In-transit monitoring management method and system for logistics transportation

Abstract

The invention relates to the technical field of data processing, in particular to an in-transit monitoring management method and system for logistics transportation, and the method comprises the steps: taking a mean value of adjacent data of any data in a vehicle speed data sequence as an ideal value of the data, calculating the noise intensity of the data, and correcting the noise intensity, the noise intensity represents the difference between the data and the ideal value, screening the corrected data with relatively low noise degree from the adjacent data of the preset filtering window of the data, adding the data into the filtering window to obtain the filtering window updated for the first time, and repeating the updating process on the basis of the updated filtering window, and calculating the optimization degree of the filtering window updated each time, performing mean filtering on the data by using the filtering window of which the optimization degree meets a preset screening condition, and monitoring the transportation process based on the filtered data. According to the invention, the accuracy of the filtered vehicle speed data is ensured, and accurate monitoring of the logistics transportation process can be realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing. More particularly, the present application relates to a method and system for in-transit monitoring and management of logistics transportation. BACKGROUND

[0002] In logistics transportation, transportation safety and process monitoring have become an important trend of development, and monitoring the speed of logistics vehicles is a key link. By monitoring the speed of the vehicle in real time, the progress of the transportation task can be intuitively understood, and the arrival time of the vehicle can be predicted; at the same time, real-time monitoring can also be used to detect speed abnormalities, thereby ensuring transportation safety. In order to accurately monitor the logistics transportation process, the collected speed data needs to be cleaned. As a commonly used and simple and effective filtering method, mean filtering can effectively process the speed data collected in the logistics transportation process, achieving good data cleaning effect.

[0003] In related technologies, such as the patent application file with publication number CN116643951A, a cold-chain logistics transportation big data monitoring and collecting method is disclosed, which includes: through two-dimensional coordinate system conversion of the initial temperature data sequence and the temperature data sequence, the first temperature abnormal reference value and the second temperature abnormal reference value of each collection period are obtained, the collection period with temperature abnormality is obtained according to the first temperature abnormal reference value and the second temperature abnormal reference value, and the abnormal sensor is obtained and adjusted and replaced.

[0004] In related technologies, the influence of noise is not fully considered when determining abnormal data, which may cause deviation in the accuracy judgment of abnormal sensors, so that the abnormal sensors cannot be correctly replaced. The accuracy of data collected based on the replaced sensors is low, which further affects the monitoring effect of the logistics transportation process. SUMMARY

[0005] In order to solve the problem that the logistics transportation process cannot be accurately monitored due to low data accuracy, the present application provides a method and system for in-transit monitoring and management of logistics transportation.

[0006] According to a first aspect of the present application, a method for in-transit monitoring and management of logistics transportation is provided, comprising: obtaining a speed data sequence of a vehicle in a logistics transportation process; taking the mean value of the adjacent data of any data in the speed data sequence as the ideal value of the data, calculating the noise intensity of the data, the noise intensity representing the difference between the data and the ideal value, correcting the noise intensity using the average noise intensity of the data within the preset neighborhood range, and the correction value is the normalized value of the product of the average noise intensity and the noise intensity; From the adjacent data of the preset filter window of the data, data with a smaller corrected noise degree is screened and added to the filter window to obtain a first updated filter window, and the updating process is repeated based on the updated filter window, the preference degree of the filter window updated each time is calculated, the filter window with the preference degree meeting the preset screening condition is used for mean filtering of the data, and the transportation process is monitored based on the filtered data; Preference degree: is the preference degree of the filter window updated for the first time; is the preference degree of the filter window updated for the first time; is the corrected noise intensity of the first data; is the corrected noise intensity of the first data; is the corrected noise intensity of all data in the filter window updated for the first time except the first data; is the corrected noise intensity of all data in the filter window updated for the first time except the first data.

[0007] The application can adaptively adjust the position and size of the filter window when the vehicle speed data is subjected to mean filtering, so that the under-filtering and over-filtering in the traditional mean filtering using a filter window with a fixed position and size can be avoided, the accuracy of the filtered vehicle speed data is ensured, and the accurate monitoring of the logistics transportation process can be realized based on the vehicle speed data with high accuracy.

[0008] Preferably, the noise intensity of the data is calculated, including: the difference between any data in the vehicle speed data sequence and the ideal value of the data is taken as the abruptness of the data; the standard deviation of the data in the neighborhood range is used to calculate the credibility of the abruptness, the credibility is negatively correlated with the standard deviation, the credibility is taken as a weight to weight the abruptness, and the noise intensity of the data is obtained.

[0009] The application can exclude the influence of normal data in a local range which is similar to the noise change due to normal fluctuations.

[0010] Preferably, the difference is obtained by: calculating the absolute value of the difference between any data in the vehicle speed data sequence and the ideal value of the data to obtain the difference between the data and the ideal value of the data.

[0011] The application can accurately evaluate the degree of deviation of each data in the vehicle speed data sequence from the normal change trend in a local range, so as to obtain the abruptness of the corresponding data in the local range.

[0012] Preferably, the credibility satisfies the following relationship: In the formula,​​​ For the first The credibility of the mutability of individual data; For the first The standard deviation of data within the neighborhood of each data point; It is a natural exponential function.

[0013] Preferred methods for obtaining the neighborhood range include: Taking any data point in the vehicle speed data sequence as the center, select a data segment containing a preset number of data points to obtain the neighborhood range of that data point.

[0014] Preferably, the noise intensity is corrected using the average noise intensity of data within a preset neighborhood range of the data, satisfying the following relationship: ; In the formula, For the first The noise intensity after data correction; For the first Noise intensity of each data point; For the first Within the neighborhood of the data, the first Noise intensity of each data point; For the first The amount of data within the neighborhood of each data point; It is the hyperbolic tangent function.

[0015] This invention can eliminate the possibility that data may have high noise levels due to sudden braking or acceleration of the vehicle, thereby enabling accurate assessment of the likelihood that each data point is noise.

[0016] Preferably, the mean filter is applied to any data using a filter window whose preference meets the preset screening criteria, including: The filter window that meets the preset screening criteria is used as the target window. The average value of all data in the target window is used to replace any data to perform mean filtering on any data.

[0017] This invention avoids the filtering and under-filtering issues that occur when performing mean filtering on vehicle speed data, thus ensuring the accuracy of the filtered vehicle speed data.

[0018] According to a second aspect of the present invention, an in-transit monitoring and management system for logistics transportation is provided, the system including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the first aspect of the present invention.

[0019] The present invention has the following effects: 1. When performing mean filtering on vehicle speed data, this invention can adaptively adjust the position and size of the filtering window, which can avoid under-filtering and filtering wave phenomena that exist when performing mean filtering on vehicle speed data, ensuring the accuracy of the filtered vehicle speed data, thereby achieving accurate monitoring of the logistics transportation process.

[0020] 2. The optimization degree of the updated filter window calculated by the present invention can accurately evaluate the filtering effect when the corresponding data is mean filtered with the data in the corresponding filter window, so as to accurately select the best filter window when mean filtering each data, and ensure the accuracy of the adaptive filter window.

[0021] 3. This invention integrates data from multiple sources to calculate the corrected noise intensity of each data point in the vehicle speed data sequence, and can accurately assess the possibility that the vehicle speed data is noise. Attached Figure Description

[0022] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings. In the drawings, several embodiments of the invention are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts, wherein: Figure 1 This is a flowchart illustrating the steps of an embodiment of the present invention for an in-transit monitoring and management method for logistics transportation. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0025] Reference Figure 1 A method for in-transit monitoring and management of logistics transportation, comprising steps S1-S4, as detailed below: S1: Obtain vehicle speed data sequences during logistics transportation.

[0026] Specifically, a vehicle speed sensor can be installed at a suitable location on the vehicle. Then, during the logistics transportation process, the readings of the vehicle speed sensor can be collected at a certain frequency, such as 1Hz, to obtain a sequence of vehicle speed data during the logistics transportation process. This embodiment does not impose any special limitation on the data collection frequency.

[0027] S2: the noise intensity of any data in the vehicle speed data sequence is calculated by taking the mean value of the adjacent data of the data as the ideal value of the data, the noise intensity representing the difference between the data and the ideal value.

[0028] It should be noted that in the logistics transportation process, the vehicle will be affected by the road conditions, and may appear the phenomenon of jolt, when the vehicle jolt, the vehicle speed sensor may be subjected to physical impact, thereby causing the noise in the collected vehicle speed data. The noise usually appears as a mutation point in a local range, and the ideal value of the data is determined by the linear interpolation method, which can reflect the value or the predicted local change trend of the corresponding data, therefore, the difference between the true value and the ideal value of the corresponding data is calculated, the degree of deviation of the corresponding data from the normal change trend in the local range is evaluated, and the noise intensity of the corresponding data is obtained.

[0029] In an example embodiment of the present application, the determination of the noise intensity of any data in the vehicle speed data sequence can be achieved by the following steps: Step one: the difference between any data in the vehicle speed data sequence and the ideal value of the data is taken as the mutation of the data. In an example embodiment of the present application, the determination of the difference between any data in the vehicle speed data sequence and the ideal value of the data can be achieved by the following steps: The absolute value of the difference between any data in the vehicle speed data sequence and the ideal value of the data is calculated to obtain the difference between the data and the ideal value of the data.

[0030] Alternatively, the ratio between any data in the vehicle speed data sequence and the ideal value of the data can also be calculated to obtain the difference between the data and the ideal value of the data, and the determination method of the difference between the data is not particularly limited in this embodiment.

[0031] Step two: the credibility of the mutation is calculated by using the standard deviation of the data in the neighborhood range of the data, the credibility is negatively correlated with the standard deviation, the credibility is taken as the weight to weight the mutation, and the noise intensity of the data is obtained.

[0032] Specifically, the credibility of the mutation of any data in the vehicle speed data sequence satisfies the following relationship: ; In the formula, is the credibility of the mutation of the first data; is the credibility of the mutation of the first data; is the standard deviation of the data in the neighborhood range of the first data; is the standard deviation of the data in the neighborhood range of the first data; is the natural exponential function, wherein the natural exponential function is an exponential function with a natural constant as the base.

[0033] Among them, when When the value is small, it indicates that the data fluctuations within the neighborhood are relatively stable. Therefore, if the data shows a large variability, the cause of this variability is more likely to be noise, and the reliability of the variability is relatively high. Conversely, when... A large value indicates that the data fluctuations within the neighborhood of the data are relatively drastic. Therefore, when it is determined that the data has a large variability, the reason for the large variability is more likely to be normal data fluctuation, and the reliability of the variability of the data is relatively low.

[0034] In another embodiment, the negative or reciprocal of the standard deviation of data within the neighborhood of any given data can be used as the confidence level of the data's mutability.

[0035] Furthermore, once the mutability of any data point and the reliability of that mutability are determined, the noise intensity of that data can be calculated. Specifically, the noise intensity of any data point in the vehicle speed data sequence satisfies the following relationship: ; In the formula, For the first The noise level of each data point; , as well as The first The value of the first data point, the first The value of the data and the first data +1 data value; For the first The standard deviation of data within the neighborhood of each data point; It is the absolute value symbol.

[0036] in, Reflects the first The ideal value for each data point; Reflects the first The larger the difference between the true and ideal values ​​of a data point, the greater the variability of the data and the greater the corresponding noise intensity. Reflects the first The higher the value, the greater the reliability of the mutability of the data.

[0037] In one exemplary embodiment of the present invention, the neighborhood range of any data in the vehicle speed data sequence can be determined through the following steps: Taking any data point in the vehicle speed data sequence as the center, select a data segment containing a preset number of data points to obtain the neighborhood range of that data point.

[0038] Optionally, the preset value can be recorded as When the amount of data on either side of any data point in the vehicle speed data sequence is less than If so, discard the data from that side and combine it with the data from the other side. A data segment consisting of several data points is used as the neighborhood range of that data. In this embodiment... =3, This embodiment does not impose any special limitation on the amount of data contained within the neighborhood range.

[0039] S3: Using the average noise intensity of the data within the preset neighborhood range, the noise intensity is corrected. The correction value is the normalized value of the product of the average noise intensity and the noise intensity.

[0040] It should be noted that during logistics transportation, sudden braking or acceleration may occur, leading to significant abrupt changes in vehicle speed data at corresponding moments. This results in normal data containing extremely high noise levels, necessitating correction for the calculated noise intensity. Road conditions causing vehicle bumps can also cause vehicle vibrations, during which speed data is typically subject to continuous noise interference. Furthermore, sudden braking or acceleration causing abrupt changes in speed data is often instantaneous. Therefore, this invention, based on this characteristic, corrects the noise intensity of corresponding data by assessing the overall noise level within a neighborhood range, thereby avoiding excessive noise in normal data and accurately assessing the likelihood of data being noise.

[0041] Specifically, the noise intensity after correction for any data point in the vehicle speed data sequence satisfies the following relationship: ; In the formula, For the first The noise intensity after data correction; For the first Noise intensity of each data point; For the first Within the neighborhood of the data, the first Noise intensity of each data point; For the first The amount of data within the neighborhood of each data point; It is the hyperbolic tangent function.

[0042] in, Reflects the first The larger the value, the higher the overall noise level of the data in the neighborhood of the data, indicating that the data is more likely to be noise, and the corresponding noise intensity after correction is relatively large.

[0043] Optionally, when the average noise intensity in the neighborhood range of any data point is small, it indicates that the overall noise level of the data in the neighborhood range is low; if the noise intensity of the any data is large at this time, it indicates that the reason for the large noise intensity of the any data is that the vehicle is suddenly braking or accelerating, and thus the noise intensity of the data needs to be reduced, so as to avoid that the normal data has a large noise intensity and ensure that the possibility of each data in the vehicle speed data sequence being noise can be accurately evaluated.

[0044] In another embodiment, the function of is normalized, and the present embodiment does not particularly limit the way of normalization.

[0045] S4: From the adjacent data of the preset filter window of the data, data with a smaller corrected noise degree is selected and added to the filter window to obtain a first updated filter window, and the updating process is repeated based on the updated filter window, the preference degree of each updated filter window is calculated, the filter window satisfying the preset screening condition by using the preference degree is used to perform mean filtering on the data, and the transportation process is monitored based on the filtered data.

[0046] It should be noted that mean filtering is a commonly used and simple and effective filtering method, and has good effect on data cleaning. However, due to the uncertainty of the environment faced by the logistics vehicle in the driving process, the position and intensity of the noise also often show uncertainty. The traditional mean filtering is to filter the data by using a filter window with fixed position and size, which is difficult to adapt to such changes, resulting in the possibility of over-filtering or under-filtering in the filtering result, affecting the effect of data cleaning. Therefore, the present application improves the traditional mean filtering algorithm, and the specific improvement contents are as follows: the filter window of each data is preset, then the filter window of each data is iteratively updated, and the preference degree of each updated filter window is calculated, so as to use the filter window with the preference degree meeting the preset screening condition to filter the corresponding data.

[0047] It should be further noted that when any data in the vehicle speed data sequence is filtered by using the improved mean filter, if the overall noise intensity of the data in the current filter window except the any data is low, it indicates that the number of real data existing in the current filter window is relatively large, and the preference degree of the current filter window is relatively high. At the same time, if the noise intensity of the any data is low, it indicates that the any data does not need to be filtered by using additional data, and the preference degree of the filter window of the data is relatively high.

[0048] Specifically, the preference degree of the filter window of the any data after each update satisfies the following relationship: ;​ wherein, is the preferred degree of the first updated filter window; is the preferred degree of the first updated filter window; is the noise intensity of the first data in the data sequence; is the noise intensity of the first data in the data sequence; is the noise intensity of the first data in the data sequence; is the noise intensity of the first data in the data sequence; is the average of the noise intensities of all data in the first updated filter window except the first data.

[0049] Next, taking the filtering of the first data in the vehicle speed data sequence as an example, the filtering process of the present application is described in detail: First, the filter window of the first data in the vehicle speed data sequence is preset, and in this embodiment, the preset filter window of each data is a window containing only the corresponding data. Of course, a suitable preset filter window can also be set according to specific conditions, and the size of the preset filter window in this embodiment is not particularly limited. Then, from the adjacent data in the preset filter window, the data with a smaller corrected noise intensity is selected and added to the preset filter window to obtain the first updated filter window, and the preferred degree of the first updated filter window is calculated, denoted as

[0050] After that, the process of adding data is repeated to obtain each updated filter window, and the preferred degree of each updated filter window is calculated, and when is greater than , and is greater than , it is determined that the preferred degree of the first updated filter window meets the preset screening condition, and the first updated filter window is used to perform mean filtering on the first data in the vehicle speed data sequence. In an example embodiment of the present application, the mean filtering of data can be achieved by the following steps: The filter window whose preferred degree meets the preset screening condition is used as a target window, and the average value of all data in the target window is used to replace any data to perform mean filtering on any data.

[0051] In an example embodiment of the present application, the mean filtering of data can be achieved by the following steps: The filter window whose preferred degree meets the preset screening condition is used as a target window, and the average value of all data in the target window is used to replace any data to perform mean filtering on any data.

[0052] ​​​​Further, each data in the vehicle speed data sequence can be mean filtered based on steps S2-S4, data cleaning is completed, then the system can determine the arrival time when the vehicle travels at the corresponding vehicle speed according to the cleaned vehicle speed data, so that the logistics transportation process can be monitored, and whether the vehicle has abnormal behaviors such as overspeed at the corresponding time can be judged based on the cleaned vehicle speed data, so as to timely remind the driver to pay attention to speed reduction, thereby improving the safety of logistics transportation.

[0053] The application further provides an in-transit monitoring and management system for logistics transportation, which comprises a memory and a processor, and the memory stores a computer program, the computer program integrates the functions of the in-transit monitoring and management method for logistics transportation, and when the computer program is executed, the accuracy of the filtered vehicle speed data is ensured by the in-transit monitoring and management method for logistics transportation, and accurate monitoring of the logistics transportation process can be realized.

[0054] In the description of the present specification, the meaning of "a plurality of", "several" is at least two, for example, two, three or more, etc., unless otherwise explicitly specifically limited.

[0055] Although the present specification has shown and described several embodiments of the present application, it will be apparent to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, changes and alternatives without departing from the idea and spirit of the present application. It should be understood that various alternatives to the embodiments of the present application described herein can be employed in practicing the present application.

Claims

1. A method for in-transit monitoring and management of logistics transportation, characterized in that, The method comprises the following steps: obtaining a vehicle speed data sequence of a vehicle during a logistics transportation process; calculating a noise intensity of any data in the vehicle speed data sequence, wherein the noise intensity represents a difference between the data and an ideal value of the data, the ideal value being a mean value of adjacent data of the data, and the noise intensity is corrected by using an average noise intensity of data within a preset neighborhood range of the data, and the correction value is a normalized value of a product of the average noise intensity and the noise intensity; selecting data with a smaller corrected noise intensity from adjacent data of a preset filter window of the data to add to the filter window to obtain a first updated filter window, and repeating the updating process based on the updated filter window to calculate a preference degree of the updated filter window, and using a filter window with a preference degree satisfying a preset screening condition to perform mean value filtering on the data, and monitoring the transportation process based on the filtered data; the degree of preference ; the degree of preference of the filter window after the first update the degree of preference of the noise intensity after the data correction the degree of preference of the average of the noise intensities of all data in the filter window after the second update, except for the data after the data correction 2. A method for in-transit monitoring and management of logistics shipments as claimed in claim 1 wherein, the calculation of the noise intensity of the data comprises: using a difference between any data in the vehicle speed data sequence and the ideal value of the data as a mutation of the data; calculating a credibility of the mutation by using a standard deviation of data within a neighborhood range of the data, wherein the credibility is negatively correlated with the standard deviation, and the noise intensity of the data is obtained by weighting the mutation by using the credibility as a weight.

3. A method for in-transit monitoring and management of logistics shipments as claimed in claim 2 wherein, the method for obtaining the difference comprises: calculating an absolute value of a difference between any data in the vehicle speed data sequence and the ideal value of the data to obtain the difference between the data and the ideal value of the data.

4. A method for in-transit monitoring and management of logistics shipments as claimed in claim 2 wherein, the credibility satisfies the following relationship: ； wherein is the confidence of the mutation of the th data; is the standard deviation of the data in the neighborhood of the th data; is the natural exponential function.

5. A method for in-transit monitoring and management of logistics shipments as claimed in claim 4 wherein, the method for obtaining the neighborhood range comprises: selecting a data segment containing a preset number of data with the data in the vehicle speed data sequence as a center to obtain the neighborhood range of the data.

6. The method for in-transit monitoring and management of logistic transportation of claim 1, wherein, the correction of the noise intensity by using the average noise intensity of data within the preset neighborhood range of the data satisfies the following relationship: ； In the formula, is the noise intensity of the first data; is the noise intensity of the first data; is the noise intensity of the first data; is the noise intensity of the first data; is the noise intensity of the first data; is the noise intensity of the first data; is the noise intensity of the first data; is the data amount within the neighborhood range of the first data; is the data amount within the neighborhood range of the first data; is the hyperbolic tangent function.

7. The method for in-transit monitoring and management of logistic transportation of claim 1, wherein, the mean value filtering of the data by using the filter window with the preference degree satisfying the preset screening condition comprises: using the filter window with the preference degree satisfying the preset screening condition as a target window, and replacing the data by using an average value of all data in the target window to perform mean value filtering on the data.

8. An in-transit monitoring management system for logistics transportation, characterized by, The in-transit monitoring and management system for logistics transportation comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the steps of the in-transit monitoring and management method for logistics transportation according to any one of claims 1-7.

Images