Vehicle loading behavior detection method, system and terminal based on median property

Abstract

The invention provides a median property-based vehicle loading behavior detection method, system and terminal, and particularly relates to the technical field of data processing, and the scheme comprises the steps of detecting sensing data of a target monitoring point on a vehicle in a loading process; based on a preset sliding window, processing the sensing data by using a median property to obtain a pressure median value in each sliding window; based on all the pressure median values, a vehicle loading behavior is determined. According to the scheme, the sensing data is processed by utilizing the denoising property of the median, so that the anti-interference performance of the sensing data can be remarkably improved, and the accuracy of the judgment result of the vehicle loading behavior can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a vehicle loading behavior detection method, system and terminal based on the median property. Background Art

[0002] Currently, most vehicle loading behavior detection methods identify the loading behavior of a vehicle by detecting the sensing data information installed at different positions of the vehicle or the weight information of the vehicle and the container. For example, an unlocking sensor is used to detect the unlocking signal or locking signal of the container lock to control the loading and unloading of the vehicle, and sensors are used to detect the weight or height information in the loading and unloading area to identify the whole-vehicle loading and unloading behavior of the container; or, based on the electronic fence information, vehicle information, and the loading information of the container detected by sensors, the whole-vehicle loading behavior of the container is identified, where the loading information includes the weight of the loaded container, loading and unloading box positioning, and box number identification.

[0003] However, in the process of using sensors to measure data, these methods are often interfered by electromagnetic signals, resulting in noise in the sensing data and inaccurate sensing data, thus causing inaccurate identification of the vehicle loading and unloading behavior. Summary of the Invention

[0004] In view of the above deficiencies of the prior art, the purpose of the present invention is to provide a vehicle loading behavior detection method, system and terminal based on the median property, aiming to solve the problem of inaccurate identification of vehicle loading and unloading behavior in the prior art.

[0005] To achieve the above purpose, the first aspect of the present invention provides a vehicle loading behavior detection method based on the median property, including:

[0006] Detecting the sensing data of the target monitoring points on the vehicle during the loading process;

[0007] Based on a preset sliding window, using the median property to process the sensing data to obtain the pressure median value within each sliding window;

[0008] Based on all the pressure median values, determining the vehicle loading behavior.

[0009] Optionally, the detecting the sensing data of the target monitoring points on the vehicle during the loading process includes:

[0010] Detecting the sensing data of each target monitoring point on the vehicle during the loading process according to a preset detection frequency to obtain a series of sensing data corresponding to each target monitoring point;

[0011] Based on the sensing data of all the target monitoring points, obtaining the sensing data of the vehicle during the loading process.

[0012] Optionally, based on a preset sliding window, the sensing data is processed using the median property to obtain the median pressure value within each sliding window, including:

[0013] The time period corresponding to the loading process is segmented based on a preset sliding window to obtain a number of time segments;

[0014] Calculate the median of the sensing data within each of the time segments to obtain the median pressure value within each sliding window.

[0015] Optionally, based on all the median pressure values, determining the vehicle loading behavior includes:

[0016] Calculate the difference between the median pressure values of adjacent time segments to obtain the pressure change value between adjacent time segments;

[0017] Based on the pressure change values of each of the adjacent time segments, determine the vehicle loading behavior.

[0018] Optionally, based on the pressure change values of every two adjacent time segments, determining the vehicle loading behavior includes:

[0019] If the pressure change value between any two adjacent time segments is negative and the absolute value of the pressure change value is greater than a preset first pressure change threshold, determine that the vehicle loading behavior is container lifting;

[0020] If the pressure change value between any two adjacent time segments is positive and the pressure change value is greater than a preset second pressure change threshold, determine that the vehicle loading behavior is container returning;

[0021] If the proportion of negative numbers among the pressure change values of all adjacent time segments is greater than a preset first negative proportion threshold, determine that the vehicle loading behavior is starting to load goods;

[0022] If the proportion of negative numbers among the pressure change values of all adjacent time segments is equal to a preset second negative proportion threshold, determine that the vehicle loading behavior is ending the loading of goods.

[0023] Optionally, the first pressure change threshold, the second pressure change threshold, the first negative proportion threshold, and the second negative proportion threshold are set based on the type of goods loaded on the vehicle and the historical pressure data of the target monitoring point on the detected vehicle.

[0024] A second aspect of the present invention provides a vehicle loading behavior detection system based on the median property, the system including:

[0025] A data acquisition module for detecting the sensing data of the target monitoring point on the vehicle during the loading process;

[0026] A data processing module, configured to process the sensing data based on a preset sliding window and using the median property to obtain the median pressure value within each sliding window.

[0027] A vehicle loading behavior determination module, configured to determine the vehicle loading behavior based on all the median pressure values.

[0028] In a third aspect of the present invention, there is provided an intelligent terminal, which includes a memory, a processor, and a vehicle loading behavior detection program based on the median property stored on the memory and executable on the processor. When the vehicle loading behavior detection program based on the median property is executed by the processor, it implements the steps of any one of the above-mentioned vehicle loading behavior detection methods based on the median property.

[0029] In a fourth aspect of the present invention, there is provided a computer-readable storage medium, on which a vehicle loading behavior detection program based on the median property is stored. When the vehicle loading behavior detection program based on the median property is executed by a processor, it implements the steps of any one of the above-mentioned vehicle loading behavior detection methods based on the median property.

[0030] Compared with the prior art, the beneficial effects of the present solution are as follows:

[0031] The present invention uses sensors to detect the sensing data during the vehicle loading process, processes the sensing data using the property of the median to denoise, obtains the median of several sensing data, can significantly improve the anti-interference ability of the sensing data, and converts the median of the sensing data into load pressure data, which can effectively improve the accuracy of the determination result of the vehicle loading behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0033] Figure 1 It is a flowchart of the vehicle loading behavior detection method based on the median property of the present invention;

[0034] Figure 2 It is a schematic diagram of the module of the vehicle loading behavior detection system based on the median property of the present invention;

[0035] Figure 3 It is a schematic diagram of the structure of the intelligent terminal of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] In the following description, specific details such as specific system architectures, technologies, etc. are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0037] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or their combinations.

[0038] It should also be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0039] It should be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0040] As used in this specification and the appended claims, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" depending on the context. Similarly, the phrases "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" depending on the context.

[0041] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0042] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0043] In view of the problem of inaccurate recognition of vehicle loading and unloading behaviors in the prior art, the present invention proposes a vehicle loading behavior detection method based on the median property. Specifically, it uses sensors to detect sensing data during the vehicle loading process, and utilizes the noise reduction property of the median to process the sensing data to obtain the median of a number of sensing data, which can significantly improve the anti-interference ability of the sensing data. Then, it converts the median of the sensing data into load pressure data, which can effectively improve the accuracy of the determination result of the vehicle loading behavior.

[0044] An embodiment of the present invention provides a vehicle loading behavior detection method based on the median property, which is deployed on electronic devices such as computers and servers and is applied to the scenario of loading and unloading goods from vehicles, aiming at detecting the vehicle loading behavior. The type of the above vehicle is not limited and can be any vehicle that can load goods. Specifically, as Figure 1 shown, the steps of the method in this embodiment include:

[0045] Step S100: Detect the sensing data of the target monitoring point on the vehicle during the loading process;

[0046] Specifically, considering that when loading a vehicle, the vehicle frame will deform due to the vehicle load and the degree of deformation will increase with the increase of the load, resulting in a change in the distance between the vehicle frame and the rear suspension. Therefore, in this embodiment, according to the vehicle type, cargo type, and the loading area to be monitored, the target monitoring point is determined. For example, the target monitoring point is set on the carriage floor, cargo support frame, vehicle frame, etc., and the sensor is installed on the target monitoring point to detect the sensing data of the target monitoring point on the vehicle during the loading process, ensuring that the sensor is in close contact with the monitoring surface and can accurately reflect the pressure change at this position.

[0047] As an exemplary example, in this example, a ranging sensor is installed by setting a number of target monitoring points at the position of the vehicle frame opposite to the rear suspension, or a pressure sensor for measuring the vehicle load is installed by setting a number of target monitoring points on the frame. During the loading process, the load of the vehicle changes with the processes of lifting the container, loading the goods, and returning the container. Then, the deformation degree of the frame changes accordingly, resulting in a change in the distance between the frame and the rear suspension, and the signals received by the sensors also change accordingly. Therefore, the analog signals of the distance between the frame and the rear suspension are received by all the ranging sensors, or the analog signals of the vehicle load are received by all the pressure sensors to obtain sensing data. Among them, lifting the container refers to the act of placing one or more empty containers for loading goods on the frame at the same time using devices such as a jib, and a sudden increase in weight can be observed; loading the goods refers to the act of workers carrying multiple goods into the container one by one, and multiple and continuous weight increases can be observed. Among them, loading the goods includes two key detection points of the loading behavior, namely starting to load the goods and ending to load the goods; returning the container refers to the act of using devices such as a jib to return one or more containers loaded with goods on the frame to a designated location (such as a container yard, a wharf, etc.) at the same time, and a sudden decrease in weight can be observed. Further, sensors for object detection can be used to identify the types of containers and goods to be loaded to assist in identifying the behaviors of lifting the container, loading the goods, and returning the container.

[0048] It is easy to understand that in this embodiment, a process of lifting the container, loading the goods, and returning the container represents a loading process. In fact, a complete loading process may include one or more processes of lifting the container, loading the goods, and returning the container, and the judgment methods of the loading behaviors in each process of lifting the container, loading the goods, and returning the container are the same. At the same time, if the single-piece weights of the loaded goods are different, or the loading methods are different, the changes in the vehicle loading state monitored during the loading process will be different.

[0049] Step S200: Based on a preset sliding window, use the median property to process the sensing data to obtain the median pressure value within each sliding window;

[0050] Specifically, in vehicle loading behavior detection, sensing data may be interfered by various factors, such as electromagnetic interference, resulting in noisy data. For a set of data containing noise (outliers), since the median selects the middle value of the set of data and is not easily affected by extreme values, it can reflect the middle level of the set of data and the central tendency of the data, thus achieving the effect of removing noise. Based on this, in this embodiment, for a series of sensing data within several preset time periods during the vehicle loading process, by sorting this series of sensing data and determining the median, the median of the sensing data is obtained, and then the median of the sensing data is converted into the load pressure data of the vehicle's loaded goods through data conversion, thereby obtaining the median value of the load pressure data to capture the general change of the load pressure data and avoid errors caused by local noise fluctuations, so as to obtain data changes related to the actual loading behavior. Among them, the preset time period refers to a relatively short period of time during the entire vehicle loading process that contains at least one moment when the sensing data changes.

[0051] Step S300: Determine the vehicle loading behavior based on all the median pressure values.

[0052] Specifically, first, according to the vehicle type, load capacity, and characteristics of the loaded goods, set the range of the median pressure value so that this range should be able to accurately reflect the normal pressure level of the vehicle under different loading states and ensure that the loading process complies with the vehicle's loading specifications; and set a safety threshold. When there is a median pressure value exceeding this threshold, it is considered that there may be a safety hazard in the vehicle's loading behavior. Then, compare each median pressure value with the range of the median pressure value and / or the safety threshold. If all the median pressure values are within the safe range and comply with the vehicle's loading specifications, then it is determined that the vehicle's loading behavior is safe and reasonable, thus accurately determining the vehicle loading behavior; if it is monitored that a certain median pressure value exceeds the safety threshold or does not conform to the vehicle's loading specifications, a warning prompt is issued to check the vehicle's loading situation in a timely manner to eliminate potential safety hazards, and the corresponding median pressure value is deleted.

[0053] In this embodiment, sensors are used to detect the sensing data during the vehicle loading process, and the property of the median to denoise is used to process the sensing data to obtain the median of several sensing data, which can significantly improve the anti-interference ability of the sensing data, and convert the median of the sensing data into the load pressure data, which can effectively improve the accuracy of the determination result of the vehicle loading behavior.

[0054] In a preferred embodiment, detecting the sensing data of the target monitoring point on the vehicle during the loading process in step S100 includes:

[0055] Step S110: Detect the sensing data of each target monitoring point on the vehicle during the loading process according to a preset detection frequency, and obtain a series of sensing data corresponding to each target monitoring point;

[0056] Step S120: Based on the sensing data of all the target monitoring points, obtain the sensing data of the vehicle during the loading process.

[0057] Specifically, according to the actual loading requirements, preset the detection frequency, which can accurately reflect the changes in the load and vehicle state during the loading process; detect the sensing data of each target monitoring point on the vehicle during the loading process according to the preset detection frequency, and obtain a series of sensing data corresponding to each target monitoring point to obtain the overall sensing data change of the vehicle detected at this target monitoring point during the loading process; organize the sensing data of all target monitoring points at each detection moment to form a structured data set, and perform a weighted summation process on the sensing data of all target monitoring points at the same moment according to the influence degree of different monitoring points on the overall load or vehicle state, and obtain the sensing data corresponding to each detection moment of the vehicle during the loading process.

[0058] In this embodiment, according to the preset detection frequency, detect the sensing data of each target monitoring point on the vehicle during the loading process, and by performing a weighted summation of the sensing data of each target detection point, it can accurately reflect the overall sensing data corresponding to each detection moment of the vehicle during the loading process.

[0059] In a preferred implementation manner, in step S200, based on a preset sliding window, use the median property to process the sensing data to obtain the pressure median value within each sliding window, including:

[0060] Step S210: Based on the preset sliding window, divide the time period corresponding to the loading process to obtain several time segments;

[0061] Step S220: Calculate the median of the sensing data within each time segment to obtain the pressure median value within each sliding window.

[0062] Specifically, according to the data characteristics and analysis requirements of the loading process, determine a suitable sliding window size, such as 5 minutes, 10 minutes, etc.; for the time period corresponding to the entire loading process, starting from the starting moment, initialize a time window with a size of the sliding window size, and gradually move the window backward in units of a preset step size to divide the time period corresponding to the loading process until the time period covering the entire loading process is obtained, and several time segments are obtained. Among them, the step size can be set to be the same as the window size (i.e., non-overlapping), or can be set to be smaller than the window size (i.e., overlapping), and is specifically set according to the analysis requirements and data characteristics.

[0063] For each time segment, extract the sensing data of all target monitoring points within that time segment, sort the sensing data within each time segment, and find the value at the middle position after sorting, which is the median of the sensing data within that time segment. If the number of data points is odd, the median is the value at the middle position; if the number of data points is even, the median is the average of the two middle values. Then, convert the median of the sensing data into the load pressure data of the vehicle's loaded goods through data conversion, so as to obtain the median pressure value of the load pressure data, capture the general change of the load pressure data within that time segment, avoid errors caused by local noise fluctuations, and thus obtain the data change related to the actual loading behavior.

[0064] In this embodiment, the time period corresponding to the loading process is segmented based on a preset sliding window, and the median of the sensing data within each time segment is calculated, so as to obtain the median pressure value within each sliding window, providing reliable data support for accurately judging the vehicle loading behavior in each stage later.

[0065] In a preferred embodiment, determining the vehicle loading behavior based on the median pressure value in step S300 includes:

[0066] Step S310: Calculate the difference between the median pressure values of adjacent time segments to obtain the pressure change value of adjacent time segments;

[0067] Step S320: Determine the vehicle loading behavior detection result based on the pressure change values of each adjacent time segment.

[0068] Specifically, since different vehicle loading behaviors are obtained based on the changing trends of sensing data, in this embodiment, the difference in the median pressure values of adjacent time segments is calculated, that is, the difference obtained by subtracting the median pressure value of the previous time segment from the median pressure value of the subsequent time segment, to obtain the pressure change value between adjacent time segments. This pressure change value may be positive or negative. Then, based on the positive or negative nature of the pressure change values of each adjacent time segment and the proportion of positive and negative pressure change values, the vehicle loading behavior detection result is determined. Specifically, it includes: if the pressure change value between any two adjacent time segments is negative and the absolute value of this pressure change value is greater than a preset first pressure change threshold, it is determined that the vehicle loading behavior is container lifting; if the pressure change value between any two adjacent time segments is positive and this pressure change value is greater than a preset second pressure change threshold, it is determined that the vehicle loading behavior is container returning; if the proportion of negative numbers among the pressure change values of all adjacent time segments is greater than a preset first negative proportion threshold, it is determined that the vehicle loading behavior is starting to load goods; if the proportion of negative numbers among the pressure change values of all adjacent time segments is equal to a preset second negative proportion threshold, it is determined that the vehicle loading behavior is ending the loading of goods.

[0069] As an exemplary example, according to the following definition of vehicle loading behavior and the processing method of sensing data according to the median property, the vehicle loading behaviors at each stage corresponding to the entire loading process are obtained, specifically as follows:

[0070] This example defines four key vehicle loading behaviors, namely container lifting, container returning, starting to load goods, and ending the loading of goods, that is:

[0071] The observed time window is represented as T = [t 1 , …, t N , t 1 ≤ … ≤ t N , and the ideal sensing data corresponding to the time points is represented as W = [w 1 , …, w N , where N represents the total number of monitoring time points.

[0072] Container lifting: There exists a certain moment t k , t 1 < t k < t N , where k represents a certain monitoring time point between [1, …, N]; in [t 1 , …, t k , there is w 1 = w 2 =... = w k , indicating that no loading operation occurs at the first k detection points; in [t k+1 , …, t N , there is w k+1 = wk+2 =...= w N , while w k < w k+1 , indicating that an empty container is placed on the chassis at time t k+1 .

[0073] Returning the container: There exists a certain moment t k , t 1 < t k < t N ; in [t 1 ,..., t k , there is w 1 = w 2 =...= w k , indicating that no loading operation occurs at the first k detection points; in [t k+1 ,..., t N , there is w k+1 = w k+2 =...= w N , while w k > w k+1 , indicating that a container full of goods is removed from the chassis at time t k+1 .

[0074] Starting to load: There exists a certain moment t k , t 1 < t k < t N ; in [t 1 ,..., t k , there is w 1 = w 2 =...= w k , indicating that no loading operation occurs at the first k detection points; in [t k+1 ,..., t N , there is w k+1 < w k+2 <...< w N , indicating that the process of workers moving goods into the container starts at time t k+1 .

[0075] Ending the loading: There exists a certain moment t k , t 1 < t k < t N ; in [t 1 ,..., t k , there is w 1 < w 2 <...< w k , indicating that no loading operation occurs at the first k detection points; in [t k+1 ,..., tN , there is w k+1 = w k+2 =... = w N , indicating that by time t k the container has been fully assembled and the goods inside the container will no longer change.

[0076] For the entire loading process, the actual sensing data within the actually collected time window T is denoted as W original = [w 1 , …, w N ; using the median property to process the collected actual sensing data W original to obtain median(W original ) = W median , let W median = w = M 1 = M 2 =... = M J , where M j is the median of the sensing data within the moving window, j ∈ [1,..., J], J is the total number of medians, M j = median(w i , w i +1,..., w i+Q ), M j+1 = median(w i +S, w i +S+1,..., w i+S+Q ), Q is the size of the sliding window, S is the step length of the moving window, Q and S are used to control the data smoothing degree, remove unnecessary noise, and at the same time retain the details of signal changes. Both are set with reference to historical data. It should be noted that W refers to an idealized sensing data, which is the pure sensing data corresponding to W original in the case of no noise. Thus, the median of the sensing data in each time segment is obtained, and then the median pressure value in each sliding window is obtained through data conversion. Since the sliding window calculation can smooth local noise and enable the data to more truly reflect the changes in loading behavior during the loading process; since the median has anti-interference ability and can retain the true change trend of the data without excessive smoothing to prevent key loading behavior data from being misfiltered, such as the small decrease in data at the start of a small-scale loading can be retained.

[0077] Then, calculate the difference between the median pressure values of adjacent time segments to obtain the pressure change value of adjacent time segments. Let sub(W median ) = W change , Sub(W median ) represents the difference obtained by taking the difference of the sensing data in each adjacent time segment in W median , that is, Wchange = [M 2 -M 1 , M 3 -M 2 ,..., M J -M J-1 = [C 1 , C 2 ,..., C J-1 , C j represents the difference between the sensing data in the j-th time segment and the sensing data in the (j - 1)-th time segment, where j ∈ [2, J], and the median difference of the sensing data corresponding to all adjacent time segments is obtained. Since the difference between the sensing data in adjacent time segments is smoothed data processed by the median, its difference can highlight the data change trend caused by the loading behavior and reduce the influence of random fluctuations of noise interference.

[0078] Finally, based on the pressure change values of each of the adjacent time segments, the vehicle loading behavior is determined, including: If there exists a K, where K ∈ W change , abs(K) - (sum(W change - abs(K)) >> α, indicating that K is a number in the data W change and its absolute value is much larger than the sum of the other numbers in W change , and K < 0, where α represents the first pressure change threshold, then the vehicle loading behavior is determined to be lifting the container; If there exists a K, where K ∈ W change , abs(K) - (sum(W change - abs(K)) >> β, indicating that K is a number in the data W change and its absolute value is much larger than the sum of the other numbers in W change , and K > 0, where β represents the second pressure change threshold, then the vehicle loading behavior is determined to be returning the container; If the proportion of the number of negative numbers in W change to the total number is greater than the first negative proportion threshold γ (preferably set γ = 0.8), that is, count(W change < 0) / count(W change ) > γ, the vehicle loading behavior is determined to be starting to load goods. If γ = 0.8, that is, more than 80% of the change amounts of the sensing data along the time axis are negative, it indicates that the vehicle loading process is in a process of continuous and slow increase in the load weight; If the proportion of the number of negative numbers in W change to the total number is greater than the first negative proportion threshold δ (preferably set δ = 0.5), that is, count(W change < 0) / count(W change)≈δ, it is determined that the vehicle loading behavior is the end of loading. If δ = 0.5, that is, 50% of the change amount of the sensing data along the time axis is negative, it indicates that the change data during the vehicle loading process is positive and negative, so the load pressure basically does not change. In summary, the vehicle loading behavior is defined as: analyze(W change ) = result, result = (stutus, time), stutus = [lifting the container, returning the container, starting loading, ending loading], and time is the time when the vehicle loading behavior status is detected. It should be noted that the first pressure change threshold, the second pressure change threshold, the first negative ratio threshold, and the second negative ratio threshold in this embodiment are set based on the type of goods loaded on the vehicle and the historical pressure data of the target monitoring point on the detected vehicle.

[0079] In this embodiment, through strict K - value screening, it is possible to accurately capture the time points when the data drops significantly during container lifting and rises significantly during container returning, avoiding misjudging small - amplitude noise fluctuations as loading behaviors. Using the median difference of the sensing data corresponding to adjacent time segments to judge the start and end of loading can accurately reflect the change trend of the loading state. The discriminant conditions for each loading behavior are closely combined with the actual data changes. The K - value conditions for container lifting and returning and the negative number ratio conditions for loading behaviors are strict and accurate, which can effectively avoid misjudging or missing the judgment of loading behaviors and ensure the accuracy and effectiveness of the detection results.

[0080] As Figure 2 shown, corresponding to the above - mentioned vehicle loading behavior detection method based on the median property, an embodiment of the present invention also provides a vehicle loading behavior detection system based on the median property. The above - mentioned vehicle loading behavior detection system based on the median property includes:

[0081] A data acquisition module 210, configured to detect the sensing data of the target monitoring point on the vehicle during the loading process;

[0082] A data processing module 220, configured to process the sensing data based on a preset sliding window and use the median property to obtain the median pressure value within each sliding window;

[0083] A vehicle loading behavior determination module 230, configured to determine the vehicle loading behavior based on all the median pressure values.

[0084] Specifically, in this embodiment, the specific functions of the above - mentioned vehicle loading behavior detection system based on the median property can also refer to the corresponding descriptions in the above - mentioned vehicle loading behavior detection method based on the median property, and will not be elaborated here.

[0085] Based on the above - mentioned embodiments, the present invention also provides an intelligent terminal, and its principle block diagram can be as Figure 3As shown in the figure. The above intelligent terminal includes a processor, a memory, a network interface, and a display screen connected through a system bus. Among them, the processor of the intelligent terminal is used to provide computing and control capabilities. The memory of the intelligent terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a vehicle loading behavior detection program based on the median property. The internal memory provides an environment for the operation of the operating system and the vehicle loading behavior detection program based on the median property in the non-volatile storage medium. The network interface of the intelligent terminal is used to communicate with an external terminal through a network connection. When the vehicle loading behavior detection program based on the median property is executed by the processor, it implements the steps of any one of the above vehicle loading behavior detection methods based on the median property. The display screen of the intelligent terminal can be a liquid crystal display screen or an electronic ink display screen.

[0086] Those skilled in the art can understand that Figure 3 the block diagram of the principle shown in is only the block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the intelligent terminal to which the solution of the present invention is applied. The specific intelligent terminal may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0087] In one embodiment, an intelligent terminal is provided. The above intelligent terminal includes a memory, a processor, and a vehicle loading behavior detection program stored on the above memory and executable on the above processor. When the vehicle loading behavior detection program based on the median property is executed by the above processor, it implements the steps of any one of the vehicle loading behavior detection methods provided by the embodiments of the present invention.

[0088] The embodiments of the present invention also provide a computer-readable storage medium. The above computer-readable storage medium stores a vehicle loading behavior detection program based on the median property. When the vehicle loading behavior detection program based on the median property is executed by a processor, it implements the steps of any one of the vehicle loading behavior detection methods provided by the embodiments of the present invention.

[0089] It should be understood that the sequence numbers of the above steps do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be assigned to different functional units and modules according to needs, that is, the internal structure of the above device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present invention. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0091] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by 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. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0093] In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are only illustrative. For example, the above-mentioned division of modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0094] The above-described embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A vehicle loading behavior detection method based on median property, characterized in that: The following steps are involved: Detect sensor data from target monitoring points on the vehicle during loading; Based on a preset sliding window, the sensor data is processed using a median property to obtain a median pressure value within each sliding window; Based on all said median pressure values, the vehicle loading behavior is determined.

2. The vehicle loading behavior detection method based on median property according to claim 1 is characterized in that: The sensing data of the target monitoring point on the vehicle during the detection of loading includes: According to the preset detection frequency, the sensor data of each target monitoring point on the vehicle during the loading process is detected respectively to obtain a series of sensor data corresponding to each target monitoring point; Based on the sensor data of all the target monitoring points, the sensor data of the vehicle during the loading process is obtained.

3. The vehicle loading behavior detection method based on median property according to claim 1 is characterized in that: The method of processing the sensor data based on the preset sliding window using the median property to obtain the median pressure value in each sliding window includes: The time period corresponding to the loading process is divided based on a preset sliding window to obtain several time segments; The median of the sensing data in each of the time segments is calculated to obtain the median pressure value in each sliding window.

4. The vehicle loading behavior detection method based on median property according to claim 3 is characterized in that: The determining of the vehicle loading behavior based on all the median pressure values ​​includes: Calculate the difference between the median pressure values ​​of adjacent time segments to obtain the pressure change values ​​of adjacent time segments; The vehicle loading behavior is determined based on the pressure change values ​​of each of the adjacent time segments.

5. The vehicle loading behavior detection method based on median property according to claim 4 is characterized in that: The determining of the vehicle loading behavior based on the pressure change value of each two adjacent time segments includes: If the pressure change values ​​of any two adjacent time segments are negative and the absolute value of the pressure change value is greater than the preset first pressure change threshold, the vehicle loading behavior is determined to be container pickup; If the pressure change value of any two adjacent time segments is positive and the pressure change value is greater than a preset second pressure change threshold, the vehicle loading behavior is determined to be a container return; If the negative ratio of the pressure change values ​​in all adjacent time segments is greater than a preset first negative ratio threshold, it is determined that the vehicle loading behavior is the start of loading; If the negative percentage of the pressure change values ​​in all adjacent time segments is equal to a preset second negative percentage threshold, it is determined that the vehicle loading behavior is to end loading.

6. The vehicle loading behavior detection method based on median property according to claim 5 is characterized in that: The first pressure change threshold, the second pressure change threshold, the first negative number ratio threshold and the second negative number ratio threshold are set based on the type of cargo loaded on the vehicle and the historical pressure data of the target monitoring point detected on the vehicle.

7. A vehicle loading behavior detection system based on median property, characterized in that: The system comprises: A data acquisition module is used to detect sensor data from target monitoring points on the vehicle during loading; A data processing module, used to process the sensor data based on a preset sliding window using the median property to obtain a median pressure value in each sliding window; The vehicle loading behavior determination module is used to determine the vehicle loading behavior based on all the median pressure values.

8. An intelligent terminal, characterized in that: The intelligent terminal includes a memory, a processor, and a vehicle loading behavior detection program based on the median property stored in the memory and executable on the processor. When the vehicle loading behavior detection program based on the median property is executed by the processor, the steps of the vehicle loading behavior detection method based on the median property as described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a vehicle loading behavior detection program based on the median property, and when the vehicle loading behavior detection program based on the median property is executed by the processor, the steps of the vehicle loading behavior detection method based on the median property as described in any one of claims 1-6 are implemented.

Images