technology, the starting location, ending location, and transport route of each transport task are monitored in real time to ensure the accuracy of each data point; the Internet of Things (IoT) technology is used to monitor resource requirements in real time, such as monitoring the load of trucks, vehicle status, and specific requirements of goods, so that key data related to transport tasks can be obtained at any time, providing accurate support for route optimization and resource scheduling.

[0030] In addition to collecting real-time data, it also relies on the integration of historical data, which contains various characteristics of past transportation tasks, such as transportation time, cost, delays, problems in the transportation process, etc. The acquisition and processing of historical data will ensure its availability through steps such as data cleaning and normalization to avoid deviations in the subsequent optimization process due to incomplete or erroneous data.

[0031] By using big data technology to analyze historical data of different modes of transportation (such as land transportation, sea transportation, air transportation, etc.), we can extract the key features of transportation tasks, calculate the performance indicators of each mode of transportation (such as transportation time, cost, risk, etc.), and build a transportation task feature data set. , is the number of data points included in the transport task feature dataset, which contains all transport task information (e.g., time, location, resource requirements, and load).

[0032] By evaluating the similarity between data points, we can better understand the overall characteristics of the transportation task; by calculating the similarity between data points and constructing a similarity matrix based on a weighted model based on Euclidean distance and inner product, we can measure the similarity between data points; the calculation of similarity is not only based on straight-line distance, but also takes into account the inner product between data points, which can better express the similarity of data points in high-dimensional space, ensuring that path selection and resource scheduling can be performed based on the comprehensive information of data points, avoiding inaccurate path selection caused by overly simple distance measurement. The formula for constructing the similarity matrix is ​​as follows:

[0033] in, Represents the first Data points and Data points The similarity between them is determined by calculating the distance between two data points; and Respectively represent data points and data points; It is Data points and Data points The Euclidean distance between It is used to adjust the Data points and Data points The standard deviation of the similarity between It is Data points and Data points The inner product between It is an adjustment term used to adjust the contribution of the inner product to the similarity, obtained through experiments. Euclidean distance It measures the direct spatial distance between data points, indicating how close two data points are in geometric space. , further considers the linear correlation of data points in different dimensions, helping to capture more complex similarity relationships.

[0034] In big data analysis, density analysis helps identify the distribution characteristics of transportation tasks in space, and density calculation is performed based on the calculated similarity matrix to evaluate the distribution density of each data point in space. The calculation of distribution density not only considers the similarity between data points, but also introduces weighted factors of distance and inner product to ensure that the density value can truly reflect the relative position and relationship of data points; by weighting similarity and adjusting the influence range of density, it ensures that the distribution density of each data point can accurately reflect the local aggregation characteristics of the transportation task feature data set in space, which helps to further guide the evolution process of data points and the optimization of path selection and resource scheduling. The calculation formula of distribution density is:

[0035] in, It is Data points The distribution density reflects the degree of aggregation of data points in space; It is Data points and Data points The Euclidean distance between them indicates the degree of separation of the two data points in space; is the weight coefficient, which is used to control the effect of Euclidean distance on distribution density and is adjusted through experiments; is the weight coefficient, which is used to control the influence of the inner product on the distribution density and is adjusted through experiments. By calculating the distribution density of each data point, it reflects the degree of aggregation of the data points in the overall space.

[0036] S2. Based on the similarity and distribution density between data points, update the data point location of the transportation task, conduct a comprehensive evaluation of the path, and select the optimal path.

[0037] In the process of path selection and resource scheduling, dynamic evolution is one of the core mechanisms. Each data point is updated according to certain rules in each round of iteration, and path selection is optimized through dynamic evolution. Specifically, in the process of evolution, each data point is not only affected by the similarity with other data points, but also adjusted according to the influence of external disturbances and distribution density. Therefore, in each round of update process, it is necessary to consider how to accurately update its position based on the current state of the data point, combined with the similarity matrix, external disturbances and current distribution density. The data point position update formula is:

[0038] in, It is Data points In time The position of , that is, the updated data point position; It is Data points In time The position of , that is, the position of the data point before the update; is the learning rate, which is used to control the step size of the data point position update and is obtained through experiments; It is Data points In time location; It is Data points The external disturbance vector acts on Data points External factors, including physical forces, environmental changes, market changes, etc. is the adjustment coefficient of external disturbance, which is used to control the influence of external factors on position update and is obtained through experiments; is the adjustment coefficient, which is used to control the influence of distribution density on position update and is obtained through experiments. The position update of each data point is not only affected by the similarity with other data points, but also by the external disturbance vector and distribution density. Through dynamic evolution, data points can be gradually migrated to the optimal position, so as to play a better role in subsequent path selection and resource scheduling.

[0039] Considering that multimodal transport involves different modes of transport, route selection does not rely on a single mode of transport, but needs to comprehensively consider the advantages and disadvantages of various modes of transport. Therefore, a weight calculation model for multimodal transport routes is designed; the weight of the route is a measure of the route's time. The key indicators of comprehensive benefits take into account the influence of multiple factors, such as the distance of the path, transportation time, historical reliability of the path, and the space-time inversion factor. Specifically, the distance and transportation time of the path are the most basic measurement criteria, which affect the physical distance and time cost in the transportation process respectively; the historical reliability of the path reflects the performance of the path in past transportation tasks, and can reflect the stability and safety of the path; the space-time inversion factor further introduces the impact of historical paths on the current path selection, and considers the reference role of the operation trajectory of historical paths for current decisions; using the distribution density and the updated data point position as dynamic adjustment factors, it can optimize the path selection in real time according to the actual changes in the transportation tasks. Therefore, the calculation formula for the path weight is:

[0040]

[0041] in, Is the path In time The weight on indicates the quality of the path; Is the path distance; Is the path In time Transportation time on Is the path Historical reliability, based on the path In time The deviation between the actual time experienced and the expected time is calculated; Is the path In time The spatiotemporal inversion factor on is used to reflect the spatiotemporal variability of the path; , , , , , is the weight coefficient, which is used to adjust the contribution of each factor to the path weight calculation and is obtained through experiments; is the time decay factor, which is used to control the effect of path changes over time and is obtained experimentally; is the adjustment coefficient, which is used to control the smoothness of the spatiotemporal inversion factor and is obtained through experiments; is the spatial attenuation factor, which is used to control the effect of the path distance on the space-time inversion factor and is obtained through experiments; is the length of the time window, which is used to determine the calculation period of the spatiotemporal inversion factor; is the time-integrated variable; Is the path In time The weight on .

[0042] The goal of optimal path selection is to comprehensively evaluate the advantages and disadvantages of the path based on multiple factors, and select the optimal path that can minimize the overall transportation cost and time. The factors include the distance of the path, the transportation time, the historical reliability of the path, and the time-space inversion factor. Construct the optimal path objective function, and obtain a global optimal path selection plan by weighted calculation of the various costs of all paths, so as to effectively meet the various requirements of the transportation task, reduce costs and improve efficiency. The optimal path objective function is as follows:

[0043] in, is the optimal path, indicating the shortest path selected; is the set of all paths; and is the adjustment coefficient, which is used to adjust the impact of path distance and spatiotemporal inversion factors on path selection.

[0044] The optimal path is connected to the logistics management system, and the specific path plan and time schedule are converted into path instructions, which are sent to various logistics operation systems, including the control systems of various transportation tools such as transportation vehicles, ships, and aircraft. The path instructions include information such as transportation time, starting point, end point, and path nodes. The optimal path involves the coordinated operation of multiple modes of transportation, such as road, rail, water, and air transportation. Real-time data sharing and scheduling of various modes of transportation are achieved through a digital platform to ensure smooth connection of each transportation link.

[0045] Through IoT devices and sensors, data from each transportation link is obtained in real time, including transportation progress, cargo status, environmental conditions, etc. All information is summarized and analyzed through a digital platform and provided to operators and decision makers to ensure that they can understand every detail of the logistics process in a timely manner and make necessary adjustments.

[0046] In summary, a multimodal digital logistics management method based on AI algorithm and big data analysis has been completed.

[0047] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0048] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0049] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A multimodal digital logistics management method based on AI algorithm and big data analysis, characterized in that: The following steps are involved: S1. Extract features from historical data of different transportation modes, construct a transportation task feature data set, and calculate the similarity between data points; perform density calculation based on the similarity between data points to obtain the distribution density of data points; S2. Based on the similarity and distribution density between data points, update the data point location of the transportation task, conduct a comprehensive evaluation of the path, and select the optimal path.

2. According to claim 1, a multimodal digital logistics management method based on AI algorithm and big data analysis is characterized in that: The S1 specifically includes: Based on the transport task feature dataset, the straight-line distance and inner product between data points are calculated to obtain the similarity between data points.

3. The multimodal digital logistics management method based on AI algorithm and big data analysis according to claim 2 is characterized in that: The S1 specifically includes: Based on the similarity between data points, weighted factors of distance and inner product are introduced to obtain the distribution density of data points.

4. According to claim 1, a multimodal digital logistics management method based on AI algorithm and big data analysis is characterized in that: The S2 specifically includes: Based on the similarity between data points, external disturbances and current distribution density, the data point positions are updated; the data point position update formula is: in, It is Data points In time The position of indicates the updated data point position; It is Data points In time location; is the learning rate; Represents the first Data points and Data points The similarity between It is Data points In time location; It is Data points The external disturbance vector of is the adjustment coefficient of external disturbance; is the adjustment coefficient; It is Data points The distribution density of is the number of data points contained in the transportation task feature dataset.

5. The multimodal digital logistics management method based on AI algorithm and big data analysis according to claim 4 is characterized in that: The S2 specifically includes: A weight calculation model for multimodal transport paths is introduced to calculate the path weight based on the distribution density of data points and the updated data point positions.

6. The multimodal digital logistics management method based on AI algorithm and big data analysis according to claim 5 is characterized in that: The S2 specifically includes: The weight calculation model of the multimodal transport path introduces the time-space inversion factor and combines the distance, transportation time and historical reliability of the path to calculate the path weight; the calculation formula of the path weight is: in, Is the path In time The weight on Is the path distance; Is the path In time Transportation time on Is the path historical reliability; Is the path In time The space-time inversion factor on ; , , , , , is the weight coefficient; is the time decay factor; is the adjustment coefficient; is the spatial attenuation factor; is the length of the time window; is the time-integrated variable; Is the path In time The weight on .

7. The multimodal digital logistics management method based on AI algorithm and big data analysis according to claim 6 is characterized in that: The S2 specifically includes: Based on the path weight, combined with the path distance, transportation time, historical reliability of the path, and time-space inversion factors, the objective function is constructed, and the globally optimal path selection scheme is selected to obtain the optimal path.

8. The multimodal digital logistics management method based on AI algorithm and big data analysis according to claim 7 is characterized in that: The S2 specifically includes: Connect the optimal route with the logistics management system, convert the route plan and time schedule into route instructions, and send them to various logistics operation systems to achieve real-time data sharing and scheduling of various transportation modes.

Images