Multimodal transport service network optimization method

Abstract

The invention discloses a multimodal transport service network optimization method, which relates to the technical field of freight transport, and comprises the following steps: constructing a unified nanosecond global synchronous clock reference, carrying out time synchronization on hub nodes in various transport modes, collecting first frequency data and second frequency data in real time based on the clock reference, and carrying out time synchronization on hub nodes in various transport modes; the first frequency data is an information flow refresh frequency, and the second frequency data is a logistics physical flow shift frequency. By unifying the nanosecond synchronous clock and the block chain timestamp, high-precision synchronization and deep calibration of the information flow and the logistics flow in multiple transportation modes are realized, and multimodal transportation time consistency and data credibility are improved. The speed benchmarking matrix and wavelet phase difference analysis are combined, synchronous unbalance is accurately quantified, the digital twin is driven by a real-time unbalance index to dynamically complement information flow, the continuity and accuracy of a scheduling decision are guaranteed, and operation errors and transportation risks are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of freight transportation, and in particular to a method for optimizing a multimodal transport service network. Background Art

[0002] Intermodal transport service network optimization refers to the efficient connection and resource allocation between different modes of transport (such as rail, road, water, and aviation) in the freight and transportation sector through systematic design and dynamic collaborative management. This approach aims to improve overall transport efficiency, reduce logistics costs, shorten transport cycles, and enhance the robustness and responsiveness of the transport network. This optimization process not only involves the joint planning of transport routes, hubs, vehicle scheduling, and vehicle switching, but also involves integrated scheduling and intelligent decision-making based on factors such as the timeliness, capacity matching, loading and unloading efficiency, and information flow synchronization of each mode of transport. By applying operational optimization, intelligent algorithms, and big data analysis, optimizing the intermodal transport network can achieve optimal allocation of transport resources, dynamic decongestion of bottleneck nodes, and multi-scenario emergency scheduling. This ultimately builds a low-carbon, efficient, flexible, and cost-sensitive integrated logistics service system, enhancing the overall stability and competitiveness of the supply chain.

[0003] The existing technology has the following deficiencies: In multimodal transport hubs, existing technologies commonly suffer from a mismatch between the speed of information flow at hub nodes and the speed of physical logistics. This is particularly true during transshipment, which involves multiple modes of transport. The data exchange and monitoring systems at hub nodes fail to fully cover all aspects of the logistics process, leading to synchronization discrepancies between information flow and cargo flow. This can lead to operational errors such as misdirection, missed shipments, and duplicate loading and unloading, reducing the visibility and traceability of the entire multimodal transport process. This problem is particularly acute in transport scenarios involving high-value or sensitive goods. Loss or delays in information flow can lead to incorrect cargo flow, abnormal cargo delays, and even transportation accidents, posing a serious threat to the stability and security of the logistics chain.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for optimizing an intermodal transport service network. By unifying the nanosecond-level global synchronous clock benchmark and blockchain timestamp, high-precision time synchronization and deep calibration of information flow and logistics flow under various transport modes can be achieved, thereby improving the time consistency and data credibility of the entire intermodal transport process. Through speed benchmarking matrix and multi-scale wavelet phase difference analysis, the synchronization deviation can be accurately characterized and the synchronization imbalance can be quantified. By combining the real-time imbalance index with the incremental residual matching of the digital twin, the information flow gaps can be dynamically filled to ensure the continuity and accuracy of scheduling decisions. The overall visualization and intelligent scheduling capabilities of intermodal transport are improved, the stability and security of the logistics network are enhanced, and operational errors and transportation risks are reduced to solve the problems in the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for optimizing a multimodal transport service network, comprising the following steps: S101. Build a unified nanosecond-level global synchronous clock benchmark to synchronize the time of various hub nodes under various transportation modes. Based on the synchronous clock benchmark, collect the first frequency data and second frequency data of each hub node in real time. The first frequency data represents the refresh frequency of the information flow, and the second frequency data represents the displacement frequency of the physical flow of logistics. Ensure that the collected first and second frequency data have a unified nanosecond-level time calibration. S102. Based on a unified nanosecond-level global synchronous clock reference and in combination with a blockchain-based multi-party verifiable timestamp mechanism, perform a time domain deep calibration of the first frequency data and the second frequency data across transport modes. Dynamically generate a timing consistency matrix based on the calibrated first frequency data and the second frequency data. The timing consistency matrix is ​​used to ensure time synchronization across the entire process of multiple transport modes. S103. Based on the time consistency matrix, extract the transmission velocity vector corresponding to the information flow and the displacement velocity vector corresponding to the physical flow of the logistics, and construct a velocity benchmarking matrix under a unified scale based on the transmission velocity vector and the displacement velocity vector. The velocity benchmarking matrix is ​​used to provide a data foundation and scale unification for subsequent frequency domain and phase analysis; S104. Based on the velocity benchmarking matrix, a multi-scale wavelet phase difference analysis method is applied to analyze the phase difference and mismatch amplitude of the transmission velocity vector and the displacement velocity vector in multiple time windows, thereby obtaining the phase shift spectrum and mismatch amplitude of the information flow and logistics physical flow velocity vectors, and forming a synchronization deviation feature set covering multiple time scales; S105. Based on the synchronization deviation feature set, an adaptive entropy weight assignment mechanism is used to dynamically weight the synchronization deviation features at different time scales. Based on the weighted processing results, a real-time imbalance index is calculated. The real-time imbalance index is used to quantify the degree of synchronization imbalance between information flow and physical flow of logistics. S106. Based on the incremental residual matching mechanism of the digital twin driven by the real-time imbalance index, the digital twin is used to continuously track the residual dynamics between the physical flow trajectory of logistics and the information flow data, and high-frequency hypothetical state update frames are generated based on the residual dynamics. Through the hypothetical state update frames, in the scenario where there is a lag or breakpoint in the information flow, the gaps in system perception are filled, and the continuity and accuracy of scheduling decisions in the multimodal transport service network are maintained.

[0007] Preferably, S101 includes: Establish a unified nanosecond-level global synchronized clock benchmark at each hub node under various transportation modes. By configuring high-precision atomic clocks or global navigation satellite system timing devices and combining them with wide-area clock synchronization protocols, synchronize time signals to all hub nodes and deploy time synchronization devices to maintain a nanosecond-level error range. Collect first-frequency data and second-frequency data in real time, and configure a high-precision timestamp marking mechanism based on a synchronous clock reference to stamp each collected data with a nanosecond-level timestamp and synchronize verification; The collected first-frequency data and second-frequency data are checked for consistency and cleaned to remove abnormal points. The data sequence is optimized through interpolation repair and time series smoothing to establish a time series index based on unified time calibration.

[0008] Preferably, S102 includes: Based on a unified nanosecond-level global synchronous clock reference, the first-frequency data and the second-frequency data are preliminarily time-aligned to correct time errors caused by local clock drift or signal delays in different transport modes. Combined with the blockchain's multi-party verifiable timestamp mechanism, the preliminarily aligned data timestamps are written into the blockchain ledger, and the timestamps are stored and verified through distributed consensus to ensure the integrity and authenticity of the timestamps. Based on the blockchain verification results, a time domain deep calibration algorithm is used to dynamically calculate the time drift and delay compensation value, and dynamic time warping and time series interpolation technology are used to achieve refined time alignment of data; Based on the deeply calibrated data, a time consistency matrix is ​​dynamically generated to record the time stamps and data status of information flow and physical logistics flow, which is used to reflect the time synchronization relationship and change trend of the entire process.

[0009] Preferably, S103 includes: Based on the time consistency matrix, the transmission speed vector of information flow and the displacement speed vector of logistics physical flow are extracted. The information flow rate is calculated by frequency increment and time difference, and the logistics speed is calculated by displacement distance and time interval. Perform maximum and minimum normalization or standard deviation normalization on the extracted transmission velocity vector and displacement velocity vector, unify the numerical scale, and set the weight coefficient according to application requirements; A speed benchmarking matrix with a unified scale is constructed based on the normalized speed vector. The matrix elements record the correspondence between the information flow and the logistics flow speed, and introduce speed difference and change trend indicators. The velocity calibration matrix is ​​smoothed and completed using interpolation or sliding average to complete timing calibration and index optimization, ensuring data continuity and stability for frequency domain and phase analysis.

[0010] Preferably, S104 includes: According to the speed benchmarking matrix, multiple time windows are set to sample the information flow transmission speed vector and the logistics physical flow displacement speed vector in sections to form a time series pair; Apply continuous wavelet transform to the velocity vector sequence in each time window, perform multi-scale decomposition using wavelet basis functions, extract amplitude and phase information at different frequencies, and obtain the phase spectrum of each vector; Based on the wavelet transform results, the phase difference and mismatch amplitude of the two vectors at the same time scale and frequency are calculated to form the phase shift spectrum and mismatch amplitude spectrum; Based on the phase offset spectrum and mismatch amplitude spectrum, a synchronization deviation feature set including indicators such as average phase difference, phase difference variance, and maximum mismatch amplitude is constructed, and scale unification and sequence encoding are achieved through feature normalization and time series identification.

[0011] Preferably, S105 includes: Based on the synchronization deviation feature set, an initial entropy weight model for feature weight evaluation is established. The entropy value of each feature is calculated through information entropy to form the initial weight distribution. Based on the entropy weight model, the sliding time window is combined to dynamically evaluate the volatility and trend of the features in the current time series, an adaptive adjustment mechanism is used to dynamically correct the feature weights, and a time scale weight adjustment factor is introduced; Based on the dynamic weighted feature weights, the synchronization deviation feature set is weighted and summed to form a weighted comprehensive deviation sequence to quantify the global synchronization deviation; Based on the weighted comprehensive deviation sequence, combined with statistical normalization and dynamic baseline comparison, the real-time imbalance index is calculated, and the sensitivity and robustness of the real-time imbalance index are enhanced through exponential smoothing and trend correction factors.

[0012] Preferably, S106 includes: Based on the dynamic changes of the real-time imbalance index, the incremental residual tracking start conditions and frequency of the digital twin are determined, and the incremental residual between the physical flow trajectory of logistics and the information flow data is dynamically calculated; Based on the continuous tracking of incremental residuals, trend extraction, fluctuation analysis and mutation detection algorithms are applied to extract the dynamic characteristics of residuals and identify hysteresis patterns, breakpoint patterns or abnormal drift patterns; Based on the dynamic characteristics of the residual, time series prediction and state space modeling are used to generate high-frequency hypothetical state update frames, predict the expected state of the information flow and mark the confidence level and error range; Based on the hypothetical state update frame, the scheduling decision logic is dynamically completed, the logistics trajectory and information flow data are integrated, the perception blind spots are eliminated, and the accuracy and adaptability of the prediction model are optimized through continuous comparison and correction.

[0013] In the above technical solution, the technical effects and advantages provided by the present invention are: By constructing a unified nanosecond-level global synchronous clock benchmark and combining it with a blockchain-based multi-party verifiable timestamp mechanism, this invention achieves high-precision time synchronization and deep cross-modal calibration of information flows and physical logistics flows under various transportation modes, comprehensively improving the time consistency and data credibility of the entire multimodal transport process. Through the coordinated application of the speed benchmark matrix and multi-scale wavelet phase difference analysis, it can accurately characterize the synchronization deviation characteristics of information flows and physical logistics flows at different time scales, and dynamically evaluate and quantify their degree of synchronization imbalance. Furthermore, relying on the real-time imbalance index and the incremental residual matching mechanism of the digital twin, it continuously tracks and dynamically fills in the perception gaps in the information flow. Especially in scenarios where the information flow is lagging or at a breakpoint, it can maintain the continuity and accuracy of scheduling decisions by generating high-frequency hypothetical state update frames. Overall, it significantly improves the full-link visualization level and scheduling intelligence capabilities of the multimodal transport service network, enhances the stability, resilience, and security of the logistics network in complex and changing environments, and effectively reduces the error rate of logistics operations and transportation safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction to the drawings required for use in the embodiments will be given below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0015] Figure 1 The present invention is a method flow chart of a multimodal transport service network optimization method. DETAILED DESCRIPTION

[0016] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0017] The present invention provides Figure 1 A multimodal transport service network optimization method shown includes the following steps: S101. Build a unified nanosecond-level global synchronous clock benchmark to synchronize the time of various hub nodes under various transportation modes. Based on the synchronous clock benchmark, collect the first frequency data and second frequency data of each hub node in real time. The first frequency data represents the refresh frequency of the information flow, and the second frequency data represents the displacement frequency of the physical flow of logistics. Ensure that the collected first and second frequency data have a unified nanosecond-level time calibration. The specific implementation is as follows: First, a unified nanosecond-level global synchronized clock benchmark is established. Specifically, by configuring high-precision atomic clocks or global navigation satellite system timing devices, combined with a wide-area clock synchronization protocol, the time signal is synchronously transmitted to all hub nodes participating in multimodal transport, ensuring that various hub nodes under different transport modes operate collaboratively under the same time reference framework. By deploying a high-stability time synchronization device at each hub node, it is ensured that the local clocks of all hub nodes and the global synchronized clock benchmark remain within the nanosecond error range. In addition, to ensure the time synchronization accuracy during long-term operation, a self-checking and dynamic correction mechanism for time synchronization is implemented. The error between the local clock and the global synchronized clock benchmark is periodically compared, and the timing accuracy of the local clock is automatically corrected based on the comparison results.

[0018] On the basis of completing the global nanosecond-level time synchronization, the real-time collection of the first frequency data and the second frequency data is implemented for various hub nodes under various transportation modes. Specifically, in the process of data information collection at the hub node, the frequency of operations such as data refresh, information interaction, and data update are detected and recorded in real time for the processing link of the information flow, thereby forming the first frequency data. Synchronously, in the process of physical flow of logistics, the displacement frequency of the goods at different nodes is measured in real time through continuous monitoring of the physical movement path, displacement distance, and arrival and departure time of the goods to obtain the second frequency data. The collection of both types of frequency data needs to be accurately time-stamped under a unified time base to avoid time deviations caused by different time sources.

[0019] To ensure that the data sources for the aforementioned first- and second-frequency data have uniform nanosecond-level time calibration, a high-precision timestamp mechanism must be configured during the collection process. This mechanism, based on a globally synchronized clock reference, accurately timestamps each information flow refresh or physical movement capture event and performs nanosecond-level synchronization verification on all timestamps. This timestamp verification ensures that the first- and second-frequency data have a one-to-one correspondence on the same time scale, achieving time alignment and uniform accuracy for different data types.

[0020] To ensure data calibration accuracy and integrity, the collected first- and second-frequency data must undergo consistency verification and data cleaning. Specifically, this involves removing data anomalies caused by sensor errors, signal delays, or abnormal fluctuations, and using methods such as interpolation and time series smoothing to correct and optimize the data series. Based on the unified time calibration results, a time series index is established for the data sets of information flow and physical logistics flow, allowing for subsequent accurate modeling and analysis of the synchronization relationship, frequency response, and phase differences between the information flow and logistics flow.

[0021] Through the coordinated implementation of the above steps, the full-area time synchronization and high-precision frequency data collection of the multimodal transport hub can be effectively achieved, providing a solid data foundation and time guarantee for subsequent time domain calibration and synchronization analysis.

[0022] S102. Based on a unified nanosecond-level global synchronous clock reference and in combination with a blockchain-based multi-party verifiable timestamp mechanism, perform a time domain deep calibration of the first frequency data and the second frequency data across transport modes. Dynamically generate a timing consistency matrix based on the calibrated first frequency data and the second frequency data. The timing consistency matrix is ​​used to ensure time synchronization across the entire process of multiple transport modes. The specific implementation is as follows: First, based on the established unified nanosecond-level global synchronized clock reference, a preliminary time alignment is performed on the first-frequency data and second-frequency data collected from each hub node under different transportation modes. This step verifies the time stamps and time series of all collected data, corrects data with deviations in collection time based on the nanosecond-level time reference, and adjusts time errors caused by local device clock drift, signal transmission delays, and other factors across different transportation modes to a globally unified time frame. This preliminary alignment ensures basic temporal consistency between different data sources, laying the foundation for subsequent in-depth calibration.

[0023] Integrating a blockchain-based multi-party verifiable timestamp mechanism, the preliminarily aligned first and second frequency data undergo reliable time calibration and verification. Specifically, the timestamp information for the first and second frequency data is hashed into the blockchain ledger. Through blockchain's distributed consensus mechanism, multi-party verification and tamper-proof storage of the timestamps are achieved. By storing and verifying all key time points on-chain, the integrity and authenticity of the timestamps are ensured, preventing time inconsistencies caused by data falsification or record tampering in multi-modal and multi-party scenarios. This ensures the credibility and transparency of the subsequent calibration process.

[0024] Based on the blockchain verification results of the aforementioned timestamps, a time-domain deep calibration algorithm is used to fine-tune the time alignment of the first-frequency data and the second-frequency data. This deep calibration analyzes the time series characteristics of the first-frequency data and the second-frequency data, combining the timestamp differences before and after the correction, to dynamically calculate the time drift and delay compensation value of the cross-transportation mode data, thereby achieving accurate mapping of data in different modes onto a unified timeline. In this process, to address the nonlinear changes in time drift under multiple transportation modes, a dynamic time warping algorithm and time series interpolation technology are used to correct time alignment errors within different time periods, ensuring that each data point forms a strictly consistent time stamp throughout the entire process.

[0025] A time consistency matrix is ​​dynamically generated based on the first-frequency data and second-frequency data that have undergone deep time domain calibration. This matrix maps the time series of the first-frequency data and the second-frequency data to the row and column axes of a two-dimensional matrix. The matrix elements record the time stamps and data status of the information flow and physical logistics flow at corresponding time points. This matrix can intuitively reflect the time synchronization relationship and changing trends of data under different transportation modes. The time consistency matrix not only provides a standardized time mapping foundation for subsequent speed benchmarking and phase analysis of information flow and logistics flow, but also serves as an important supporting tool for full-link visualization, scheduling optimization, and anomaly detection in multimodal transport.

[0026] Through the progressive and coordinated effects of the above steps, the time consistency and data credibility of information flow and physical logistics flow under cross-transportation modes have been comprehensively improved, and high-precision, full-process time synchronization and dynamic optimization of the multimodal transport service network have been achieved.

[0027] S103. Based on the time consistency matrix, extract the transmission velocity vector corresponding to the information flow and the displacement velocity vector corresponding to the physical flow of the logistics, and construct a velocity benchmarking matrix under a unified scale based on the transmission velocity vector and the displacement velocity vector. The velocity benchmarking matrix is ​​used to provide a data foundation and scale unification for subsequent frequency domain and phase analysis; The specific implementation is as follows: First, based on the temporal consistency matrix, for each time node of the information flow and the physical logistics flow, the transmission velocity vector corresponding to the information flow and the displacement velocity vector corresponding to the physical logistics flow are extracted. Specifically, for the information flow, by calculating the frequency increment and time difference of the adjacent information state changes at each time node, the rate of change of the information flow at each moment is quantified to form the transmission velocity vector of the information flow. For the physical logistics flow, based on the displacement distance of each cargo in physical space and the corresponding time interval, the displacement velocity per unit time is calculated to form the displacement velocity vector of the physical logistics flow. This step ensures that the data of the information flow and the physical logistics flow are expressed in the form of velocity vectors, establishing a direct quantification basis for the dynamic changes of both.

[0028] The extracted transmission velocity vectors and displacement velocity vectors are scale-normalized. Because the transmission velocity of information flow and the displacement velocity of physical logistics flow differ in terms of units, orders of magnitude, and range of variation, a direct comparison will result in inconsistent data dimensions, affecting the accuracy of subsequent analysis. To this end, using methods based on maximum and minimum normalization or standard deviation normalization, the two types of velocity vectors are uniformly mapped to the same numerical interval or standard distribution, ensuring that the velocity vectors are comparable and operational at the same numerical scale. Furthermore, during the normalization process, corresponding weight coefficients are set for the velocity vectors of information flow and physical logistics flow based on actual application requirements to enhance numerical sensitivity to specific flow stages or key nodes.

[0029] Based on the normalized transmission speed vector and displacement speed vector, a speed benchmarking matrix with a unified scale is constructed. The row and column axes of the matrix correspond to the time series of information flow and the time series of physical logistics flow, respectively. Each element in the matrix forms a speed benchmarking association by matching the speed values ​​of information flow and physical logistics flow at the corresponding time point. In order to improve the representation ability of the speed benchmarking matrix, the absolute value of speed difference, relative ratio and trend index of speed change are further introduced as supplementary dimensions of the matrix to comprehensively reflect the dynamic synchronization and speed synergy of information flow and logistics flow at different time points. The speed benchmarking matrix not only records static speed comparison data, but also covers the dynamic trajectory of speed change, forming a speed benchmarking mapping with complete data dimensions and rich representation capabilities.

[0030] To ensure the compatibility and data continuity of the velocity calibration matrix in subsequent frequency-domain and phase analysis, the constructed velocity calibration matrix undergoes data smoothing and missing data completion. Mathematical methods such as interpolation and sliding averages are used to correct gaps and sudden changes caused by discontinuous data acquisition or abnormal fluctuations, improving the smoothness and continuity of the matrix data. Furthermore, the matrix undergoes time-series calibration and index optimization to ensure flexible access and analysis at multiple time scales, providing a stable, accurate, and traceable data foundation for subsequent frequency-domain wavelet phase difference analysis and synchronization deviation feature extraction.

[0031] Through the systematic implementation of the above steps, accurate matching of information flow and physical logistics flow at the speed level is achieved, and a speed matching matrix with unified scale, complete structure and dynamic response capability is established, which greatly enhances the data processing depth and intelligent analysis capabilities of the present invention in the optimization of multimodal transport service networks.

[0032] S104. Based on the velocity benchmarking matrix, a multi-scale wavelet phase difference analysis method is applied to analyze the phase difference and mismatch amplitude of the transmission velocity vector and the displacement velocity vector in multiple time windows, thereby obtaining the phase shift spectrum and mismatch amplitude of the information flow and logistics physical flow velocity vectors, and forming a synchronization deviation feature set covering multiple time scales; The specific implementation is as follows: First, based on the information flow transmission velocity vectors and logistics physical flow displacement velocity vectors recorded in the velocity benchmarking matrix, multiple time windows are set for segmented data sampling. These multiple time windows are designed based on the characteristics of the actual logistics flow cycle and information flow refresh cycle, covering multiple scales from seconds, minutes, hours, to days, ensuring that they can capture short-term changes, periodic fluctuations, and synchronization deviations under long-term trends. Within each time window, the corresponding velocity vector sequence is extracted to form the time series pair to be analyzed, providing raw data support for subsequent wavelet transforms and phase difference calculations.

[0033] The continuous wavelet transform (CWT) method is applied to the velocity vector sequence within each time window, projecting the transmission velocity vector of the information flow and the displacement velocity vector of the physical flow of logistics into the time-frequency domain. By selecting wavelet basis functions with good time-frequency localization properties, the velocity vector sequence is decomposed at multiple scales to obtain amplitude and phase information at different frequency components. This step not only distinguishes the different frequency characteristics of velocity changes but also reveals the phase distribution characteristics at various time scales. Through wavelet transform processing, the phase spectra of the information flow and logistics flow are obtained, laying the foundation for the subsequent accurate calculation of the phase difference.

[0034] After completing the wavelet transform and obtaining the phase information of each vector, the phase difference between the information flow transmission velocity vector and the logistics physical flow displacement velocity vector is calculated based on the correspondence between the same time scale and frequency components. Specifically, for each frequency level and time segment, the phase offset of the two vectors is calculated point by point to form a complete phase difference sequence. At the same time, based on the amplitude difference and phase difference dynamics of the two vectors, the mismatch amplitude is further calculated, that is, the degree of amplitude deviation in the speed change trend between the information flow and the logistics flow under the same time scale and frequency conditions. Through the joint calculation of phase difference and mismatch amplitude, the phase offset spectrum and mismatch amplitude spectrum of the information flow and the logistics flow are constructed to comprehensively characterize the synchronization and synergy between the two at different time scales.

[0035] Based on the phase offset spectra and mismatch amplitude spectra obtained in multiple time windows and frequency levels, a synchronization deviation feature set covering multiple time scales is constructed. This feature set includes multi-dimensional indicators such as average phase difference, phase difference variance, maximum mismatch amplitude, minimum mismatch amplitude, and amplitude fluctuation rate at different time scales. It is used to quantitatively describe the synchronization deviation and inconsistency characteristics of information flow and logistics flow at various time scales. To improve the practicality and generalization capabilities of the feature set, feature normalization and time series identification methods are further adopted to unify the scale and serialize the feature data, ensuring direct application in subsequent synchronization imbalance index calculation, dynamic scheduling optimization, and anomaly detection analysis.

[0036] Through the coordinated processing of the above steps, not only is an in-depth analysis of information flow and logistics physical flow in multiple time scales and frequency domains achieved, but it also provides solid feature support and quantitative basis for a comprehensive and accurate grasp of their synchronization and dynamic imbalance status.

[0037] S105. Based on the synchronization deviation feature set, an adaptive entropy weight assignment mechanism is used to dynamically weight the synchronization deviation features at different time scales. Based on the weighted processing results, a real-time imbalance index is calculated. The real-time imbalance index is used to quantify the degree of synchronization imbalance between information flow and physical flow of logistics. The specific implementation is as follows: For the acquired synchronization deviation feature set covering multiple time scales, an initial entropy weight model for feature weight assessment is established. This model first statistically analyzes the distribution characteristics of each feature in the synchronization deviation feature set across the entire sample sequence, extracting statistics such as the standard deviation, mean, and range for each feature. Based on the principle of information entropy, the entropy value of each feature is calculated. Lower entropy values ​​indicate greater variability across the entire sample, indicating a higher contribution to distinguishing different synchronization deviation states, and vice versa. Through this statistical process, a preliminary set of entropy weights reflecting the amount of feature information and variability are formed, providing a basic weight allocation framework for subsequent dynamic weighting.

[0038] On the basis of the entropy weight model, an adaptive adjustment mechanism is introduced to dynamically correct the feature weights. Specifically, the sensitivity and contribution of each synchronization deviation feature are evaluated in combination with the real-time feature performance under the current time series. During this evaluation process, the sliding time window method is used to dynamically calculate the coefficient of variation and fluctuation amplitude of each feature in the latest period of time. If a feature shows greater volatility and trend in the current window, its weight is increased, otherwise its weight is reduced. In addition, considering the degree of influence of different time scales on the global synchronization deviation, the time scale weight adjustment factor is introduced to realize the weight redistribution of short-cycle, medium-cycle and long-cycle features. This adaptive weight adjustment mechanism ensures the real-time and sensitivity of weight distribution, and can adjust the importance of features as the logistics scenario changes dynamically.

[0039] Based on the dynamically weighted feature weights, all features in the synchronization deviation feature set are weighted and summed to form a comprehensive indicator sequence, namely the weighted comprehensive deviation sequence. Specifically, the normalized values ​​of each time scale and each feature are multiplied by their corresponding dynamic weights, and all product results are summed up according to the time scale to which the features belong to form a dynamic weighted indicator reflecting the global synchronization state. This step ensures that the contribution of different features to the global synchronization deviation is fully reflected, and the weight distribution fully reflects the dynamic force of each feature in the current tense. Through this comprehensive method of weighted summation, the multi-dimensional and multi-time scale feature set is converted into a single, quantifiable indicator expression, which facilitates further numerical analysis and application.

[0040] After obtaining the weighted comprehensive deviation sequence, a real-time imbalance index is calculated as a core indicator to quantify the degree of synchronization imbalance between information flow and physical logistics. The real-time imbalance index is calculated by combining statistical normalization with dynamic baseline comparison methods. The latest value in the weighted comprehensive deviation sequence is compared with the historical baseline range to determine its position within the normal fluctuation range. When the real-time imbalance index deviates from the fluctuation range set by the historical mean and variance, the real-time imbalance index is adjusted upward, reflecting an increase in synchronization imbalance; conversely, the real-time imbalance index decreases, indicating a restoration of synchronization. To enhance the sensitivity and robustness of the real-time imbalance index, exponential smoothing and trend correction factors are further introduced into the calculation of the real-time imbalance index to avoid misjudgments caused by short-term extreme fluctuations. The final output of the real-time imbalance index not only provides a quantitative description of the current synchronization deviation but also can trigger early warnings for synchronization imbalances by setting thresholds, guiding the dynamic optimization and risk intervention of logistics scheduling.

[0041] Through the orderly execution of the above steps, a synchronization deviation weight assessment and index quantification mechanism is formed, which fully supports the precise monitoring and intelligent adjustment of the synchronization of information flow and logistics physical flow in the multimodal transport service network.

[0042] S106: An incremental residual matching mechanism driven by a real-time imbalance index for the digital twin. The digital twin is used to continuously track the residual dynamics between the physical flow trajectory of logistics and information flow data. Based on the residual dynamics, high-frequency hypothetical state update frames are generated. These hypothetical state update frames are used to fill in gaps in system perception in scenarios where information flow lags or breakpoints occur, thereby maintaining the continuity and accuracy of scheduling decisions in the multimodal transport service network. The specific implementation is as follows: First, based on the dynamic changes in the real-time imbalance index, the digital twin's incremental residual tracking start conditions and tracking frequency are determined. When the real-time imbalance index reaches the set dynamic threshold, indicating that the synchronization between the information flow and the physical flow of logistics has shown an imbalance trend, the digital twin immediately initiates the incremental residual tracking process. This process constructs a virtual simulation path corresponding to the physical logistics flow path in the digital twin, and dynamically calculates the residual increment at each time node based on the numerical residual between the latest physical logistics flow trajectory and the historical information flow data. At this time, the physical logistics flow trajectory uses its multi-dimensional dynamic attributes such as displacement, velocity, and acceleration as the basic reference, while the information flow data is compared based on attributes such as timestamp, update frequency, and data integrity. The residual between the two is output in real time as a continuous numerical sequence, providing basic data support for the subsequent generation of hypothetical states.

[0043] Based on the continuous tracking of incremental residuals, a feature extraction and pattern recognition model based on residual dynamics is established. By applying algorithms such as trend extraction, fluctuation analysis, and mutation detection to the residual incremental sequence, key characteristic parameters of residual dynamics, including residual accumulation, residual volatility, and residual mutation points, are identified. This allows the determination of hysteresis patterns, breakpoint patterns, or abnormal drift patterns in the information flow. The results of this feature extraction and pattern recognition are used to guide the generation strategy of hypothetical state update frames. This ensures that the generated hypothetical state update frames are not simply an extension of existing data, but rather intelligently predict the possible states and trends of information flows based on the dynamic reality of physical logistics and the residual characteristics.

[0044] Based on the pattern recognition results of the residual dynamics, high-frequency hypothetical state update frames are generated in real time. The hypothetical state update frame is a dynamic fitting and intelligent completion of the information flow in the case of lag or breakpoint scenarios. The specific method is as follows: In the digital twin, based on the actual trajectory of the current physical flow of logistics and the dynamic characteristics of the residuals, combined with the residual evolution law of similar historical scenarios, time series prediction and state space modeling methods are used to predict the expected state of the information flow in the next time slice and several future time slices, and generate a virtual data frame with high temporal resolution. This high-frequency hypothetical state update frame not only covers the estimated timestamp, information flow refresh frequency, data integrity and other attributes, but also annotates the corresponding confidence level and error range to ensure availability and risk controllability in actual applications.

[0045] Based on the high-frequency generated hypothetical state update frames, the scheduling decision logic of the intermodal transport service network is dynamically supplemented and corrected. By integrating the hypothetical state update frames with real-time physical logistics flow trajectories and existing information flow data, a global perception view is constructed, eliminating perception blind spots caused by information flow lags or breakpoints. This ensures that the scheduling system can maintain accurate understanding of the intermodal transport process and make scientific decisions even when perception data is incomplete. At the same time, the digital twin continuously compares and corrects the generated hypothetical state update frames with real data based on subsequent supplementation and restoration of actual information flows, dynamically revising the prediction model and improving the accuracy and adaptability of subsequent hypothetical state generation.

[0046] Through the coordinated operation of the above steps, not only the perception fault and lag problems between intermodal transport information flow and physical logistics flow are effectively solved, but also the scheduling continuity, decision-making accuracy and dynamic recovery ability of the intermodal transport network are enhanced, and the innovative and practical value of digital twins and incremental residual matching in the field of smart logistics are fully exerted.

[0047] By constructing a unified nanosecond-level global synchronized clock benchmark and combining it with a blockchain-based multi-party verifiable timestamp mechanism, this invention achieves high-precision time synchronization and deep cross-modal calibration of information flows and physical logistics flows under various transport modes, comprehensively improving the temporal consistency and data credibility of the entire multimodal transport process. By combining a velocity benchmarking matrix with multi-scale wavelet phase difference analysis, it accurately characterizes the synchronization deviation characteristics of information flows and physical logistics flows at different time scales, dynamically assessing and quantifying the degree of synchronization imbalance. Furthermore, relying on a real-time imbalance index and a digital twin incremental residual matching mechanism, it continuously tracks and dynamically fills in perception gaps in information flows. Especially in scenarios with information flow lags or breakpoints, it generates high-frequency hypothetical state update frames to maintain the continuity and accuracy of scheduling decisions. Overall, this invention significantly improves the full-link visualization and intelligent scheduling capabilities of the multimodal transport service network, enhances the stability, resilience, and security of the logistics network in complex and changing environments, effectively reduces the error rate of logistics operations and transportation safety risks, and is particularly suitable for the high-reliability transportation of high-value or sensitive materials.

[0048] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. A method for optimizing a multimodal transport service network, characterized in that: The following steps are involved: S101. Build a unified nanosecond-level global synchronous clock benchmark to synchronize the time of hub nodes under various transportation modes. Based on this clock benchmark, collect first frequency data and second frequency data in real time. The first frequency data is the information flow refresh frequency, and the second frequency data is the logistics physical flow displacement frequency. S102. Based on the clock reference and in combination with the blockchain multi-party verifiable timestamp mechanism, perform time domain deep calibration on the first frequency data and the second frequency data, and dynamically generate a timing consistency matrix; S103. Based on the time consistency matrix, extract the transmission speed vector of the information flow and the displacement speed vector of the physical flow of the logistics, and construct a speed benchmarking matrix with a unified scale; S104. Based on the velocity alignment matrix, apply multi-scale wavelet phase difference analysis to analyze the phase difference and mismatch amplitude between the transfer velocity vector and the displacement velocity vector, and form a multi-time-scale synchronization deviation feature set; S105. Based on the synchronization deviation feature set, an adaptive entropy weight assignment mechanism is used to dynamically weight the synchronization deviation features, calculate the real-time imbalance index, and quantify the degree of synchronization imbalance between information flow and physical flow of logistics; S106. Based on the real-time imbalance index, drive the incremental residual matching of the digital twin, continuously track the residual dynamics of the physical flow trajectory of logistics and the information flow data, generate high-frequency hypothetical state update frames, and fill in the perception gaps when the information flow lags or breaks.

2. The method for optimizing a multimodal transport service network according to claim 1, wherein: S101 includes: Establish a unified nanosecond-level global synchronized clock benchmark at each hub node under various transportation modes. By configuring high-precision atomic clocks or global navigation satellite system timing devices and combining them with wide-area clock synchronization protocols, synchronize time signals to all hub nodes and deploy time synchronization devices to maintain a nanosecond-level error range. Collect first-frequency data and second-frequency data in real time, and configure a high-precision timestamp marking mechanism based on a synchronous clock reference to stamp each collected data with a nanosecond-level timestamp and synchronize verification; The collected first-frequency data and second-frequency data are checked for consistency and cleaned to remove abnormal points. The data sequence is optimized through interpolation repair and time series smoothing to establish a time series index based on unified time calibration.

3. The method for optimizing a multimodal transport service network according to claim 1, wherein: S102 includes: Based on a unified nanosecond-level global synchronous clock benchmark, the first-frequency data and the second-frequency data are preliminarily time-aligned to correct time errors under different transport modes. Combined with the blockchain's multi-party verifiable timestamp mechanism, the preliminarily aligned data timestamps are written into the blockchain ledger, and the timestamps are stored and verified through distributed consensus. Based on the blockchain verification results, a time domain deep calibration algorithm is used to dynamically calculate the time drift and delay compensation value, and dynamic time warping and time series interpolation technology are used to achieve time alignment of data; Based on the deeply calibrated data, a time consistency matrix is ​​dynamically generated to record the time stamps and data status of information flow and physical flow of logistics.

4. The method for optimizing a multimodal transport service network according to claim 3, wherein: S103 includes: Based on the time consistency matrix, the transmission speed vector of information flow and the displacement speed vector of logistics physical flow are extracted. The information flow rate is calculated by frequency increment and time difference, and the logistics speed is calculated by displacement distance and time interval. Normalize the extracted transmission velocity vector and displacement velocity vector, unify the numerical scale, and set the weight coefficient according to application requirements; A speed benchmarking matrix with a unified scale is constructed based on the normalized speed vector. The matrix elements record the correspondence between the information flow and the logistics flow speed, and introduce speed difference and change trend indicators. The speed calibration matrix is ​​smoothed and completed using interpolation or sliding average to complete timing calibration and index optimization.

5. The method for optimizing a multimodal transport service network according to claim 1, wherein: S104 includes: According to the speed benchmarking matrix, multiple time windows are set to sample the information flow transmission speed vector and the logistics physical flow displacement speed vector in sections to form a time series pair; Apply continuous wavelet transform to the velocity vector sequence in each time window, perform multi-scale decomposition using wavelet basis functions, extract amplitude and phase information at different frequencies, and obtain the phase spectrum of each vector; Based on the wavelet transform results, the phase difference and mismatch amplitude of the two vectors at the same time scale and frequency are calculated to form the phase shift spectrum and mismatch amplitude spectrum; Based on the phase offset spectrum and the mismatch amplitude spectrum, a synchronization deviation feature set is constructed, and scale unification and sequence encoding are achieved through feature normalization and time series identification.

6. The method for optimizing a multimodal transport service network according to claim 1, wherein: S105 includes: Based on the synchronization deviation feature set, an initial entropy weight model for feature weight evaluation is established. The entropy value of each feature is calculated through information entropy to form the initial weight distribution. Based on the entropy weight model, the sliding time window is combined to dynamically evaluate the volatility and trend of the features in the current time series, an adaptive adjustment mechanism is used to dynamically correct the feature weights, and a time scale weight adjustment factor is introduced; Based on the dynamic weighted feature weights, the synchronization deviation feature set is weighted and summed to form a weighted comprehensive deviation sequence to quantify the global synchronization deviation; Based on the weighted comprehensive deviation sequence, combined with statistical normalization and dynamic baseline comparison, the real-time imbalance index is calculated, and the sensitivity and robustness of the real-time imbalance index are enhanced through exponential smoothing and trend correction factors.

7. The method for optimizing a multimodal transport service network according to claim 6, wherein: S106 includes: Based on the dynamic changes of the real-time imbalance index, the incremental residual tracking start conditions and frequency of the digital twin are determined, and the incremental residual between the physical flow trajectory of logistics and the information flow data is dynamically calculated; Extract residual dynamic features based on continuous tracking of incremental residuals to identify hysteresis patterns, breakpoint patterns or abnormal drift patterns; Based on the dynamic characteristics of the residual, time series prediction and state space modeling are used to generate high-frequency hypothetical state update frames, predict the expected state of the information flow and mark the confidence level and error range; Based on the hypothetical state update frame, the scheduling decision logic is dynamically completed, the logistics trajectory and information flow data are integrated, the perception blind spots are eliminated, and the accuracy and adaptability of the prediction model are optimized through continuous comparison and correction.

Images