Intelligent Logistics Matching Method Empowered by Dynamic Data

Abstract

The present invention discloses an intelligent logistics matching method empowered by dynamic data, specifically relating to the technical field of logistics matching. First, real-time operation data of the logistics matching system is obtained, and an initial state feature vector is constructed through standardization processing. Secondly, a target order delivery group with stable operation and reasonable matching is screened out. Subsequently, by calculating the state feature similarity of the current order, the optimal order delivery group is matched. For abnormal matching situations, an abnormal pattern recognition method is adopted to extract abnormal features of the transport capacity distribution and abnormal features of the temporal variation of the matching pattern, calculate the abnormal matching degree, and generate a matching adjustment instruction based on the calculation result to dynamically optimize the matching weight. The present invention effectively avoids the problem of deviation accumulation caused by self-reinforcement of the matching algorithm, reduces the phenomenon of algorithmic islands, improves the adaptive ability of the logistics matching system, makes the allocation of logistics resources more efficient and fair, and improves the operation efficiency of the overall logistics network.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics matching, and specifically relates to an intelligent logistics matching method empowered by dynamic data. Background Art

[0002] With the rapid development of e-commerce, instant delivery, and supply chain management, the intelligent demand for logistics matching is increasing day by day. Traditional logistics matching methods mainly rely on static data, such as fixed transportation routes, preset warehouse resource allocation rules, and historical order data. However, this method cannot fully cope with the dynamic changes in the logistics environment, such as sudden traffic jams, real-time order demand fluctuations, and weather condition impacts. Therefore, the intelligent logistics matching method empowered by dynamic data has gradually become the focus of research and application. This method realizes precise and efficient logistics matching by collecting dynamic data such as traffic flow, vehicle positions, and order status in real time, and combining artificial intelligence, optimization algorithms, and big data analysis technologies, thereby improving transportation efficiency, reducing costs, and enhancing the user experience.

[0003] The existing technologies have the following deficiencies:

[0004] In an intelligent logistics matching system based on dynamic data, the algorithm continuously adjusts scheduling decisions to adapt to the real-time changing environment. However, if the system overly relies on the data generated by itself rather than the external real environment data, it may lead to the problem of distortion in the dynamic data feedback loop. Specifically, the logistics matching algorithm may deviate due to continuous automatic adjustments in a short period. For example, due to uneven early scheduling decisions, orders in certain areas may be misjudged as low-demand areas, resulting in a reduction in the transportation capacity allocation in these areas and further exacerbating the supply-demand imbalance. This cumulative error may be amplified after long-term operation, leading to long-term low logistics efficiency in some areas and even the phenomenon of algorithmic islands, that is, the order matching in some areas is long-term ignored or processed with low priority, affecting the fairness and stability of the overall logistics network. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent logistics matching method empowered by dynamic data to solve the deficiencies in the background art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: An intelligent logistics matching method empowered by dynamic data, including:

[0007] Obtain the real-time operation data of the logistics matching system and perform standardization processing on it to form an initial state feature vector;

[0008] Based on long-term monitoring data, screen out the target order delivery groups with stable logistics network operation and reasonable matching results;

[0009] Calculate the similarity between the initial state feature vector and the state features of the target order delivery group, determine the optimally matched order delivery group, and generate an optimal logistics matching plan;

[0010] If the similarity is lower than the preset similarity threshold, it is determined that the logistics matching is abnormal, and different types of abnormal matching patterns are identified, and the abnormal features under each abnormal matching pattern are extracted;

[0011] Combine the abnormal features of the logistics capacity distribution and the abnormal features of the temporal variation of the matching pattern, calculate the abnormal matching degree, and generate corresponding matching adjustment instructions according to the calculation results to dynamically adjust the matching weights.

[0012] Preferably, the screening of the target order delivery group further uses the K-means clustering algorithm to classify the historical order data to determine the target group with the most stable matching and the highest delivery success rate: set the number of clusters k, initialize the cluster centers, and calculate the Euclidean distance from each order group to the cluster centers: iteratively update the cluster centers until convergence, and select the order group with the smallest standard deviation and the highest matching success rate as the target delivery group.

[0013] Preferably, the cosine similarity calculation method is used to calculate the similarity between the initial state feature vector and the target order delivery group. If the cosine similarity is lower than the set threshold, it is determined that the matching is abnormal, and the abnormal matching pattern is identified, and the abnormal features of the logistics capacity distribution and the temporal variation of the matching pattern are extracted for abnormal pattern analysis and adjustment.

[0014] Preferably, after analyzing the abnormal change of the regional capacity supply-demand ratio extracted, calculate the abnormal index of the capacity supply-demand ratio. The calculation method of the abnormal index of the capacity supply-demand ratio is as follows:

[0015] Within each time window t, collect the available capacity number of the target area A , which represents the current number of schedulable vehicles / riders within area A, and the number of orders to be matched , which represents the total number of orders to be matched within area A currently;

[0016] Within each time window t, calculate the regional capacity supply-demand ratio: ; calculate the change rate of the capacity supply-demand ratio within the time window , and the expression is: ; calculate the historical capacity supply-demand ratio mean and standard deviation of area A within the past N time windows, define the abnormal index of the capacity supply-demand ratio, and the expression is: ; where: is the abnormal index of the capacity supply-demand ratio, is a very small positive number to prevent the denominator from being 0, is the historical capacity supply-demand ratio mean, is the standard deviation of the historical supply-demand ratio of transportation capacity.

[0017] Preferably, after analyzing the abnormal situation of the matching pattern conversion frequency, a matching pattern conversion frequency deviation index is generated. The method for obtaining the matching pattern conversion frequency deviation index is as follows:

[0018] Record the number of matching pattern conversions within the past N time windows to form a time series, and train an ARIMA model to enable it to predict the normal trend of the matching pattern conversion frequency; calculate the actual matching pattern conversion frequency and the ARIMA predicted value of the difference , the expression is: ; after calculating the mean square error MSE of the difference, calculate the matching pattern conversion frequency deviation index, and the expression is: ; where c is a very small number, is the matching pattern conversion frequency deviation index.

[0019] Preferably, the transportation capacity supply-demand ratio abnormal index and the matching pattern conversion frequency deviation index are normalized so that they are both within [0,1], and the abnormal matching degree is calculated according to the normalized transportation capacity supply-demand ratio abnormal index and the matching pattern conversion frequency deviation index.

[0020] Preferably, compare the obtained abnormal matching degree with a pre-set threshold. If the abnormal matching degree is greater than or equal to the pre-set threshold, it indicates that there is an abnormality in the current matching strategy. At this time, a matching adjustment instruction is generated, including adjusting the matching weight, dynamically optimizing the transportation capacity allocation, and optimizing the matching algorithm; if the abnormal matching degree is less than the pre-set threshold, it indicates that the current matching strategy is still within the normal range, and there is no need to adjust the matching plan, and the current matching rule is maintained.

[0021] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0022] 1. The present invention constructs a standardized initial state feature vector, combines long-term monitoring data, screens out the target order delivery group with stable matching and high delivery success rate, and realizes accurate logistics matching. Through cosine similarity calculation, the current order is dynamically matched with the optimal order delivery group, and when the matching is abnormal, the transportation capacity supply-demand ratio abnormal index and the matching pattern conversion frequency deviation index are used for intelligent analysis to identify the imbalance of logistics transportation capacity distribution and abnormal fluctuations in the matching pattern, thereby optimizing the matching strategy. The present invention uses machine learning methods such as K-means clustering and ARIMA time series analysis to improve the stability of matching, avoid the accumulation of deviations caused by data feedback loop distortion, reduce the algorithm island phenomenon, and improve the fairness and overall operation efficiency of the logistics system.

[0023] 2. The present invention can monitor the status of the logistics network in real time, dynamically identify and optimize abnormal matching situations, and ensure that the matching strategy conforms to the actual supply and demand relationship. By normalizing the abnormal index and setting a threshold based on the abnormal matching degree, the automatic adjustment and optimization of the matching strategy are realized, thereby improving the flexibility and adaptability of logistics scheduling. The present invention can optimize the allocation of logistics resources in a dynamic and complex environment, reduce the empty load rate, improve the distribution efficiency, reduce costs, and ensure the long-term stable operation of the system, providing more accurate and reliable technical support for intelligent logistics matching. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0025] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0027] For the embodiments, please refer to Figure 1 As shown, the intelligent logistics matching method based on dynamic data empowerment in this embodiment includes:

[0028] Obtain the real-time operation data of the logistics matching system and perform standardization processing on it to form an initial state feature vector;

[0029] Based on the long-term monitoring data, screen out the target order delivery groups with stable logistics network operation and reasonable matching results;

[0030] Calculate the state feature similarity between the initial state feature vector and the target order delivery group, determine the order delivery group with the optimal matching, and generate an optimal logistics matching plan;

[0031] If the similarity is lower than the preset similarity threshold, it is determined that the logistics matching is abnormal, and different types of abnormal matching modes are identified, and the abnormal features under each abnormal matching mode are extracted;

[0032] Calculate the anomaly matching degree by combining the abnormal characteristics of logistics transport capacity distribution and the abnormal characteristics of the temporal variation of the matching mode, and generate corresponding matching adjustment instructions according to the calculation results to dynamically adjust the matching weights.

[0033] Obtain the real-time operation data of the logistics network from various data sources of the logistics matching system (including the order management system, the vehicle networking system, the map API, the weather forecast service, etc.). The collected data mainly includes the following categories:

[0034] (1) Order information data: order number, order placement time, order source; order type (same-city distribution, long-distance transportation, express delivery, etc.); cargo attributes (weight, volume, special storage requirements); pick-up location, delivery location, expected delivery time;

[0035] (2) Transport capacity status data: real-time location of the transport vehicle, available load capacity; delivery route of the vehicle, historical driving track; driver information (experience level, driving habits, etc.); empty load rate, current delivery task status;

[0036] (3) Traffic condition data (obtained through the map API): real-time road traffic conditions (smooth, congested, road closed, etc.); traffic flow density of the main logistics arteries; influencing factors such as accident reports, construction areas, etc.;

[0037] (4) Environmental factor data: weather conditions (temperature, rainfall, wind speed, etc.); emergencies (natural disasters, road closure announcements, etc.); The data collection frequency needs to be set according to the real-time requirements of the logistics system. For example, high-frequency deliveries (such as takeaways, same-city express deliveries) may need to be updated every minute, while long-distance transportation may be updated on an hourly basis.

[0038] The collected data often has redundancy, errors, and missing values, and needs to be preprocessed to improve data quality. Remove duplicate order information through fields such as order number and timestamp. Optimize the GPS location data trajectory and remove offset values. Use the Z-score method or the box plot method to detect and remove outliers. For example, the vehicle speed far exceeds the speed limit or is negative (abnormal GPS data); unify the format, for example, convert the timestamp to the standard format (ISO 8601). Adopt mean imputation: For example, if the traffic flow data in a certain area is lost in a short period of time, it can be filled with the average value of adjacent periods.

[0039] Different types of data may have different value ranges. For example, the order quantity may be from hundreds to thousands, while the traffic congestion index is between 0 and 1. To avoid the impact of numerical scale differences on the matching algorithm, normalization processing is required. The normalized data needs to further extract key features to construct the feature vectors required for the intelligent matching algorithm.

[0040] Convert the extracted various features into vector form according to a certain format. For example: ; where: represents order features (such as order volume, delivery urgency); represents transportation capacity features (such as load factor, route optimization degree); represents environmental features (such as weather impact, traffic index).

[0041] The final feature vector will be stored in the dynamic data cache of the matching system as the input of the intelligent matching algorithm. This vector will be continuously updated in subsequent matching optimization steps to ensure that the matching results can adapt to the real-time changing logistics environment.

[0042] Extract long-term monitoring information from the historical data of the logistics matching system, mainly including: Order matching records: order quantity, delivery time, delivery success rate, historical matching strategies, etc. Transportation capacity allocation: vehicle utilization rate, empty load rate, overloading rate, delivery task completion situation, etc. Delivery network stability: delivery time fluctuation, order concentration, order distribution in the delivery area, etc. Organize the data in time series format to ensure that sufficient historical records are included (such as data for the past 3 months, 6 months, 1 year).

[0043] In order to screen out the order delivery groups with stable operation, the following key stability indicators need to be calculated:

[0044] Calculate the proportion of deliveries that can be completed on time after historical order matching , the expression is: ; if > 90% (the threshold can be adjusted), it indicates that the matching is reasonable and proceeds to the next screening.

[0045] Calculate the deviation between the actual delivery time and the estimated delivery time of the matched orders , measured by the standard deviation, the expression is: ; set a threshold (such as < 15 minutes), if satisfied, it is considered that the matching is stable.

[0046] Calculate the order distribution in different regions , if the order quantity is long-term concentrated in a specific region (such as a city or a specific business district), it indicates that the matching regularity is strong, and the Gini coefficient can be used to measure the order distribution: ; where, represents the order proportion in different regions. If G < 0.4, it indicates that the order distribution is relatively balanced and the matching is reasonable.

[0047] In order to further screen out the order groups with stable matching, the K-means clustering algorithm or the DBSCAN density clustering algorithm can be used for data classification.

[0048] Construct the following feature vectors: ; where: is the matching success rate, is the volatility of delivery time, G is the order density (distribution of delivery hotspots), is the average delivery distance, is the capacity load rate (ratio of empty load to full load), is the average traffic congestion index. Use the K-means algorithm to classify the order delivery groups and determine the stable matching groups: Set the number of clusters k (such as 3 - 5), initialize the cluster centers, calculate the Euclidean distance from each order group to the cluster centers: Iteratively update the cluster centers until convergence. Select the order group with the smallest standard deviation and the highest matching success rate as the target delivery group.

[0049] During the intelligent logistics matching process, it is necessary to calculate the status feature vector of the current order based on dynamic data and perform similarity matching with the target order delivery group to determine the optimal matching plan.

[0050] Initial state feature vector ; where: represents order features (such as order volume, delivery urgency); represents capacity features (such as load rate, route optimization degree); represents environmental features (such as weather impact, traffic index). This vector is processed by data standardization (such as Min - Max normalization) to make the feature values within the same scale.

[0051] The feature vector library S of the target order delivery group stores multiple historical stable matching group feature vectors: ; where each represents the feature vector of an order delivery group with a relatively high historical matching success rate.

[0052] Calculate the cosine similarity between the current order vector V and each target group vector S , and the expression is: ; is between [-1, 1]. The closer the value is to 1, the more similar the features of the current order and the target group are.

[0053] Select the one with the highest similarity as the target order delivery group. After determining the optimal matching order group, generate the final logistics matching plan, which specifically includes: Based on the historical data of the target order delivery group, select the most matching transportation resources: Ensure a reasonable capacity load rate to avoid overloading or empty loading. Prioritize the selection of transportation plans with relatively stable historical delivery timeliness. If the target group involves multiple delivery areas, use clustering scheduling optimization to divide the orders into reasonable transportation batches.

[0054] Based on the historical trajectory data of the target delivery group and combined with real-time traffic information, the A* search algorithm or Dijkstra algorithm is used to optimize the delivery route: If the current road is congested, select the alternative route used by similar orders in history. Combine the order timeliness requirements and dynamically adjust the delivery sequence.

[0055] For special situations, the system dynamically adjusts the matching scheme: If the similarity of the matching group is insufficient, human-machine collaborative intervention is allowed to manually adjust the matching weight. Combine historical trend analysis, adjust the matching parameters, and improve the matching accuracy. Dynamically adjust the capacity allocation during peak periods to ensure the optimal matching result.

[0056] When the calculated similarity is lower than the preset similarity threshold (e.g., 0.8), it indicates that there may be an abnormality in the matching scheme of the current order. It is necessary to further identify the abnormal matching pattern and extract the key abnormal features under different abnormal patterns. The abnormal matching patterns can be divided into abnormal distribution of logistics capacity and abnormal temporal changes in the matching pattern.

[0057] The abnormal matching patterns are mainly automatically identified through methods such as cluster analysis, statistical analysis, and machine learning. The specific steps are as follows:

[0058] K-means clustering to identify abnormal patterns: Use the historical matching data as the training set and classify the matching patterns using the K-means clustering algorithm. Set the central cluster of the normal matching pattern. If the matching scheme of the current order deviates far from the central cluster, it is determined as abnormal. Calculate the Euclidean distance between the matching scheme of the current order and each matching pattern. If it exceeds the standard deviation range of the normal pattern, it is classified as an abnormal matching.

[0059] Abnormal detection based on statistical thresholds: Calculate the matching success rate: If it is lower than the historical average level (e.g., 90%), it is determined as abnormal. Calculate the average deviation of the delivery time: If it exceeds 3 times the standard deviation, it belongs to the abnormal matching pattern. Statistically analyze the growth rate of the number of failed matching orders. If the number of failed matching orders surges within a short period, it indicates that there is a problem with the system's matching logic.

[0060] Abnormal detection based on machine learning (LOF method): Adopt the local outlier factor algorithm to calculate the local outlier factor score of the current matching scheme in the historical data. If the LOF score is high (much higher than that of normal orders), it indicates that the matching pattern is abnormal.

[0061] When the supply and demand of logistics capacity do not match, it may lead to a decline in delivery efficiency. Extract the key abnormal feature: regional capacity supply-demand ratio , the expression is: ; If the regional capacity supply-demand ratio is much lower than the historical average, it indicates a shortage of capacity in that region.

[0062] After analyzing the abnormal changes in the supply-demand ratio of regional transportation capacity, calculate the abnormal index of the supply-demand ratio of transportation capacity. The calculation method of the abnormal index of the supply-demand ratio of transportation capacity is as follows:

[0063] Within each time window (such as 10 minutes, 30 minutes, 1 hour), collect the following data for the target area A:

[0064] Available transportation capacity , indicating the number of currently dispatchable vehicles / riders within area A. Number of orders to be matched , indicating the total number of orders to be matched within area A.

[0065] Within each time window t, calculate the regional transportation capacity supply-demand ratio: ; If > 1, it indicates that the transportation capacity is sufficient and there may be idle transportation capacity. If < 1, it indicates that the transportation capacity is insufficient and may lead to delays in order delivery.

[0066] Calculate the change rate of the transportation capacity supply-demand ratio within the time window , and the expression is: ; If fluctuates too much, it indicates that the regional supply-demand changes are drastic and there may be abnormalities in the matching system.

[0067] Calculate the mean and standard deviation of the historical transportation capacity supply-demand ratio of area A within the past N time windows, and define the abnormal index of the transportation capacity supply-demand ratio to measure the abnormal degree of the current supply-demand ratio. The expression is: ; Among them: is the abnormal index of the transportation capacity supply-demand ratio. The larger the value, the more serious the degree of supply-demand imbalance. is a very small positive number (such as 0.0001) to prevent the denominator from being 0. is the mean of the historical transportation capacity supply-demand ratio. is the standard deviation of the historical transportation capacity supply-demand ratio, measuring the normal fluctuation range of supply-demand changes.

[0068] If < 1, the change in the supply-demand ratio is within the normal range and no adjustment is required. If ) < 2, the supply-demand ratio shows a medium abnormality, and the transportation capacity scheduling can be adjusted appropriately. If ≥ 2, the supply-demand ratio is severely abnormal, and the matching strategy needs to be adjusted immediately (such as increasing transportation capacity, optimizing matching rules).

[0069] The matching logic of the logistics matching system should be relatively stable. If the matching mode fluctuates abnormally in a short period of time, it indicates that there may be problems with the matching strategy. Extract the key abnormal features: matching mode conversion frequency , and the expression is: If the matching pattern switches frequently within a short period (e.g., 10 times in 5 minutes), it indicates that there is a problem with the instability of the system strategy.

[0070] After analyzing the abnormal situation of the obtained matching pattern conversion frequency, a matching pattern conversion frequency deviation index is generated. The method for obtaining the matching pattern conversion frequency deviation index is as follows:

[0071] Record the number of matching pattern conversions within the past N time windows (such as 5 minutes, 10 minutes, 30 minutes) to form a time series, and select appropriate parameters (p, d, q), where: p is the autoregressive term, indicating how many past values the current value is related to. d is the order of differencing to ensure the stationarity of the time series. q is the moving average term, indicating the impact of the error on the current value. Train the ARIMA model so that it can predict the normal trend of the matching pattern conversion frequency.

[0072] Calculate the actual matching pattern conversion frequency and the ARIMA predicted value The difference , and the expression is: ; After calculating the mean square error MSE of the difference, calculate the matching pattern conversion frequency deviation index, and the expression is: ; Where, c is an extremely small number (such as 0.0001) to prevent the denominator from being 0, is the matching pattern conversion frequency deviation index; if ≥2, it indicates that the matching pattern conversion frequency has a serious abnormality and may require re-optimizing the matching strategy.

[0073] Normalize the transport capacity supply-demand ratio anomaly index and the matching pattern conversion frequency deviation index so that they are both within [0, 1], and calculate the abnormal matching degree according to the normalized transport capacity supply-demand ratio anomaly index and the matching pattern conversion frequency deviation index.

[0074] For example, the present invention can calculate the abnormal matching degree using the following formula, and the calculation expression is: ; In the formula, is the abnormal matching degree, is the transport capacity supply-demand ratio anomaly index, is the matching pattern conversion frequency deviation index, are the weight coefficients of the transport capacity supply-demand ratio anomaly index and the matching pattern conversion frequency deviation index (which can be optimized according to experimental experience or machine learning), and are all greater than 0.

[0075] Compare the obtained anomaly matching degree with a preset threshold. If the anomaly matching degree is greater than or equal to the preset threshold, it indicates that there is an anomaly in the current matching strategy, which may be caused by uneven transport capacity allocation or unstable matching patterns. Generate a matching adjustment instruction:

[0076] Adjust the matching weight: If is large (transport capacity imbalance), increase the weight of transport capacity scheduling and optimize the supply-demand matching strategy. If is large (frequent fluctuations in the matching pattern), reduce the algorithm adjustment frequency and enhance the stability of the matching strategy.

[0077] Dynamically optimize transport capacity allocation: If the supply-demand ratio is severely imbalanced, dispatch more transport capacity to the shortage area. If a certain area has a long-term supply-demand imbalance, adjust the long-term matching rules (such as optimizing the storage location and adding transfer points).

[0078] Optimize the matching algorithm: Combine historical data to retrain the matching model and improve the stability and accuracy of the matching. Reduce the sensitivity to high-frequency strategy switches and minimize unnecessary pattern conversions.

[0079] If the anomaly matching degree is less than the preset threshold, it indicates that the current matching strategy is still within the normal range, and there is no need to adjust the matching plan. Maintain the current matching rules.

[0080] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0081] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that contains one or more sets of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0082] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context. Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this document can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0083] As described above, the above are only the specific implementation manners of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application.

Claims

1. An intelligent logistics matching method empowered by dynamic data, characterized in that: Including: Obtain the real-time operation data of the logistics matching system, and perform standardization processing on it to form an initial state feature vector; Based on the long-term monitoring data, screen out the target order delivery groups with stable logistics network operation and reasonable matching results; Calculate the state feature similarity between the initial state feature vector and the target order delivery group, determine the optimally matched order delivery group, and generate an optimal logistics matching plan; If the similarity is lower than the preset similarity threshold, it is determined that the logistics matching is abnormal, and different types of abnormal matching patterns are identified, and the abnormal features under each abnormal matching pattern are extracted; Combined with the abnormal features of the logistics capacity distribution and the abnormal features of the temporal change of the matching pattern, calculate the abnormal matching degree, and generate corresponding matching adjustment instructions according to the calculation results to dynamically adjust the matching weight; The abnormal feature of the logistics capacity distribution is the abnormal index of the capacity supply-demand ratio, and the abnormal feature of the temporal change of the matching pattern is the deviation index of the matching pattern conversion frequency; Among them, the method for obtaining the matching pattern conversion frequency deviation index is as follows: record the number of matching pattern conversions in the past N time windows to form a time series, and train an ARIMA model to enable it to predict the normal trend of the matching pattern conversion frequency; calculate the actual matching pattern conversion frequency and the ARIMA predicted value of the difference , and the expression is: ; after calculating the mean square error MSE of the difference, calculate the matching pattern conversion frequency deviation index, and the expression is: ; where c is an extremely small number, is the matching pattern conversion frequency deviation index.

2. The intelligent logistics matching method based on dynamic data empowerment according to claim 1, wherein: For the screening of the target order delivery group, the K-means clustering algorithm is further used to classify the historical order data to determine the target group with the most stable matching and the highest delivery success rate: set the number of clusters k, initialize the cluster center, and calculate the Euclidean distance from each order group to the cluster center: iteratively update the cluster center until convergence, and select the order group with the smallest standard deviation and the highest matching success rate as the target delivery group.

3. The intelligent logistics matching method based on dynamic data empowerment according to claim 2, characterized in that: The cosine similarity calculation method is used to calculate the similarity between the initial state feature vector and the target order delivery group. If the cosine similarity is lower than the set threshold, it is determined that the matching is abnormal, and the abnormal features of the logistics capacity distribution and the temporal change of the matching pattern are identified for abnormal pattern analysis and adjustment.

4. The intelligent logistics matching method based on dynamic data empowerment according to claim 3, wherein: After analyzing the abnormal change of the regional capacity supply-demand ratio extracted, calculate the abnormal index of the capacity supply-demand ratio. The calculation method of the abnormal index of the capacity supply-demand ratio is: Within each time window t, collect the available transportation capacity in the target area A , representing the current number of dispatchable vehicles / riders in area A and the number of orders to be matched , representing the total number of orders to be matched in area A; At each time window t, calculate the supply-demand ratio of regional transport capacity: ; Calculate the change rate of the supply-demand ratio of transport capacity within the time window , and the expression is: ; Calculate the mean and standard deviation of the historical transport capacity supply-demand ratio of calculation area A within the past N time windows, and define the transport capacity supply-demand ratio anomaly index. The expression is as follows: ; where: is the transport capacity supply-demand ratio anomaly index, is a very small positive number to prevent the denominator from being 0, is the mean of the historical transport capacity supply-demand ratio, is the standard deviation of the historical transport capacity supply-demand ratio.

5. The intelligent logistics matching method based on dynamic data empowerment according to claim 4, characterized in that: Normalize the abnormal index of the capacity supply-demand ratio and the deviation index of the matching pattern conversion frequency so that they are both in the range of [0,1], and calculate the abnormal matching degree according to the normalized abnormal index of the capacity supply-demand ratio and the deviation index of the matching pattern conversion frequency.

6. The intelligent logistics matching method based on dynamic data empowerment according to claim 5, wherein: Compare the obtained abnormal matching degree with the preset threshold. If the abnormal matching degree is greater than or equal to the preset threshold, it indicates that there is an abnormality in the current matching strategy. At this time, generate a matching adjustment instruction, including adjusting the matching weight, dynamically optimizing the capacity allocation, and optimizing the matching algorithm; if the abnormal matching degree is less than the preset threshold, it indicates that the current matching strategy is still within the normal range, and there is no need to adjust the matching plan, and the current matching rule is maintained.

Images