Logistics vehicle real-time monitoring method, device and equipment and storage medium

Abstract

The invention relates to the technical field of logistics, in particular to a logistics vehicle real-time monitoring method, device and equipment and a storage medium. The logistics vehicle real-time monitoring method comprises the following steps: acquiring real-time data of a vehicle and related data of an enterprise system so as to update local data; multiple models are adopted to extract and count the data of the latest period of time in the local data, and statistical data are obtained; weights are given to data at different times in the statistical data to obtain adjustment data, and a time sequence analysis model is adopted to calculate a vehicle information predicted value according to the adjustment data; and acquiring latest vehicle arrival data, and performing judgment and early warning on overtime of the vehicle according to the latest vehicle arrival data and the vehicle information predicted value by adopting an early warning model. According to the method, the data of the latest period of time can be dynamically acquired in real time, and the time sequence analysis model is adopted to predict the vehicle arrival data of the logistics network in a future period of time, so that the prediction accuracy is higher.

Description

Technical Field

[0001] The present invention relates to the field of logistics technology, and in particular to a method, device, equipment and storage medium for real-time monitoring of logistics vehicles. Background Art

[0002] Traditional monitoring systems have significant limitations in predicting vehicle transport status. They fail to fully exploit the potential of combining historical data with real-time transport status and lack the ability to comprehensively analyze dynamic variables and make real-time corrections. Current prediction methods primarily rely on simple rules of thumb or static models, ignoring the complex and ever-changing dynamic factors of the transport process. This results in significant deviations between predictions and actual conditions.

[0003] In practical applications, traditional systems fail to effectively integrate real-time traffic information when predicting vehicle arrival times, nor do they fully account for seasonal and time-of-day variations in road efficiency. Furthermore, existing systems are unable to dynamically adjust prediction models based on historical data and real-time conditions to account for speed fluctuations during transportation due to factors such as weather changes and fluctuations in vehicle mechanical performance. This static prediction approach is unable to adapt to the complexity and dynamic nature of the transportation environment.

[0004] This limitation directly leads to insufficient forecast accuracy, making it impossible to provide precise decision-making support for logistics companies. This makes it difficult for logistics companies to rationally arrange subsequent processes such as warehousing and loading and unloading, increasing operating costs and potential risks. Summary of the Invention

[0005] In view of the above-mentioned deficiencies in the prior art, the purpose of the present invention is to provide a real-time monitoring method, device, equipment and storage medium for logistics vehicles, aiming to solve the technical problem that the static prediction method in the prior art is difficult to accurately estimate the arrival time of vehicles.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A first aspect of the present invention provides a real-time monitoring method for logistics vehicles, comprising the following steps: obtaining real-time data of vehicles and enterprise system-related data to update local data; using multiple models to extract and count data from the most recent period of local data to obtain statistical data; assigning weights to data at different times in the statistical data to obtain adjusted data, using a time series analysis model to calculate vehicle information prediction values based on the adjusted data; obtaining the latest vehicle arrival data, using an early warning model to determine and issue early warnings for vehicle timeouts based on the latest vehicle arrival data and vehicle information prediction values.

[0008] Optionally, in a first implementation method of the first aspect of the present invention, the acquisition of the vehicle's real-time data and enterprise system-related data to update the local data specifically includes: adopting a polling algorithm to periodically acquire the vehicle's real-time data at set time intervals; cleaning and preprocessing the real-time data to obtain preprocessed data, and updating the local data based on the preprocessed data; acquiring enterprise system-related data, adopting an incremental synchronization algorithm, and updating the local data based on the enterprise system-related data.

[0009] Optionally, in a second implementation of the first aspect of the present invention, the use of multiple models to extract and count the data of the most recent period in the local data to obtain statistical data specifically includes: constructing a sliding window model, setting the time window of the sliding window model, and using the sliding window model to extract the data of the most recent period in the local data; using a counting model to count the departure data based on the data of the most recent period; using a dual counting model to count the expected arrival data and actual arrival data based on the data of the most recent period; summarizing the data of the most recent period, departure data, expected arrival data and actual arrival data to obtain statistical data.

[0010] Optionally, in a third implementation method of the first aspect of the present invention, weights are assigned to data at different times in the statistical data to obtain adjusted data, and a time series analysis model is used to calculate the vehicle information prediction value based on the adjusted data, specifically including: using a weighted average algorithm to assign weights to data at different times in the statistical data to obtain adjusted data; using an autoregressive integral sliding average model to predict the number and tonnage of vehicles distributed in a future time period based on the adjusted data to obtain a prediction result; obtaining the actual arrival data of the vehicle, comparing the actual arrival data of the vehicle with the prediction result to obtain a deviation result, and using a feedback control algorithm to adjust the parameters of the autoregressive integral sliding average model based on the deviation result.

[0011] Optionally, in a fourth implementation method of the first aspect of the present invention, the latest vehicle arrival data is obtained, and an early warning model is used to determine and warn of vehicle timeouts based on the latest vehicle arrival data and vehicle information prediction values, specifically including: constructing an early warning model, and setting the timeout determination rules in the early warning model; using an adaptive threshold algorithm to adjust the trigger conditions in the timeout determination rules based on statistical data and historical data; inputting the latest vehicle arrival data and vehicle information prediction values into the early warning model to obtain a comparison result, and matching the comparison result with the timeout determination rules; when the comparison result meets the trigger conditions in the timeout determination rules, it is determined that the vehicle has timed out and an early warning is issued.

[0012] Optionally, in a fifth implementation of the first aspect of the present invention, an adaptive threshold algorithm is used to adjust the triggering conditions in the timeout determination rule according to historical vehicle data, specifically including: obtaining historical vehicle data, the historical vehicle data including the vehicle's departure station, arrival station, departure time, arrival time and driving route, calculating the historical transportation time according to the departure time and arrival time, generating a warning threshold according to the historical transportation time, aggregating the historical vehicle data and the warning threshold to form a vehicle transportation data set; extracting the vehicle's latest departure station, departure time and current position from statistical data, and obtaining the vehicle's planned driving route; using an adaptive threshold algorithm, matching the vehicle's latest departure station, departure time, current position and planned driving route with the vehicle transportation data set to obtain a warning threshold, and adjusting the warning threshold in the timeout determination rule.

[0013] Optionally, in a sixth implementation of the first aspect of the present invention, when the comparison result meets the triggering conditions in the timeout determination rule, it is determined that the vehicle has timed out and an early warning is issued, specifically including: setting an early warning processing strategy, and dividing the vehicle's timeout duration into early warning levels; the early warning levels include level one early warning, level two early warning, and level three early warning, and response measures are formulated according to the early warning levels; when the comparison result meets the triggering conditions in the timeout determination rule, it is determined that the vehicle has timed out, the vehicle timeout duration is matched with the early warning processing strategy, and corresponding response measures are executed.

[0014] The second aspect of the present invention provides a real-time monitoring device for logistics vehicles, including: a data update module for obtaining real-time data of vehicles and enterprise system-related data to update local data; a statistical module for using multiple models to extract and count data from the most recent period of local data to obtain statistical data; a prediction module for assigning weights to data at different times in the statistical data to obtain adjusted data, using a time series analysis model to calculate vehicle information prediction values based on the adjusted data; an early warning module for obtaining the latest vehicle arrival data, using an early warning model to determine and issue early warnings for vehicle timeouts based on the latest vehicle arrival data and vehicle information prediction values.

[0015] Optionally, in a first implementation method of the second aspect of the present invention, the data update module includes: a polling unit, used to adopt a polling algorithm to periodically obtain real-time data of the vehicle at set time intervals; a preprocessing unit, used to clean and preprocess the real-time data, obtain preprocessed data, and update local data based on the preprocessed data; an update unit, used to obtain enterprise system-related data, adopt an incremental synchronization algorithm, and update local data based on enterprise system-related data.

[0016] Optionally, in a second implementation of the second aspect of the present invention, the statistical module includes: an extraction unit, used to construct a sliding window model, set the time window of the sliding window model, and use the sliding window model to extract data from the most recent period of local data; a first statistical unit, used to use a counting model to count the departure data based on the data from the most recent period of time; a second statistical unit, used to use a double counting model to count the expected arrival data and actual arrival data based on the data from the most recent period of time; and a summary unit, used to summarize the data from the most recent period of time, departure data, expected arrival data, and actual arrival data to obtain statistical data.

[0017] Optionally, in a third implementation of the second aspect of the present invention, the prediction module includes: a weight unit, used to adopt a weighted average algorithm to assign weights to data at different times in the statistical data to obtain adjusted data; a prediction unit, used to adopt an autoregressive integral moving average model to predict the number of vehicles and tonnage distributed in the future time period based on the adjusted data to obtain a prediction result; a feedback unit, used to obtain the actual arrival data of the vehicle, compare the actual arrival data of the vehicle with the prediction result to obtain a deviation result, and adopt a feedback control algorithm to adjust the parameters of the autoregressive integral moving average model according to the deviation result.

[0018] Optionally, in a fourth implementation of the second aspect of the present invention, the early warning module includes: a construction unit for constructing an early warning model and setting the timeout determination rules in the early warning model; an adjustment unit for using an adaptive threshold algorithm to adjust the trigger conditions in the timeout determination rules according to statistical data and historical data; a matching unit for inputting the latest vehicle arrival data and vehicle information prediction values into the early warning model to obtain a comparison result, and matching the comparison result with the timeout determination rules; a judgment unit for judging that the vehicle has timed out and issuing an early warning when the comparison result meets the trigger conditions in the timeout determination rules.

[0019] Optionally, in a fifth implementation of the second aspect of the present invention, the adjustment unit includes: a generation subunit for acquiring historical vehicle data, the historical vehicle data including the vehicle's departure station, arrival station, departure time, arrival time and driving route, calculating the historical transportation time based on the departure time and arrival time, generating a warning threshold based on the historical transportation time, and aggregating the historical vehicle data and the warning threshold to form a vehicle transportation data set; an acquisition subunit for extracting the vehicle's latest departure station, departure time and current position from statistical data, and acquiring the vehicle's planned driving route; an adjustment subunit for using an adaptive threshold algorithm to match the vehicle's latest departure station, departure time, current position and planned driving route with the vehicle transportation data set to obtain a warning threshold, and adjust the warning threshold in the timeout determination rule.

[0020] Optionally, in a sixth implementation of the second aspect of the present invention, the determination unit includes: a division subunit, for setting a warning processing strategy, and dividing warning levels according to the vehicle's timeout duration; a formulation subunit, for the warning levels include level one warning, level two warning, and level three warning, and for formulating response measures according to the warning levels; a determination subunit, for determining that the vehicle has timed out when the comparison result meets the trigger condition in the timeout determination rule, matching the vehicle timeout duration with the warning processing strategy, and executing corresponding response measures.

[0021] The third aspect of the present invention provides a real-time monitoring device for logistics vehicles, comprising a memory and at least one processor, wherein the memory stores computer-readable instructions; the at least one processor calls the computer-readable instructions in the memory to execute the various steps of the real-time monitoring method for logistics vehicles as described above.

[0022] A fourth aspect of the present invention provides a computer-readable storage medium having computer-readable instructions stored thereon. When the computer-readable instructions are executed by a processor, the various steps of the above-mentioned method for real-time monitoring of logistics vehicles are implemented.

[0023] Beneficial effects: The present invention provides a real-time monitoring method for logistics vehicles. The real-time monitoring method for logistics vehicles first obtains the real-time data of the vehicle and the relevant data of the enterprise system to achieve real-time update of the local data to ensure the timeliness of the data; then, a variety of models are used to extract and count the data of the most recent period in the local data to obtain statistical data, which not only facilitates the subsequent data utilization, but also selects data with stronger timeliness to make subsequent predictions more accurate; then, by assigning weights to the data at different times in the statistical data, the adjusted data is obtained, so that the vehicle information prediction value calculated according to the adjusted data by using the time series analysis model can more accurately reflect the changing trend of the data; finally, by adopting an early warning model, the vehicle timeout is judged and warned according to the latest vehicle arrival data and the vehicle information prediction value, so that management personnel can make arrangements and work adjustments in advance according to different situations in a timely manner, thereby improving response capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A first flow chart of a method for real-time monitoring of logistics vehicles provided by an embodiment of the present invention;

[0025] Figure 2 A second flow chart of the method for real-time monitoring of logistics vehicles provided by an embodiment of the present invention;

[0026] Figure 3 A third flow chart of the real-time monitoring method for logistics vehicles provided by an embodiment of the present invention;

[0027] Figure 4 A fourth flow chart of the method for real-time monitoring of logistics vehicles provided by an embodiment of the present invention;

[0028] Figure 5 A fifth flow chart of the method for real-time monitoring of logistics vehicles provided by an embodiment of the present invention;

[0029] Figure 6 A sixth flow chart of the real-time monitoring method for logistics vehicles provided by an embodiment of the present invention;

[0030] Figure 7 A seventh flow chart of the method for real-time monitoring of logistics vehicles provided by an embodiment of the present invention;

[0031] Figure 8 A schematic diagram of the structure of a real-time monitoring device for logistics vehicles provided by an embodiment of the present invention;

[0032] Figure 9 Another structural diagram of the real-time monitoring device for logistics vehicles provided by an embodiment of the present invention;

[0033] Figure 10 A schematic structural diagram of a real-time monitoring device for logistics vehicles provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The present invention provides a method, device, equipment and storage medium for real-time monitoring of logistics vehicles. The present invention first obtains the real-time data of the vehicle and the relevant data of the enterprise system, updates the local data in real time, and ensures the timeliness of the data; then extracts and counts the data with stronger timeliness in the most recent period of local data, provides a basis for subsequent analysis, and screens out data with more reference value to improve the accuracy of prediction. Then, by adjusting the data of different time periods in the statistical data according to the weights, combined with the time series analysis model, the vehicle information prediction value that is closer to the actual change trend is calculated. Finally, through the early warning model combined with the latest vehicle arrival data and the prediction value, the vehicle overtime situation is judged and warned in real time, so that managers can make arrangements and adjustments in advance according to different situations, thereby improving the response ability.

[0035] The terms "first," "second," "third," "fourth," and the like (if any) in the description and claims of the present invention and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or apparatus.

[0036] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 The first embodiment of the real-time monitoring method for logistics vehicles in the embodiment of the present invention includes:

[0037] S101. Obtain real-time vehicle data and enterprise system-related data to update local data;

[0038] S102. Use multiple models to extract and count the local data in the recent period to obtain statistical data;

[0039] S103. Assign weights to the data at different times in the statistical data to obtain adjusted data, and use a time series analysis model to calculate the vehicle information prediction value based on the adjusted data;

[0040] S104. Obtain the latest vehicle arrival data, use the early warning model, and determine and issue an early warning for vehicle timeout based on the latest vehicle arrival data and vehicle information prediction values.

[0041] In this embodiment, during the real-time data acquisition phase, the basic information of the vehicle can be obtained through the satellite positioning interface, and then the data can be preliminarily cleaned and preprocessed, while the relevant data is synchronized from the enterprise system. For example, the enterprise resource planning system (ERP system) integrates various resources within the enterprise, including human, material, and financial resources, to achieve information sharing and process optimization. In the field of logistics, the ERP system plays a vital role. It can not only manage basic information such as logistics orders, inventory, and distribution, but also seamlessly connect with modules such as finance, procurement, and sales to provide comprehensive operational management support for the enterprise. By further obtaining relevant information from the enterprise system for updating, local data can be made more complete.

[0042] After timely updating the local data, this embodiment uses multiple models to extract and count the data of the most recent period of time in the local data, where the data of the most recent period refers to the data within the range of the current system time to the previous N days. N can be adjusted according to actual conditions, such as data from the previous 10 days or the previous 5 days. By obtaining the most recent data for statistics, the timeliness of the data can be ensured. The subsequent vehicle information prediction value is highly correlated with the most recent data, while for data that is older in time, the correlation is smaller. By ensuring the timeliness of the data, the subsequent prediction results based on statistical data will be more accurate.

[0043] In statistical data, data from different times has varying degrees of correlation with future data. Generally speaking, the closer the date is to the current time, the greater the correlation between the corresponding data and future data. By assigning weights to each, the time series analysis model can prioritize data closer to the current time, allowing vehicle information predictions to more accurately reflect data trends.

[0044] By acquiring real-time vehicle arrival data and combining it with forecasts, it's possible to promptly identify vehicle delays or timeouts, providing managers with immediate warnings. This allows managers to understand the expected number of vehicle arrivals and loading and unloading volumes, and whether these volumes will be excessive or insufficient, allowing them to adjust staffing arrangements appropriately. For example, due to sudden traffic congestion, some vehicles may arrive late at the distribution center. The original forecast was for seven trucks to arrive before 12:00 AM, but the latest arrival data shows only four arriving within the expected timeframe. A comparison reveals that three trucks arrived late, prompting the system to issue a warning, alerting managers to the situation. The system then continuously updates the vehicle information forecast, allowing for adjustments to future staffing arrangements.

[0045] See also Figure 2 The second embodiment of the method for real-time monitoring of logistics vehicles in the embodiment of the present invention includes:

[0046] S201 uses a polling algorithm to obtain real-time vehicle data at set time intervals;

[0047] S202. Clean and preprocess the real-time data to obtain preprocessed data, and update the local data based on the preprocessed data;

[0048] S203. Obtain enterprise system related data, use incremental synchronization algorithm, and update local data based on the enterprise system related data.

[0049] The polling algorithm sends a request to the satellite navigation positioning interface at a certain interval (such as 1 minute) to obtain the vehicle's GPS coordinates and transportation status. This algorithm can ensure the real-time data while avoiding the waste of resources caused by frequent requests.

[0050] After acquiring real-time data, clean it to remove outliers. Statistical methods, such as the Z-score algorithm, can be used to detect outliers in GPS coordinates. For transportation status data, rule matching is used to check for illegal states. After cleaning, further data preprocessing, such as data padding, can be performed. If certain fields are found to be empty during data acquisition, interpolation algorithms (such as linear interpolation) can be used to fill in the missing data.

[0051] The incremental synchronization algorithm compares local data with relevant data in the enterprise system and only synchronizes updated data. This reduces the amount of data transferred and improves synchronization efficiency.

[0052] See also Figure 3 The third embodiment of the method for real-time monitoring of logistics vehicles in the embodiment of the present invention includes:

[0053] S301. Build a sliding window model, set the time window of the sliding window model, and use the sliding window model to extract the most recent data from the local data;

[0054] S302. Using a counting model, statistics of departure data are collected based on the most recent period of time;

[0055] S303 uses a double counting model to calculate the expected arrival data and the actual arrival data based on the recent data statistics;

[0056] S304. Summarize the data of the most recent period, the departure data, the expected arrival data and the actual arrival data to obtain statistical data.

[0057] The sliding window model uses the concept of a sliding window that slides over time. If the sliding window is defined as the period from 10 days before the current system time to the current time, the sliding window model extracts data from the current time to the previous 10 days in the local data, ensuring the timeliness of the data obtained.

[0058] The counting model can further analyze local data. For example, the sliding window model extracts vehicle data from the local database for the past five days, including vehicle departure time, estimated arrival time, actual arrival time, cargo quantity, and cargo weight. The counting model can count the total number of vehicles that have departed from the distribution center in the past five days, the interval between each vehicle, and the expected number of arriving cargo and trucks at each distribution center. As needed, each day can be divided into multiple time periods, such as two-hour periods, and the number of vehicles and cargo in each time period can be counted separately.

[0059] By building sliding window models, counting models, and double-counting models, logistics companies can count and analyze vehicle departure, expected arrival, and actual arrival data in real time, thereby better understanding the patterns and problems in the transportation process and providing data support for optimizing transportation plans and improving logistics efficiency.

[0060] See also Figure 4 The fourth embodiment of the method for real-time monitoring of logistics vehicles in the embodiment of the present invention includes:

[0061] S401. Using a weighted average algorithm, weights are assigned to the data at different times in the statistical data to obtain adjusted data;

[0062] S402. Using the autoregressive integrated moving average model, the number of vehicles and tonnage distributed in the future time period are predicted based on the adjusted data to obtain the prediction results;

[0063] S403. Obtain the actual arrival data of the vehicle, compare the actual arrival data of the vehicle with the predicted result, obtain the deviation result, adopt the feedback control algorithm, and adjust the parameters of the autoregressive integrated moving average model according to the deviation result.

[0064] When calculating daily averages, in addition to simply summing and averaging, you can also use a weighted average algorithm to assign different weights to data from different dates. For example, dates closer to the current time have higher weights. This can more accurately reflect data trends.

[0065] When using a time series analysis model, you can choose the Autoregressive Integrated Moving Average (ARIMA) model. This model can predict the number of vehicles and tonnage distributed by hour for the next day or several days based on the time series characteristics of historical departure data. The input is data from the 10 days preceding the current time, and the output is the predicted value. Managers can schedule staff based on the expected number of vehicle arrivals and cargo data to meet staffing requirements during peak cargo times.

[0066] To make the Autoregressive Integrated Moving Average model more suitable for predicting vehicle arrivals in the logistics industry, a feedback control algorithm can be used to automatically adjust subsequent forecasts when the actual arrival time deviates significantly from the predicted time. Specifically, the ARIMA model parameters can be adjusted based on the size and direction of the deviation to improve forecast accuracy.

[0067] See also Figure 5 The fifth embodiment of the method for real-time monitoring of logistics vehicles in the embodiment of the present invention includes:

[0068] S501. Build an early warning model and set the timeout judgment rules in the early warning model;

[0069] S502 uses an adaptive threshold algorithm to adjust the trigger conditions in the timeout determination rules based on statistical data and historical data;

[0070] S503. The latest vehicle arrival data and vehicle information prediction value are input into the warning model to obtain a comparison result, and the comparison result is matched with the timeout judgment rule;

[0071] S504. When the comparison result satisfies the triggering condition in the timeout determination rule, it is determined that the vehicle has timed out and an early warning is issued.

[0072] Specifically, the timeout judgment rule can be set as follows: if the estimated time for a truck to travel from point A to point B is 2 days, and the estimated arrival time is 13:00 on May 5th, the truck is in the "in transit" state (confirmed to have been dispatched), and the truck has not arrived at 19:00 on May 5th (13:00 plus 6 hours of reserved time), the trigger condition is met. Depending on the length of the transportation, the reserved time will be adjusted, that is, the threshold in the trigger condition is different. For short-distance transportation, the threshold is smaller. For example, if a truck with a transportation time of 1 day has not arrived 3 hours after the estimated time, the trigger warning condition is met.

[0073] The adaptive threshold algorithm automatically adjusts the timeout threshold based on statistical analysis of historical data to adapt to different transportation scenarios. For example, if a truck's estimated arrival time falls during rush hour, historical data suggests that some sections of the road it will pass through will be congested, resulting in a longer delay. In this case, the adaptive threshold algorithm will adjust the threshold to reduce misjudgments of abnormal situations.

[0074] After inputting the latest vehicle arrival data and vehicle information predictions into the early warning model, the model first generates a comparison result. For example, the latest vehicle arrival data indicates that five trucks have arrived, while the vehicle information prediction indicates seven trucks. Of the two trucks that have not arrived, Truck A is expected to arrive in one day and has exceeded its arrival time by four hours, while Truck B is expected to arrive in two days and has exceeded its arrival time by six hours. The comparison result is then matched against the timeout / failure determination rule. The timeout / failure determination rule comprehensively matches the estimated arrival time and the timeout duration to determine that Truck A meets the trigger condition, while Truck B does not. Once the trigger condition is met, early warning measures are taken for Truck A.

[0075] See also Figure 6 The sixth embodiment of the method for real-time monitoring of logistics vehicles in the embodiment of the present invention includes:

[0076] S601. Obtain historical vehicle data, including the vehicle's departure station, arrival station, departure time, arrival time, and travel route, calculate the historical transport time based on the departure time and arrival time, generate a warning threshold based on the historical transport time, and aggregate the historical vehicle data and warning threshold to form a vehicle transport data set;

[0077] S602 extracts the vehicle's latest departure site, departure time, and current location from statistical data, and obtains the vehicle's planned driving route;

[0078] S603. Adopting an adaptive threshold algorithm, the vehicle's latest departure station, departure time, current location, and planned driving route are matched with the vehicle transportation dataset to obtain a warning threshold, and the warning threshold in the timeout judgment rule is adjusted.

[0079] Different vehicles have different departure and arrival points, departure times, arrival times, and routes, resulting in different travel times and the probability of encountering emergencies. For example, if a route includes sections with a high risk of geological disasters, the road conditions are generally poor, and any delays will be much longer than those on a typical route. By generating warning thresholds and vehicle transportation datasets based on various scenarios, subsequent comparisons can be quickly performed, improving data processing speed and eliminating the need for repeated data acquisition.

[0080] The adaptive threshold algorithm matches the vehicle's most recent departure station, departure time, current location, and route with the vehicle transportation dataset. It can quickly compare historical trips along the same route, the time it took to pass through the current location, and the time it took to arrive at the destination, thereby matching the pre-set warning threshold and adjusting the warning threshold in the timeout determination rule. For example, if a vehicle has already passed through point C and its first destination is point B, historical data shows that for the same route, the time it takes to travel from point C to point B is 8 hours, and the pre-set warning threshold is 2 hours. However, for the second destination, point D, the time it takes to travel from point C to point B and then to point D is 16 hours, and the pre-set warning threshold is 5 hours. This warning threshold is output to the management systems of points B and D, respectively.

[0081] See also Figure 7 The seventh embodiment of the method for real-time monitoring of logistics vehicles in the embodiment of the present invention includes:

[0082] S701. Set up warning processing strategies and classify warning levels according to vehicle timeout duration;

[0083] S702. The warning levels include level 1, level 2, and level 3, and response measures are formulated according to the warning levels.

[0084] S703. When the comparison result meets the triggering condition in the timeout determination rule, it is determined that the vehicle has timed out, the vehicle timeout duration is matched with the warning processing strategy, and the corresponding response measures are executed.

[0085] Specifically, a timeout period of 1-12 hours can be designated as a Level 1 warning, 12-24 hours as a Level 2 warning, and 24-48 hours as a Level 3 warning. Different levels of warnings employ different handling strategies. For example, a Level 1 warning can alert the driver via text message, a Level 2 warning can notify dispatchers for manual intervention, and a Level 3 warning can activate an emergency response mechanism.

[0086] The present invention can dynamically predict vehicle arrival information for each network or distribution center over the next period of time, with predictions available for each specific time period. This allows network or distribution center managers to rationally schedule staff work schedules for the next few days based on the predictions, thereby improving both staffing efficiency and the efficiency of logistics distribution and loading and unloading.

[0087] The above describes the real-time monitoring method for logistics vehicles in the embodiment of the present invention. The following describes the real-time monitoring device for logistics vehicles in the embodiment of the present invention. Figure 8 In one embodiment of the present invention, a real-time monitoring device for logistics vehicles includes:

[0088] The data update module 10 is used to obtain the real-time data of the vehicle and the relevant data of the enterprise system to update the local data;

[0089] The statistics module 20 is used to extract and count the local data of the most recent period using multiple models to obtain statistical data;

[0090] The prediction module 30 is used to assign weights to the data at different times in the statistical data to obtain adjusted data, and calculate the vehicle information prediction value based on the adjusted data using a time series analysis model;

[0091] The early warning module 40 is used to obtain the latest vehicle arrival data and use an early warning model to determine and issue an early warning for vehicle timeout based on the latest vehicle arrival data and vehicle information prediction values.

[0092] See also Figure 9 In one embodiment of the present invention, a real-time monitoring device for logistics vehicles includes:

[0093] The data update module 10 is used to obtain the real-time data of the vehicle and the relevant data of the enterprise system to update the local data;

[0094] The statistics module 20 is used to extract and count the local data of the most recent period using multiple models to obtain statistical data;

[0095] The prediction module 30 is used to assign weights to the data at different times in the statistical data to obtain adjusted data, and calculate the vehicle information prediction value based on the adjusted data using a time series analysis model;

[0096] The early warning module 40 is used to obtain the latest vehicle arrival data and use the early warning model to determine and issue an early warning for vehicle timeouts based on the latest vehicle arrival data and vehicle information prediction values;

[0097] In this embodiment, the data updating module 10 includes:

[0098] The polling unit 11 is used to obtain the real-time data of the vehicle at set time intervals using a polling algorithm;

[0099] The preprocessing unit 12 is used to clean and preprocess the real-time data, obtain preprocessed data, and update the local data according to the preprocessed data;

[0100] An updating unit 13 is used to obtain enterprise system related data and update local data based on the enterprise system related data using an incremental synchronization algorithm;

[0101] In this embodiment, the statistics module 20 includes:

[0102] The extraction unit 21 is used to construct a sliding window model, set a time window for the sliding window model, and use the sliding window model to extract the most recent data from the local data;

[0103] The first statistical unit 22 is used to use a counting model to collect the departure data based on the data of the most recent period;

[0104] The second statistical unit 23 is used to use a double counting model to count the expected arrival data and the actual arrival data based on the data of the most recent period;

[0105] A summarizing unit 24 is used to summarize the data of the recent period, the departure data, the expected arrival data and the actual arrival data to obtain statistical data;

[0106] In this embodiment, the prediction module 30 includes:

[0107] The weighting unit 31 is used to assign weights to the data at different times in the statistical data using a weighted average algorithm to obtain adjusted data;

[0108] A prediction unit 32 is configured to use an autoregressive integrated moving average model to predict the number of vehicles and tonnage distributed in a future time period based on the adjusted data to obtain a prediction result;

[0109] A feedback unit 33 is configured to obtain actual vehicle arrival data, compare the actual vehicle arrival data with the predicted result, obtain a deviation result, and use a feedback control algorithm to adjust the parameters of the autoregressive integrated moving average model based on the deviation result;

[0110] In this embodiment, the early warning module 40 includes:

[0111] A construction unit 41 is used to construct an early warning model and set a timeout determination rule in the early warning model;

[0112] An adjustment unit 42 is configured to use an adaptive threshold algorithm to adjust the triggering condition in the timeout determination rule based on statistical data and historical data;

[0113] The matching unit 43 is used to input the latest vehicle arrival data and the vehicle information prediction value into the early warning model to obtain a comparison result, and match the comparison result with the timeout failure judgment rule;

[0114] The determination unit 44 is configured to determine that the vehicle has timed out and issue an early warning when the comparison result satisfies the triggering condition in the timeout determination rule;

[0115] In this embodiment, the adjustment unit 42 includes:

[0116] A generating subunit 421 is configured to obtain historical vehicle data, including the vehicle's departure station, arrival station, departure time, arrival time, and travel route, calculate historical transportation time based on the departure time and arrival time, generate a warning threshold based on the historical transportation time, and aggregate the historical vehicle data and the warning threshold to form a vehicle transportation dataset;

[0117] The acquisition subunit 422 is used to extract the latest departure station, departure time and current location of the vehicle from the statistical data, and obtain the planned driving route of the vehicle;

[0118] The adjustment subunit 423 is configured to use an adaptive threshold algorithm to match the vehicle's latest departure station, departure time, current location, and planned travel route with the vehicle transportation dataset to obtain a warning threshold, and adjust the warning threshold in the timeout determination rule;

[0119] In this embodiment, the determination unit 44 includes:

[0120] The classification subunit 441 is used to set a warning processing strategy and classify warning levels according to the timeout duration of the vehicle;

[0121] The formulation subunit 442 is used to formulate response measures according to the warning levels, including level one, level two, and level three;

[0122] The determination subunit 443 is configured to determine that the vehicle has timed out when the comparison result satisfies the triggering condition in the timeout determination rule, match the vehicle timeout duration with the warning processing strategy, and execute corresponding response measures.

[0123] The real-time monitoring device for logistics vehicles of the present invention obtains the vehicle's operating data and enterprise system-related data in real time, dynamically updates the local database, and ensures the timeliness and accuracy of the data. On this basis, the system extracts and counts the high-timeliness data in the recent period, filters out information with greater reference value, and provides reliable data support for subsequent analysis. By adjusting the statistical data according to the time weight and combining it with the time series analysis model, the system can accurately predict the changing trend of vehicle information and be close to the actual transportation situation. Finally, the early warning model is used in combination with the latest vehicle arrival data and predicted values to determine in real time whether the vehicle is overtime and issue an early warning, helping managers to take measures in advance, optimize resource allocation, improve response capabilities, and ensure efficient and smooth logistics operations.

[0124] The above is a detailed description of the real-time monitoring device for logistics vehicles in an embodiment of the present invention from the perspective of modular functional entities. The following is a detailed description of the real-time monitoring device for logistics vehicles in an embodiment of the present invention from the perspective of hardware processing.

[0125] Figure 10 This is a schematic structural diagram of a real-time monitoring device for logistics vehicles provided in an embodiment of the present invention. The real-time monitoring device 900 for logistics vehicles may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 910 (for example, one or more processors) and a memory 920, and one or more storage media 930 (for example, one or more mass storage devices) for storing application programs 933 or data 932. Among them, the memory 920 and the storage medium 930 can be temporary storage or permanent storage. The program stored in the storage medium 930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the real-time monitoring device 900 for logistics vehicles. Furthermore, the processor 910 can be configured to communicate with the storage medium 930, and execute a series of instruction operations in the storage medium 930 on the real-time monitoring device 900 for logistics vehicles, so as to implement the steps of the real-time monitoring method for logistics vehicles provided in the above-mentioned method embodiments.

[0126] The real-time monitoring device 900 for logistics vehicles may further include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input and output interfaces 960, and / or one or more operating systems 931, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 10 The structure of the real-time monitoring equipment for logistics vehicles shown does not constitute a limitation on the real-time monitoring equipment for logistics vehicles, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0127] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the steps of the method for real-time monitoring of logistics vehicles.

[0128] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working process of the above-described equipment or device can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0129] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc., various media that can store program code.

[0130] It is understandable that those skilled in the art can make equivalent substitutions or changes based on the technical solution and inventive concept of the present invention, and all these changes or substitutions should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A real-time monitoring method for logistics vehicles, characterized in that: The steps include: Obtain real-time data from vehicles and relevant data from enterprise systems to update local data; Use multiple models to extract and count the local data for the most recent period to obtain statistical data; Assign weights to the data at different times in the statistical data to obtain adjusted data, and use the time series analysis model to calculate the vehicle information prediction value based on the adjusted data; Obtain the latest vehicle arrival data, use the early warning model, and judge and issue early warnings for vehicle timeouts based on the latest vehicle arrival data and vehicle information prediction values.

2. The real-time monitoring method for logistics vehicles according to claim 1, characterized in that: The acquisition of real-time vehicle data and enterprise system-related data to update local data specifically includes: using a polling algorithm to regularly acquire real-time vehicle data at set time intervals; Clean and preprocess real-time data to obtain preprocessed data, and update local data based on the preprocessed data; Obtain enterprise system-related data, use incremental synchronization algorithm, and update local data based on enterprise system-related data.

3. The real-time monitoring method for logistics vehicles according to claim 1, characterized in that: The method uses multiple models to extract and count the local data in the most recent period to obtain statistical data, specifically including: Build a sliding window model, set the time window of the sliding window model, and use the sliding window model to extract the most recent data from the local data; Using a counting model, the departure data is counted based on the data of the most recent period; A double-count model is used to calculate the expected arrival data and actual arrival data based on the data of the most recent period; The data of the most recent period, the departure data, the expected arrival data and the actual arrival data are aggregated to obtain statistical data.

4. The real-time monitoring method for logistics vehicles according to claim 1, characterized in that: The method of assigning weights to the data at different times in the statistical data to obtain adjusted data, and using a time series analysis model to calculate the vehicle information prediction value based on the adjusted data specifically includes: Using the weighted average algorithm, weights are assigned to the data at different times in the statistical data to obtain adjusted data; The autoregressive integral moving average model is used to predict the number of vehicles and tonnage distributed in the future time period based on the adjusted data to obtain the prediction results; The actual arrival data of the vehicle is obtained, and the actual arrival data of the vehicle is compared with the predicted result to obtain the deviation result. The feedback control algorithm is used to adjust the parameters of the autoregressive integral moving average model according to the deviation result.

5. The real-time monitoring method for logistics vehicles according to claim 1, characterized in that: The method of obtaining the latest vehicle arrival data and using the early warning model to determine and issue an early warning for vehicle timeouts based on the latest vehicle arrival data and vehicle information prediction values specifically includes: Build an early warning model and set the timeout judgment rules in the early warning model; Adopting an adaptive threshold algorithm, the trigger conditions in the timeout judgment rule are adjusted based on statistical data and historical data; Input the latest vehicle arrival data and vehicle information prediction value into the early warning model to obtain comparison results, and match the comparison results with the timeout judgment rules; When the comparison result meets the triggering conditions in the timeout determination rule, the vehicle is determined to have timed out and an early warning is issued.

6. The method for real-time monitoring of logistics vehicles according to claim 5, characterized in that: The adaptive threshold algorithm is used to adjust the triggering conditions in the timeout determination rule based on historical vehicle data, specifically including: Acquire historical vehicle data, including the vehicle's departure station, arrival station, departure time, arrival time, and travel route; calculate historical transportation time based on the departure time and arrival time; generate a warning threshold based on the historical transportation time; and aggregate the historical vehicle data and the warning threshold to form a vehicle transportation dataset; Extract the vehicle's latest departure station, departure time, and current location from statistical data, and obtain the vehicle's planned driving route; An adaptive threshold algorithm is used to match the vehicle's latest departure station, departure time, current location, and planned driving route with the vehicle transportation dataset to obtain the warning threshold, and the warning threshold in the timeout judgment rule is adjusted.

7. The method for real-time monitoring of logistics vehicles according to claim 5, characterized in that: When the comparison result satisfies the triggering condition in the timeout determination rule, it is determined that the vehicle has timed out and an early warning is issued, specifically including: Set up early warning processing strategies and classify early warning levels based on vehicle overtime duration; The warning levels include level one, level two and level three, and response measures are formulated according to the warning levels; When the comparison result meets the trigger conditions in the timeout judgment rule, the vehicle is judged to have timed out, the vehicle timeout duration is matched with the warning processing strategy, and the corresponding response measures are executed.

8. A real-time monitoring device for logistics vehicles, characterized in that: include: Data update module, used to obtain real-time data of vehicles and relevant data of enterprise systems to update local data; The statistical module is used to extract and count the local data in the most recent period using multiple models to obtain statistical data; The prediction module is used to assign weights to the data at different times in the statistical data to obtain adjusted data, and use the time series analysis model to calculate the vehicle information prediction value based on the adjusted data; The early warning module is used to obtain the latest vehicle arrival data and adopt an early warning model to judge and issue early warnings on vehicle timeouts based on the latest vehicle arrival data and vehicle information prediction values.

9. A real-time monitoring device for logistics vehicles, characterized in that: It includes a memory and at least one processor, wherein the memory stores computer-readable instructions; the at least one processor calls the computer-readable instructions in the memory to execute the various steps of the real-time monitoring method for logistics vehicles as described in any one of claims 1-7.

10. A computer-readable storage medium having computer-readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, the various steps of the real-time monitoring method for logistics vehicles as described in any one of claims 1 to 7 are implemented.

Images