Job event identification method and apparatus, electronic device, and readable storage medium

Abstract

Embodiments of the present application provide a kind of job event identification method, device, electronic equipment and readable storage medium, involve logistics technical field.The present application embodiment obtains the loading capacity change data in the vehicle transportation way, compares loading capacity change data with the target event threshold value set, obtains the job state feature data of vehicle, according to job state feature data, the job event in the vehicle transportation way is identified.So, the effective identification of the job event in the vehicle transportation way is realized, the loading rate change situation of vehicle can be effectively mastered, and accuracy is high.

Description

Technical Field

[0001] This invention relates to the field of logistics technology, and more specifically, to a method, apparatus, electronic device, and readable storage medium for identifying operational events. Background Technology

[0002] Currently, in the logistics industry, cargo transportation may be divided into different routes based on freight demand, with each route allocated different vehicles. To ensure timely delivery, when the loading capacity of the allocated vehicles for each route cannot meet the time requirements, additional vehicles need to be added temporarily, which may increase transportation costs. Therefore, understanding the transportation capacity demand for each route to plan resources in advance and reduce costs is an urgent problem to be solved.

[0003] The key to understanding the capacity demand for each route lies in understanding how vehicle loading rates change during transportation. Knowing these changes allows for precise calculation of the route's capacity demand. Currently, the accuracy of calculating load rate changes during vehicle transportation needs improvement. Summary of the Invention

[0004] Based on this, embodiments of the present invention provide a method, apparatus, electronic device, and readable storage medium for identifying work events. By identifying work events during vehicle transportation, the changes in vehicle loading rate can be effectively monitored with high accuracy.

[0005] Embodiments of the present invention can be implemented in the following ways:

[0006] In a first aspect, embodiments of the present invention provide a job event identification method, the method comprising:

[0007] Obtain data on changes in vehicle load during transportation;

[0008] The loading change data is compared with a set target event threshold to obtain the vehicle's operational status characteristic data; the operational status characteristic data includes the operational status of the vehicle at each moment during transportation.

[0009] Based on the operational status feature data, operational events during vehicle transportation are identified.

[0010] In an optional implementation, before comparing the load change data with a set target event threshold, the method further includes:

[0011] Obtain historical load change data for the vehicle;

[0012] Based on the historical loading volume change data, the operation events of the vehicle are counted under different event thresholds to obtain the sum of the number of events corresponding to different event thresholds;

[0013] Based on the number of events corresponding to the different event thresholds, curve fitting is performed to obtain the target surface;

[0014] Calculate the first target point with the largest gradient change in the target surface, and set the event threshold corresponding to the first target point as the target event threshold; wherein, the event threshold combination includes a first event threshold and a second event threshold.

[0015] In an optional implementation, the step of acquiring data on changes in vehicle load during transport includes:

[0016] The loading data of the vehicle during transportation is obtained, and the loading data is preprocessed to obtain preprocessed loading data.

[0017] Differential processing is performed on the preprocessed loading data to obtain loading change characteristic data;

[0018] The loading volume change characteristic data is smoothed to obtain the loading volume change data.

[0019] In an optional implementation, the step of preprocessing the loading data to obtain preprocessed loading data includes:

[0020] The loading data is standardized according to the set time dimension to obtain standardized loading data.

[0021] Check if there are any missing values ​​in the standardized loading data;

[0022] If there are missing values, the standardized load data is interpolated, and the interpolated load data is smoothed to obtain the preprocessed load data.

[0023] If no missing values ​​exist, the standardized load data is smoothed to obtain preprocessed load data.

[0024] In an optional implementation, the target event threshold includes a first event threshold and a second event threshold, and the step of comparing the load change data with the set target event threshold to obtain the vehicle's operating status characteristic data includes:

[0025] The loading volume change data is compared with the first event threshold and the second event threshold respectively to obtain the comparison results;

[0026] Based on the comparison results, the load change data is marked with an operational status to obtain the operational status characteristic data of the vehicle.

[0027] In an optional implementation, the step of marking the load change data with an operational status based on the comparison result includes:

[0028] If the load change data is less than the first event threshold, the load change data is marked with a first state.

[0029] If the load change data is greater than the second event threshold, the load change data is marked with a second state.

[0030] If the load change data is greater than or equal to the first event threshold and less than or equal to the second event threshold, the load change data is marked with a third state.

[0031] In an optional implementation, the step of identifying operational events during vehicle transportation based on the operational status feature data includes:

[0032] Based on the operational status characteristic data, the changes in operational status between two adjacent moments during the vehicle's transportation are obtained;

[0033] Based on the changes in the operation status between every two adjacent time points and a preset state transition table, the operation events during vehicle transportation are identified. The state transition table includes the correspondence between the changes in the operation status between every two adjacent time points and the operation events.

[0034] In an optional implementation, after identifying the operational events during vehicle transportation based on the operational status feature data, the method further includes:

[0035] Obtain the start and end times of each of the aforementioned job events;

[0036] Based on the start and end times of each job event, each job event is integrated and processed under different time thresholds to obtain the number of events corresponding to different time thresholds;

[0037] The target curve is obtained by fitting a curve to the number of events corresponding to different time thresholds;

[0038] Calculate the second target point with the largest curvature in the target curve, and integrate each job event according to the target time threshold corresponding to the second target point to obtain the optimized job event.

[0039] In a second aspect, embodiments of the present invention provide a job event identification device, the job event identification device comprising:

[0040] The data acquisition module is used to acquire data on changes in the vehicle's load during transportation.

[0041] The data processing module is used to compare the load change data with a set target event threshold to obtain the vehicle's operational status characteristic data; the operational status characteristic data includes the operational status corresponding to each moment during the vehicle's transportation.

[0042] The event recognition module is used to identify operational events during vehicle transportation based on the operational status feature data.

[0043] Thirdly, embodiments of the present invention provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the job event recognition method described in any of the foregoing embodiments.

[0044] Fourthly, embodiments of the present invention provide a readable storage medium, the readable storage medium including a computer program, wherein the computer program, when running, controls the electronic device where the readable storage medium is located to execute the job event identification method described in any of the foregoing embodiments.

[0045] The operation event identification method, apparatus, electronic device, and readable storage medium provided in this invention acquire load change data during vehicle transportation, compare the load change data with a set target event threshold to obtain vehicle operation status characteristic data, and identify operation events during vehicle transportation based on the operation status characteristic data. In this way, effective identification of operation events during vehicle transportation is achieved, enabling effective monitoring of vehicle load rate changes with high accuracy. Attached Figure Description

[0046] The technical solution and other beneficial effects of the present invention will become apparent from the following detailed description of specific embodiments of the invention, in conjunction with the accompanying drawings.

[0047] Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0048] Figure 2 This is a flowchart illustrating a job event identification method provided in an embodiment of the present invention.

[0049] Figure 3 The graph shows the magnitude of change in unfiltered load change data and filtered load change data provided in the embodiments of the present invention.

[0050] Figure 4 This is a schematic diagram illustrating a trend in the number of loading events provided in an embodiment of the present invention.

[0051] Figure 5 This is a schematic diagram of a target surface provided in an embodiment of the present invention.

[0052] Figure 6 This is a surface plot for finding the second-order partial differential maximum value of a target surface, provided in an embodiment of the present invention.

[0053] Figure 7 This is a schematic diagram of an event recognition result provided in an embodiment of the present invention.

[0054] Figure 8 This is a block diagram of a job event recognition device provided in an embodiment of the present invention.

[0055] Icons: 100 - Electronic device; 10 - Operation event recognition device; 11 - Data acquisition module; 12 - Data processing module; 13 - Event recognition module; 20 - Memory; 30 - Processor; 40 - Communication unit. Detailed Implementation

[0056] 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 a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0057] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0058] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection, an electrical connection, or a connection that allows for communication; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0059] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0060] The following disclosure provides many different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the invention. Furthermore, reference numerals and / or letters may be repeated in different examples; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. In addition, examples of various specific processes and materials are provided in this invention, but those skilled in the art will recognize the application of other processes and / or the use of other materials.

[0061] The logistics industry requires a large number of trucks to perform transportation tasks on different routes. Because the number of waybills and the types of goods vary along these routes, specific vehicle specifications need to be allocated to different routes at different times. For each route, when the loading capacity of the allocated vehicles cannot meet the timeliness requirements, additional vehicles need to be added temporarily, which may increase transportation costs.

[0062] The fundamental issue in understanding the loading capacity of routes and vehicles in advance, and grasping the transport capacity demand for each route, boils down to identifying changes in vehicle loading rates during transportation. By understanding the changes in loading rates during the loading and unloading process of vehicles assigned to transport tasks on each route, the transport capacity demand for the route can be accurately calculated. This allows for the addition of vehicles to routes with insufficient resources, and the reduction of vehicles or the conversion of large vehicles to smaller ones to routes with wasted resources.

[0063] Currently, changes in vehicle loading rates during transportation are mostly monitored using the following methods:

[0064] The first method involves site personnel scanning barcodes and reporting the loading amount when loading and unloading goods. The specific loading amount is calculated by the cloud based on the weight registered on the waybill. However, this method is not synchronized with the site barcode scanning and loading / unloading events, resulting in discrepancies between the weight registered on the waybill and the actual weight. Consequently, the reliability of conclusions regarding changes in vehicle loading rates is low.

[0065] The second method uses AI image recognition algorithms to analyze photos taken at the start and end of loading and unloading to obtain the loading amount. However, this method is greatly affected by the lighting in the photos and the angle of the vehicle, and the calculated loading amount also differs from the actual amount, making it unreliable. Consequently, the conclusions regarding changes in vehicle loading rates are less credible.

[0066] The third method involves installing electronic fences or other equipment at the site. When a vehicle enters a specific area, it uploads data to the cloud to begin operations, and when it leaves, it reports to the cloud to end operations. However, this method cannot distinguish between loading and unloading, and the loading volume relies on external waybill data, which cannot guarantee accuracy. Consequently, the reliability of conclusions regarding changes in vehicle loading rates is also low.

[0067] Based on the above research, this embodiment provides a method, apparatus, electronic device, and readable storage medium for identifying operational events. By acquiring data on changes in vehicle load during transportation, comparing this data with a set target event threshold, and obtaining vehicle operational status characteristic data, operational events during vehicle transportation are identified based on this characteristic data. This achieves effective identification of operational events during vehicle transportation, effectively monitoring changes in vehicle load rates with high accuracy, and providing a solid foundation for subsequent route planning and optimization.

[0068] Please see Figure 1 , Figure 1 This is a schematic diagram of the structure of the electronic device provided in this embodiment. Figure 1 As shown, the electronic device 100 includes a job event recognition device 10, a memory 20, a processor 30, and a communication unit 40. The memory 20, processor 30, and communication unit 40 are electrically connected directly or indirectly to each other to achieve signal transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0069] In this embodiment, the job event identification device 10 includes at least one software functional module that can be stored in the memory 20 in the form of software or firmware. The processor 30 is used to execute the executable module (e.g., the software functional module or computer program included in the job identification device 10) stored in the memory 20. When the electronic device 100 is running, the processor 30 communicates with the memory 20 via a bus, and the processor 30 executes the executable module or computer program to implement the job event identification method described in this embodiment.

[0070] The memory 20 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0071] Processor 30 is used to perform one or more functions described in this embodiment. In some embodiments, processor 30 may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). By way of example only, processor 30 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computing (RISC) computer, or a microprocessor, or any combination thereof.

[0072] For ease of explanation, only one processor is described in the electronic device 100. However, it should be noted that the electronic device 100 in this embodiment may also include multiple processors, and therefore the steps performed by one processor as described in this embodiment may also be performed jointly or individually by multiple processors. For example, if the processor of the electronic device performs steps A and B, it should be understood that steps A and B may also be performed jointly by two different processors or individually by one processor. For example, one processor performs step A, and a second processor performs step B, or the first processor and the second processor jointly perform steps A and B.

[0073] In this embodiment, the process definition method disclosed in any implementation can be applied to the processor 30, or implemented by the processor 30.

[0074] The communication unit 40 is used to establish a communication connection between the electronic device 100 and other devices via a network, and to send and receive data via the network.

[0075] In some implementations, the network can be any type of wired or wireless network, or a combination thereof. By way of example only, the network may include wired networks, wireless networks, fiber optic networks, telecommunications networks, intranets, the Internet, local area networks (LANs), wide area networks (WANs), wireless local area networks (WLANs), metropolitan area networks (MANs), public switched telephone networks (PSTNs), Bluetooth networks, ZigBee networks, or near field communication (NFC) networks, or any combination thereof.

[0076] In this embodiment, the electronic device can be a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a physical server, or other devices. This embodiment does not impose any restrictions on the specific type of electronic device.

[0077] Understandably, Figure 1 The structure shown is for illustrative purposes only. Electronic devices may also have more advanced features. Figure 1 Showing more or fewer components, or having with Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0078] based on Figure 1 The implementation architecture of this embodiment provides a job event identification method, which is based on... Figure 1 The electronic device shown executes the following detailed explanation of the steps of the job event recognition method provided in this embodiment. Please refer to [reference needed]. Figure 2 The job event identification method provided in this embodiment includes steps S101 to S103.

[0079] Step S101: Obtain data on changes in vehicle load during transportation.

[0080] During transportation, vehicles may undergo unloading and loading operations. When these operations occur, the vehicle's load capacity will change. For example, if a vehicle's load capacity is A, and it is unloaded at a certain location with the unloading amount set as a, then the vehicle's load capacity becomes Aa. Similarly, if it is loaded at a certain location with the loading amount set as b, then the vehicle's load capacity becomes A+a.

[0081] In this embodiment, the load change data represents the change in the load of the vehicle during transportation. For example, at time T1, the load of the vehicle is M1; at time T2, the load of the vehicle is M1; and at time T3, the load of the vehicle is M3. Then, at time T2, the load change data is M1-M2, and at time T3, the load change data is M3-M2.

[0082] Since the vehicle's load capacity can be obtained from its load volume, in this embodiment, a volume sensor can be installed on the vehicle to monitor the vehicle's load volume in real time or at set intervals, thereby obtaining the vehicle's load capacity data. The monitored load capacity data is then sent to an electronic device, which analyzes the load capacity data sent by the volume sensor to obtain the vehicle's load capacity change data.

[0083] Understandably, in this embodiment, the loading data monitored by the volume sensor is time-series data, that is, data with a time sequence, and the loading change data obtained based on the loading data is also time-series data. That is, in this embodiment, the obtained loading change data includes the loading change data at each moment during vehicle transportation.

[0084] Step S102: Compare the load change data with the set target event threshold to obtain the vehicle's operating status characteristic data.

[0085] The target event threshold is a threshold value for the load change data corresponding to the occurrence of an operation event, and each operation event has a corresponding event threshold. For example, in this embodiment, vehicle operation events may include unloading events and loading events. For unloading events, a threshold value is set, and for loading events, a threshold value is set.

[0086] In this embodiment, by comparing the load change data at each moment with the target event threshold, the relevant operation status corresponding to the load change data at each moment can be obtained, that is, the operation status at each moment during vehicle transportation can be obtained, thereby obtaining the vehicle's operation status feature data.

[0087] For example, if the load change data at a certain moment is compared with a target event threshold and it is found that the load change data at that moment is related to an unloading event, then the corresponding operation status is unloading. As another example, if the load change data at that moment is compared with a target event threshold and it is found that the load change data at that moment is related to a loading event, then the corresponding operation status is loading. And as yet another example, if the load change data at that moment is compared with a target event threshold and it is found that the load change data at that moment is not related to loading / unloading events but is related to transportation events, then the corresponding operation status is transportation.

[0088] Step S103: Identify operational events during vehicle transportation based on operational status feature data.

[0089] Once the operational status feature data is obtained, operational events occurring during vehicle transportation can be identified based on this data.

[0090] In this embodiment, the operation status feature data includes the operation status corresponding to each moment during vehicle transportation. When identifying operation events occurring during vehicle transportation based on the operation status feature data, the operation events occurring during vehicle transportation can be identified based on the operation status corresponding to each moment during vehicle transportation. For example, based on the operation status data, it can be obtained that the operation status corresponding to time T1 is unloading, the operation status corresponding to time T2 is transportation, and the operation status corresponding to time T3 is loading. Therefore, it can be concluded that an unloading event occurred at time T1, the vehicle was in transportation at time T2, and a loading event occurred at time T3.

[0091] The operational event identification method provided in this embodiment acquires data on changes in vehicle load during transportation, compares this data with a set target event threshold to obtain vehicle operational status characteristic data, and identifies operational events during vehicle transportation based on this characteristic data. This achieves effective identification of operational events during vehicle transportation, effectively monitors changes in vehicle load rates with high accuracy, and provides a solid foundation for subsequent route planning and optimization.

[0092] In practical applications, the frequency at which volume sensors monitor the loading volume of each vehicle varies. For example, some vehicles are monitored every 10 seconds, some every 20 seconds, and others every 40 seconds. Furthermore, the monitoring frequency for the same vehicle may differ daily; for instance, it might be monitored every 15 seconds one day and every 25 seconds the next. This inconsistent monitoring frequency leads to discontinuities and fluctuations in the loading volume data. Therefore, in this embodiment, the following steps can be used to obtain data on changes in loading volume during vehicle transportation:

[0093] (1) Obtain the loading data during vehicle transportation, preprocess the loading data, and obtain the preprocessed loading data.

[0094] (2) Perform differential processing on the preprocessed loading data to obtain loading change characteristic data.

[0095] (3) Smooth the load change characteristic data to obtain the load change data.

[0096] Specifically, the volume sensor can acquire the vehicle's loading volume data in real time or at set intervals during transportation. The volume sensor can monitor the vehicle's loading volume in real time or at set intervals to obtain the loading volume data, and then send this data to electronic equipment.

[0097] In this embodiment, the loading data during vehicle transportation is a sequence of data with time order, which can be represented as {Y}. t1 Y t2 Y t3 ...Y tn}, where Y t1 Y represents the vehicle's load capacity as monitored at time t1. t2 Y represents the vehicle's load capacity as monitored at time t2. t3 Y represents the vehicle's load capacity as monitored at time t3. tn This represents the vehicle's load capacity as monitored at time tn.

[0098] After obtaining the loading data during vehicle transportation, the loading data can be preprocessed. In this embodiment, the preprocessing of the loading data can be data cleaning to filter out erroneous or abnormal loading data.

[0099] To ensure the continuity of the acquired load data and reduce its volatility, this embodiment preprocesses the load data to obtain preprocessed load data. The steps may include:

[0100] Based on the set time dimension, the loading volume data is standardized to obtain standardized loading volume data.

[0101] Check if there are any missing values ​​in the standardized loading data.

[0102] If there are missing values, the standardized load data is interpolated, and the interpolated load data is smoothed to obtain the preprocessed load data.

[0103] If no missing values ​​exist, the standardized load data is smoothed to obtain preprocessed load data.

[0104] Since the volume sensors installed on the vehicle have different monitoring frequencies, after obtaining the load data, it is necessary to perform frequency standardization processing on the load data of different frequencies, that is, to standardize the load data according to the set time dimension.

[0105] Optionally, the time dimension can be set to minutes, hours, or other time dimensions, without any specific limitation. Optionally, in this embodiment, minutes are used as the set time dimension.

[0106] When standardizing the load volume data according to a set time dimension, the mean of the load volume data within each minute is calculated using minutes as the time dimension. This mean is then used as the load volume data for each minute. In this way, the load volume data can be unified into minute-based data, achieving standardization and yielding standardized load volume data. In this embodiment, the standardized load volume data can be represented by a volume.

[0107] Due to variations in vehicle operation attendance or network signal issues, the acquired load data may be incomplete. For example, a vehicle might have load data available before 9 AM and after 10 AM, but if it was performing a task between 9 AM and 10 AM, no load data might be available. Incomplete load data leads to a discontinuity in the time sequence of the data, significantly interfering with subsequent event recognition. Therefore, after obtaining the standardized load data, it's necessary to check for missing values. If missing values ​​are found, interpolation processing is required on the standardized load data.

[0108] In this embodiment, when interpolating the standardized loading data, the Lagrange multiplication method can be used. Based on the Lagrange multiplication method, the value to be interpolated can be predicted by combining the data before and after the missing value. The missing value is then filled in based on the predicted value, making the data complete. For example, for the missing value between 9:00 and 10:00, the Lagrange multiplication method can be used to predict the value that should be inserted for each minute between 9:00 and 10:00 by combining the data before 9:00 and after 10:00. Then, interpolation is performed based on the predicted value, thus making the data complete.

[0109] After interpolating the standardized load data, smoothing is also required to improve its smoothness. Alternatively, if the standardized load data does not contain missing values, smoothing can be performed directly.

[0110] In this embodiment, when smoothing the load volume data, different time windows can be used to perform non-centered, centered, median, or mean sliding processing on the load volume data. After performing sliding processing on the load volume data using different time windows, the mean of the load volume data after sliding processing through different time windows can be calculated to obtain the preprocessed load volume data.

[0111] Optionally, considering that the load volume data is largely based on pre-event logic—meaning that the actual identification process doesn't wait until long after the event has ended—the data available for calculation is data prior to the current data. Therefore, in this embodiment, the load volume data is smoothed using a non-center point method, that is, the current load volume is smoothed using the last element in the window. Simultaneously, considering the high noise level of the original load volume data, to improve data stability, this embodiment uses a median moving average when the window is small, using the median of the elements in the window as a derived index for the current element.

[0112] Therefore, in this embodiment, when smoothing the load data, a median moving average with a time window of 3 (excluding the center point) can be first applied to the load data. Here, a time window of 3 means a 3-minute window, which, during smoothing, refers to a 3-minute window including the current load data. For example, when applying a median moving average with a time window of 3 to the load data at time t, the load data from the minute before time t and the two minutes before time t can be obtained. Then, the median of the load data from the previous minute, the previous two minutes, and the load data at time t is used as the smoothed load data at time t, which is a derived indicator of the load data at time t.

[0113] After performing a median moving average of non-central points with a time window of 3 on the obtained loading data, in this embodiment, it is necessary to adjust the window size and sequentially perform a median moving average of non-central points with a time window of 5 and a median moving average of non-central points with a time window of 7 on the loading data. The specific moving process of the median moving average of non-central points with a time window of 5 and the median moving average of non-central points with a time window of 7 can be referred to the median moving average of non-central points with a time window of 5, and will not be elaborated further here.

[0114] In order to obtain the fluctuation characteristics of data over a wider range of sizes, in this embodiment, after performing median moving averages of non-center points with a time window of 3, median moving averages of non-center points with a time window of 5, and median moving averages of non-center points with a time window of 7 on the loading data, it is also necessary to perform a mean moving average of non-center points with a time window of 10 on the obtained loading data.

[0115] It should be noted that when the time window is 10, the influence of noise is relatively weak. Therefore, when the time window is 10, the mean moving average is used, and the mean of the elements in the window is used as the derived index of the current element.

[0116] In this embodiment, after performing median moving average of non-central points with a time window of 3, median moving average of non-central points with a time window of 5, median moving average of non-central points with a time window of 7, and mean moving average of non-central points with a time window of 10 on the loading data, the derived index volume (3), the derived index volume (5), the derived index volume (7), and the derived index volume (10) of the loading data with a time window of 10 can be obtained.

[0117] In this embodiment, since the features derived from different window sizes express the data fluctuation characteristics in different size ranges near the current loading data, after obtaining the derived index volume(3), volume(5), volume(7), and volume(10) of the loading data with time window of 3, volume(3), volume(5), volume(7), and volume(10) of the loading data with time window of 10, based on the convolution idea, the derived indices obtained by processing the above four window sizes, namely volume(3), volume(5), volume(7), and volume(10), are averaged to obtain the preprocessed loading data, which can be represented as V(XX). The weights of the obtained preprocessed loading data are implicitly contained in the different window sizes.

[0118] Since the preprocessed loading data V(XX) represents the characteristics of the original loading data, and the identification of operational events depends on the changing trend and intensity of the loading data, after obtaining the preprocessed loading data V(XX), it is necessary to perform differential processing on the preprocessed loading data to obtain the loading change characteristic data, which can be denoted as diffxx.

[0119] In this embodiment, when performing differential processing on the preprocessed load data, a first-order differential processing can be performed. That is, for the preprocessed load data at each time step, the preprocessed load data at that time step is subtracted from the preprocessed load data at the previous time step adjacent to that time step to obtain the load change characteristic data at that time step. This process is repeated until all preprocessed load data are differentially processed to obtain the load change characteristic data.

[0120] Since the load change characteristic data obtained after differential processing has large fluctuations, in order to reduce the data fluctuations and improve stability, in this embodiment, after obtaining the load change characteristic data, it is also necessary to perform smoothing processing on the load change characteristic data.

[0121] In this embodiment, when smoothing the load change characteristic data, the load change characteristic data can first be smoothed using the center point mean with a time window of 7 minutes. That is, the load change characteristic data is smoothed using the center point mean with a time window of 7 minutes. Here, center point mean smoothing means using the current load change characteristic data as the middle element in the window for mean smoothing, while mean smoothing uses the mean of the elements in the window as a derived index of the current load change characteristic data.

[0122] In order to obtain the data fluctuation characteristics within different size ranges and reduce data volatility, after smoothing the load change characteristic data with the mean of the center point within a time window of 7, the smoothed load change characteristic data can be smoothed again with time windows of different sizes.

[0123] Optionally, in this embodiment, when the smoothed load change feature data is smoothed again with time windows of different sizes, the smoothed load change feature data can be subjected to median moving average of the center point with a time window of 3, median moving average of the center point with a time window of 5, median moving average of the center point with a time window of 7, and median moving average of the center point with a time window of 10 in sequence.

[0124] After performing median moving averages of the center points for time windows of 3, 5, 7, and 10 on the smoothed load change characteristic data, the smoothed data “diffxx3”, “diffxx5”, “diffxx7”, and “diffxx10” can be obtained.

[0125] After smoothing the data using the four window sizes mentioned above, the data obtained by smoothing the four window sizes, namely "diffxx3", "diffxx5", "diffxx7", and "diffxx10", is averaged to obtain the load change data.

[0126] After obtaining the load change data, the load change data can be compared with the set target event threshold to obtain the vehicle's operational status characteristic data.

[0127] In this embodiment, the target event threshold includes a first event threshold and a second event threshold. The step of comparing the load change data with the set target event threshold to obtain the vehicle's operating status characteristic data may include:

[0128] The load change data is compared with the first event threshold and the second event threshold respectively to obtain the comparison results.

[0129] Based on the comparison results, the load change data is marked with operational status to obtain the vehicle's operational status characteristic data.

[0130] The first event threshold is the unloading event threshold, and the second event threshold is the loading event threshold. The loading change data is compared with the first event threshold and the second event threshold respectively.

[0131] In this embodiment, comparing the load change data with the first event threshold and the second event threshold respectively means comparing the load change data at each moment with the first event threshold and the second event threshold respectively. After comparing the load change data at each moment with the first event threshold and the second event threshold respectively, the operation status of the load change data at each moment can be marked according to the comparison results, thus obtaining the vehicle's operation status characteristic data.

[0132] Optionally, based on the comparison results, the step of marking the operation status of the load change data may include:

[0133] If the load change data is less than the first event threshold, set the first state flag for the load change data.

[0134] If the load change data exceeds the second event threshold, set a second state flag for the load change data.

[0135] If the load change data is greater than or equal to the first event threshold and less than or equal to the second event threshold, the load change data is marked with a third state.

[0136] In this embodiment, for the load change data at each moment, when the load change data at that moment is less than the first event threshold, that is, when the load change data at that moment is less than the unloading event threshold, the load change data at that moment is marked as the first state, where the first state indicates that it is related to the unloading event and is in the unloading state.

[0137] When the change in load at a given moment is greater than the second event threshold, that is, when the change in load at a given moment is greater than the loading event threshold, the change in load at that moment is marked as the second state, where the second state indicates that it is in the loading state related to the loading event.

[0138] When the load change data at a given moment is greater than or equal to the first event threshold and less than or equal to the second event threshold, that is, when the load change data at a given moment is greater than or equal to the unloading event threshold and less than or equal to the loading event threshold, it indicates that the load change at that moment is small and may be noise. Therefore, the load change data at that moment is marked as the third state, which indicates that it is in the transportation state.

[0139] In this embodiment, any identifier can be used to mark the load change data at each moment, and there are no specific restrictions. To facilitate the analysis of vehicle operation events, in this embodiment, the first state can be set to tag=0, the second state to tag=20, and the third state to tag=10.

[0140] For example, when the load change data at a certain moment is less than the first event threshold, the load change data at that moment can be marked as tag=0. When the load change data at that moment is less than the second event threshold, the load change data at that moment can be marked as tag=20. When the load change data at that moment is greater than or equal to the first event threshold and less than or equal to the second event threshold, the load change data at that moment can be marked as 10.

[0141] After obtaining the operation status tags for the load change data at each time point, the vehicle's operation status characteristic data can be obtained based on these operation status tags. In this embodiment, the vehicle's operation status characteristic data can be represented by {tag}. t1 , tag t2 , tag t3 ... tag tn} indicates that the tag t1 Indicates the job status at time t1, tag t2 Indicates the job status at time t2, tag t3 Indicates the job status at time t3, tag tn This represents the job status at time tn.

[0142] In one optional implementation, to facilitate data analysis, when the load change data at a certain moment is greater than or equal to a first event threshold and less than or equal to a second event threshold, the load change data at that moment can be set to 0.

[0143] The operation event identification method provided in this embodiment compares the load change data with the first event threshold and the second event threshold by setting a first event threshold and a second event threshold. While identifying the operation status, it can also filter noise in the load change data, improving data accuracy. Figure 3 As shown, Figure 3 This is a graph showing the magnitude of change in load volume data, both before and after filtering (noise removal).

[0144] In this embodiment, the magnitude of change refers to the percentage change between the current moment and the previous moment, which can be calculated using the following formula:

[0145]

[0146] Here, diffxx represents the load change data.

[0147] The operation event identification method provided in this embodiment can obtain the operation status corresponding to the loading volume change data at each moment after obtaining the operation status feature data. However, determining the operation event during vehicle transportation solely based on the operation status corresponding to the loading volume change data at each moment has low accuracy. For example, if the loading volume change data at a certain moment is related to the unloading status, it indicates that the vehicle may be in the process of unloading, unloading, or unloading has ended. Similarly, if the loading volume change data at a certain moment is related to the loading status, it indicates that the vehicle may be in the process of loading, loading, or loading has ended. In other words, obtaining the operation status corresponding to the loading volume change data at each moment does not determine the specific operation status corresponding to the loading volume change data at each moment.

[0148] Therefore, in order to identify the specific operational status at each moment and thus identify operational events during vehicle transportation, in this embodiment, after obtaining the vehicle's operational status feature data, the step of identifying operational events during vehicle transportation based on the operational status feature data may include:

[0149] Based on the operational status characteristic data, the changes in operational status between two adjacent moments during vehicle transportation are obtained.

[0150] Based on the changes in the operational status between two adjacent time points and a preset state transition table, operational events during vehicle transportation are identified.

[0151] In this implementation, the operation status feature data includes the operation status corresponding to the load change data at each moment. Therefore, when obtaining the change of operation status between two adjacent moments during vehicle transportation based on the operation status feature data, the operation status feature data can be processed by first-order difference, that is, by comparing the status change between the previous moment and the next moment, the change of operation status between two adjacent moments during vehicle transportation can be obtained.

[0152] To identify the specific operational status at each moment, this embodiment defines a state transition table to determine the specific operational status of the next moment based on the state transition between the previous and next moments. In this embodiment, the state transition table includes the changes in operational status between every two adjacent moments and their corresponding operational events, as shown in Table 1. The table header represents the operational status of the previous moment (i.e., the operational status of the moment before the previous moment in two adjacent moments), and the row header represents the operational status of the next moment (i.e., the operational status of the moment after the next moment in two adjacent moments). Specifically, 0 represents the unloading status, related to the unloading event; 10 represents the transportation status, related to the transportation event; and 20 represents the loading status, related to the loading event. The state transition table shows nine specific operation states: "Unloading", "Transporting", "Loading", "Start Unloading", "End Unloading", "Start Loading", "End Unloading", "Error State 1", and "Error State 2". "Error State 1" means that the vehicle was in the unloading state one moment and in the loading state the next moment, which does not conform to the business scenario and is defined as an abnormal state. Similarly, "Error State 2" means that the vehicle was in the loading state one moment and in the unloading state the next moment, which is also defined as an abnormal state.

[0153] Table 1:

[0154]

[0155]

[0156] In this embodiment, when identifying work events during vehicle transportation based on the changes in work status between two adjacent moments and a preset state transition table, the changes in work status between two adjacent moments can be matched with the changes in work status between adjacent moments included in the state transition table, thereby obtaining the specific work status of the next moment in each pair of adjacent moments.

[0157] For example, given two adjacent time points T1 and T2, let T1 be the previous time point and T2 be the next time point. If the operation status at time T1 is unloading, and the operation status at time T2 is unloading, the operation status remains unchanged. After matching this with the state changes of adjacent time points in the state transition table, the specific operation status at time T2 is "Unloading in progress." If the operation status at time T1 is unloading, and the operation status at time T2 is transporting, the operation status changes from unloading to transporting. After matching this with the state changes of adjacent time points in the state transition table, the specific operation status at time T2 is "Unloading completed." If the operation status at time T1 is unloading, and the operation status at time T2 is loading, the operation status changes from unloading to loading. After matching this with the state changes of adjacent time points in the state transition table, the specific operation status at time T2 is "Error state 1."

[0158] For example, if the operation status at time T1 is "transportation" and the operation status at time T2 is "unloading," and the operation status changes from "transportation" to "unloading" between these two times, matching this with the state changes of adjacent times in the state transition table, the specific operation status at time T2 can be determined as "unloading begins." If the operation status at both times is "transportation," and the operation status remains unchanged, matching this with the state changes of adjacent times in the state transition table, the specific operation status at time T2 can be determined as "transporting in progress." If the operation status at time T1 is "transportation," and the operation status at time T2 is "loading," and the operation status changes from "transportation" to "loading" between these two times, matching this with the state changes of adjacent times in the state transition table, the specific operation status at time T2 can be determined as "loading begins."

[0159] For example, if the operation status at time T1 is loading and at time T2 is unloading, and the operation status changes from transportation to loading to unloading, matching this with the state changes of adjacent times in the state transition table, the specific operation event at time T2 is error state 2. If the operation status at time T1 is loading and at time T2 is transportation, and the operation status changes from loading to transportation, matching this with the state changes of adjacent times in the state transition table, the specific operation event at time T2 is loading completed. If the operation status at time T1 is loading and at time T2 is loading, and the operation status remains unchanged, matching this with the state changes of adjacent times in the state transition table, the specific operation event at time T2 is loading in progress.

[0160] After identifying the specific operational status at each moment, the operational events during vehicle transportation can be obtained based on the specific operational status at each moment.

[0161] In this embodiment, the operational events during vehicle transportation can be divided into loading events and unloading events. When identifying operational events during vehicle transportation based on the specific operational status at each time point, adjacent "start loading" and "end loading" can be considered as one loading event, and adjacent "start unloading" and "end unloading" can be considered as one unloading event. For example, if the specific operational status at time t1 is "start loading," the specific operational status at time t2 is "start loading," the specific operational status at time t3 is "loading in progress," the specific operational status at time t4 is "loading completed," and the specific operational status at time t5 is "transporting," then times t1 to t4 constitute one loading event. As another example, if the specific operational status at time t1 is "transporting in progress," the specific operational status at time t2 is "start unloading," the specific operational status at time t3 is "error status 1," the specific operational status at time t4 is "unloading in progress," and the specific operational status at time t5 is "unloading completed," then times t1 to t4 constitute one unloading event.

[0162] In this embodiment, after obtaining the operation events during vehicle transportation based on the specific operation status at each moment, the start and end times of loading and unloading events during vehicle transportation can be obtained, as shown in Table 2. Table 2 is a table of operation events identified based on the specific operation status at each moment.

[0163]

[0164]

[0165] Table 2 shows that, based on the specific operational status at each moment, some operational events during vehicle transportation have short intervals. For example, the unloading time starting at 00:01 on June 28, 2021, lasted for 10 minutes, while this event ended at 00:11, and immediately followed by another unloading time at 00:15, with an interval of 4 minutes between the two events, which does not match the actual situation. Therefore, it is necessary to merge events with short intervals within the same event type, where "same type" refers to loading event type or unloading event type.

[0166] Meanwhile, based on the specific operational status at each moment, some operational events during vehicle transportation are found to be short-lived. However, in practice, loading or unloading events typically last for a period of time and are not completed in a very short period of time. Therefore, short-lived operational events need to be removed.

[0167] Based on this, after identifying operational events during vehicle transportation according to operational status feature data, the operational event identification method provided in this embodiment further includes:

[0168] Get the start and end times of each job event.

[0169] Based on the start and end times of each job event, each job event is merged or eliminated under different time thresholds to obtain the number of events corresponding to different time thresholds.

[0170] The target curve is obtained by fitting curves to the number of events corresponding to different time thresholds.

[0171] Calculate the second target point with the largest curvature in the target curve, and merge or eliminate each job event according to the target time threshold corresponding to the second target point to obtain the optimized job event.

[0172] The integration and processing of job events includes merging and eliminating job events. In order not to lose event fragments, in this embodiment, job events can be merged first, and then eliminated based on the merged job events. In this way, some job events with short durations and short intervals can be retained and merged into adjacent events of the same type. After merging, job events with shorter durations can be identified as abnormal events and should be eliminated. In this way, some correct events can be avoided.

[0173] In this embodiment, the merging of loading events can be determined by a loading interval time threshold, the elimination of loading events can be determined by a loading duration threshold, the merging of unloading events can be determined by an unloading interval time threshold, and the elimination of unloading events can be determined by an unloading duration threshold.

[0174] Based on this, when integrating each operation event according to its start and end times under different time thresholds to obtain the number of events corresponding to different time thresholds, the following methods can be used: For merging loading events, all identified loading events can be merged according to the start and end times of each loading event under different loading interval time thresholds to obtain the number of loading events corresponding to different loading interval time thresholds; for eliminating loading events, all identified loading events can be eliminated according to the start and end times of each loading event under different loading duration thresholds to obtain the number of loading events corresponding to different loading duration thresholds; for merging unloading events, all identified unloading events can be merged according to the start and end times of each unloading event under different unloading interval time thresholds to obtain the number of unloading events corresponding to different unloading interval time thresholds; for eliminating unloading events, all identified unloading events can be eliminated according to the start and end times of each unloading event under different unloading duration thresholds to obtain the number of unloading events corresponding to different unloading duration thresholds.

[0175] It should be noted that when merging all identified loading events based on the start and end times of each loading event under different loading interval thresholds, for each loading interval threshold, the system can determine whether the interval between two adjacent loading events is less than the threshold. If it is less, the two adjacent loading events are merged; otherwise, they are not merged. Similarly, when eliminating all identified loading events based on the start and end times of each loading event under different loading duration thresholds, for each loading duration threshold, the system can determine whether the duration of each loading event is greater than the threshold. Loading events that are less than the threshold are eliminated, while those that are greater are retained. The merging and elimination of unloading events can be handled in the same way, and will not be elaborated further here.

[0176] After obtaining the number of loading events corresponding to different loading interval time thresholds, the number of loading events corresponding to different loading duration thresholds, the number of unloading events corresponding to different unloading interval time thresholds, and the number of unloading events corresponding to different unloading duration thresholds, curve fitting is performed based on the number of loading events corresponding to different loading interval time thresholds to obtain the target curve corresponding to the loading interval time threshold; curve fitting is performed based on the number of loading events corresponding to different loading duration thresholds to obtain the target curve corresponding to the loading duration threshold; curve fitting is performed based on the number of unloading events corresponding to different unloading interval time thresholds to obtain the target curve corresponding to the unloading interval time threshold; and curve fitting is performed based on the number of unloading events corresponding to different unloading duration thresholds to obtain the target curve corresponding to the unloading duration threshold. Figure 4 As shown, Figure 4 This is a trend graph showing the number of loading events as a function of loading interval time threshold and loading duration threshold.

[0177] After obtaining the target curves corresponding to the loading interval time threshold, loading duration threshold, unloading interval time threshold, and unloading duration threshold, for the target curve corresponding to the loading interval time threshold, the second target point with the largest curvature can be calculated. Then, based on the target loading interval time threshold corresponding to the second target point, the identified loading events are merged. For the target curve corresponding to the loading duration threshold, the second target point with the largest curvature can be calculated. Then, based on the target loading duration threshold corresponding to the second target point, the identified loading events are eliminated. For the target curve corresponding to the unloading interval time threshold, the second target point with the largest curvature can be calculated. Then, based on the target unloading interval time threshold corresponding to the second target point, the identified unloading events are merged. For the target curve corresponding to the unloading duration threshold, the second target point with the largest curvature can be calculated. Then, based on the target unloading duration threshold corresponding to the second target point, the identified loading and unloading events are eliminated. In this way, the identified loading events and unloading events can be merged and eliminated to obtain optimized operation events.

[0178] As shown in Table 3, Table 3 is a table after merging and removing loading events and unloading events in Table 2 based on target time thresholds (target loading interval time threshold, target loading duration threshold, target unloading interval time threshold, target unloading duration threshold).

[0179]

[0180] The job event identification method provided in this embodiment, after identifying a job event, obtains the start and end times of each job event, integrates each job event according to different time thresholds based on the start and end times, obtains the number of events corresponding to different time thresholds, performs curve fitting based on the number of events corresponding to different time thresholds to obtain a target curve, calculates the second target point with the largest curvature in the target curve, and integrates each job event according to the target time threshold corresponding to the second target point to obtain an optimized job event, which can effectively improve the accuracy of job event identification.

[0181] Given that in practical applications, each vehicle has different transportation task characteristics, loading volume, and loading and unloading efficiency for each vehicle at each site, and the characteristics of loading and unloading events are also different, in order to obtain more accurate loading and unloading event identification results, in this embodiment, it is necessary to independently calculate the target event threshold corresponding to each vehicle in order to achieve adaptive adaptation to the transportation operation characteristics of each vehicle.

[0182] For loading events, the event threshold essentially determines whether changes in loading volume are filtered out. For example, the event threshold affects whether small fluctuations in sensor data are considered load volume changes caused by loading / unloading. If these are considered load volume changes caused by loading / unloading, they are not filtered, leading to data errors and reducing the accuracy of event identification. Similarly, the event threshold affects whether situations with low loading / unloading efficiency and small changes in loading volume per unit time are considered data fluctuations rather than loading / unloading events. If these are considered data fluctuations, the data is filtered, resulting in missing data and inaccurate event identification. Therefore, based on factors such as vehicle, site, route, loading / unloading efficiency, and monitoring data fluctuations, it is necessary to find a relatively stable and reasonable event threshold.

[0183] Based on this, in this embodiment, the target event threshold can be obtained through the following steps:

[0184] Obtain historical data on changes in vehicle load.

[0185] Based on the historical load change data, the number of vehicle operation events is counted under different event thresholds to obtain the total number of events corresponding to different event thresholds.

[0186] The target surface is obtained by fitting curves based on the number of events corresponding to different event thresholds.

[0187] Calculate the first target point with the largest gradient change in the target surface, and set the event threshold corresponding to the first target point as the target event threshold.

[0188] In this embodiment, any historical time period can be set, and then the load change data of vehicles on the same route during that historical time period can be obtained to obtain historical load change data.

[0189] After obtaining historical load change data, the system identifies vehicle operation events based on this data at different event thresholds and statistically analyzes these events to obtain the number of events corresponding to different event thresholds.

[0190] Generally, when the event threshold is too high or too low, the number of events will decrease or increase sharply. However, around a suitable event threshold, the change in the number of events is relatively gradual. Therefore, after obtaining the number of events corresponding to different event thresholds, the optimal event threshold can be determined based on the stability of the change in the number of events. For example, for loading events, after obtaining the number of loading events corresponding to different loading event thresholds, the optimal loading event threshold can be determined based on the stability of the change in the number of loading events. Similarly, for unloading events, after obtaining the number of unloading events corresponding to different unloading event thresholds, the optimal unloading event threshold can be determined based on the stability of the change in the number of unloading events.

[0191] However, in practical applications, loading and unloading events are interdependent. When the loading event threshold is uncertain, the unloading threshold cannot be calculated independently, and vice versa. Therefore, in this embodiment, the event thresholds include both loading and unloading event thresholds. Based on historical loading volume change data, vehicle operation events are statistically analyzed under different event thresholds to obtain the sum of events corresponding to different event thresholds. For each event threshold, loading and unloading events generated by the vehicle can be identified based on historical loading volume change data under the loading and unloading event thresholds included in that event threshold. Then, the identified loading and unloading events are statistically analyzed and summed to obtain the sum of events corresponding to that event threshold.

[0192] In this embodiment, the process of identifying vehicle unloading and loading events under different event thresholds can refer to the above-described process of comparing the load change data with the set target event threshold to obtain the vehicle's operational status characteristic data, and then identifying operational events during vehicle transportation based on the operational status characteristic data. This process will not be elaborated further here.

[0193] After obtaining the sum of the number of events corresponding to different event thresholds, the sum of the number of events corresponding to different event thresholds can be curve-fitted to obtain the target surface. Specifically, when curve-fitting the sum of the number of events corresponding to different event thresholds, the loading event threshold and unloading event threshold included in each event threshold can be used as the X and Y coordinates, and the corresponding sum of the number of events can be used as the Z coordinate for curve fitting, resulting in the following... Figure 5 The spatial surface shown is the target surface.

[0194] This embodiment transforms the problem of determining the optimal loading event threshold and the optimal unloading event threshold into finding the point with the largest gradient change on the target surface. Therefore, after obtaining the target surface, the second-order partial derivative of the target surface is calculated to find the maximum value, and the point with the largest gradient change is selected as the first target point. The loading event threshold included in the event threshold corresponding to the first target point is the optimal loading event threshold, and the unloading event threshold included is the optimal unloading event threshold. The event threshold corresponding to the first target point is then set as the target event threshold. Figure 6 As shown, Figure 6 To find the maximum and minimum values ​​of the second-order partial derivatives of the target surface, the optimal thresholds are found to be (0.22, 0.18). Specifically, the optimal loading event threshold is 0.22, and the optimal unloading event threshold is 0.18. The unloading event threshold is negative when applied. Through the above process, the target event threshold for each vehicle can be calculated.

[0195] The operation event recognition method provided in this embodiment obtains an independent loading and unloading threshold for each vehicle by calculating the maximum value of the second-order partial derivative of the surface. This achieves adaptive recognition based on the transportation operation characteristics of each vehicle, thereby enabling more accurate event recognition results when identifying operation events during vehicle transportation. Figure 7 As shown, Figure 7 To identify events for a vehicle based on changes in its loading volume, a schematic diagram of the event results is obtained.

[0196] The operation event identification method provided in this embodiment combines factors such as differences in transportation tasks, vehicle volume, routes, loading and unloading efficiency, and site differences. It adaptively identifies events based on vehicle data through a dynamic threshold strategy, which can effectively grasp the changes in vehicle loading rate. Compared with traditional solutions, it has higher robustness, stability, accuracy, timeliness, and versatility.

[0197] Compared to the traditional site barcode scanning method, the operation event identification method provided in this embodiment can avoid manual operation and effectively grasp the changes in vehicle loading rate, thereby obtaining more accurate vehicle loading volume data, providing a solid foundation for subsequent route planning and optimization.

[0198] The operation event recognition method provided in this embodiment is based on data and starts from the perspective of algorithm model. It creates a general solution for vehicle loading and unloading event recognition in the logistics industry. Compared with traditional image detection algorithms, the operation event recognition method provided in this embodiment is not affected by factors such as lighting, camera angle, and distance from the vehicle, and the event recognition is more accurate.

[0199] Compared to the traditional method of deploying electronic fences on site, the operation event recognition method provided in this embodiment does not require the deployment of heavy equipment on site, thus avoiding the problem of limited recognition effect caused by insufficient equipment coverage in traditional solutions. At the same time, it saves equipment costs and has higher scalability.

[0200] Based on the same inventive concept, please refer to the following: Figure 8 This embodiment also provides a job event recognition device 10, which is applied to... Figure 1 The electronic devices shown, such as Figure 8 As shown, the job event recognition device 10 provided in this embodiment includes a data acquisition module 11, a data processing module 12, and an event recognition module 13.

[0201] The data acquisition module 11 is used to acquire data on changes in the load during vehicle transportation.

[0202] The data processing module 12 is used to compare the load change data with the set target event threshold to obtain the vehicle's operation status characteristic data; the operation status characteristic data includes the operation status corresponding to each moment during the vehicle's transportation.

[0203] The event recognition module 13 is used to identify operational events during vehicle transportation based on operational status feature data.

[0204] In an optional implementation, before comparing the load change data with a set target event threshold, the data processing module 12 is used to:

[0205] Obtain historical data on changes in vehicle load.

[0206] Based on historical load change data, the number of vehicle operation events is counted under different event thresholds to obtain the total number of events corresponding to different event thresholds.

[0207] The target surface is obtained by fitting curves based on the number of events corresponding to different event thresholds.

[0208] Calculate the first target point with the largest gradient change in the target surface, and set the event threshold corresponding to the first target point as the target event threshold.

[0209] In an optional implementation, the data acquisition module 11 is used for:

[0210] The loading data during vehicle transportation is obtained, and the loading data is preprocessed to obtain preprocessed loading data.

[0211] Differential processing is performed on the preprocessed loading data to obtain loading change characteristic data.

[0212] The loading volume change characteristic data is smoothed to obtain the loading volume change data.

[0213] In an optional implementation, the data acquisition module 11 is used for:

[0214] Based on the set time dimension, the loading volume data is standardized to obtain standardized loading volume data.

[0215] Check if there are any missing values ​​in the standardized loading data.

[0216] If there are missing values, the standardized load data is interpolated, and the interpolated load data is smoothed to obtain the preprocessed load data.

[0217] If no missing values ​​exist, the standardized load data is smoothed to obtain preprocessed load data.

[0218] In an optional implementation, the target event threshold includes a first event threshold and a second event threshold, and the data processing module 12 is used for:

[0219] The load change data is compared with the first event threshold and the second event threshold respectively to obtain the comparison results.

[0220] Based on the comparison results, the load change data is marked with operational status to obtain the vehicle's operational status characteristic data.

[0221] In an optional implementation, the data processing module 12 is used for:

[0222] If the load change data is less than the first event threshold, the load change data is marked with the first state.

[0223] If the load change data is greater than the second event threshold, the load change data is marked with a second state.

[0224] If the load change data is greater than or equal to the first event threshold and less than or equal to the second event threshold, the load change data is marked with a third state.

[0225] In an optional implementation, the event recognition module 13 is used for:

[0226] Based on the operational status characteristic data, the changes in operational status between two adjacent moments during vehicle transportation are obtained.

[0227] Based on the changes in the operational status between two adjacent time points and a preset state transition table, operational events during vehicle transportation are identified. The state transition table includes the correspondence between the changes in the operational status between two adjacent time points and the operational events.

[0228] In an optional implementation, after identifying operational events during vehicle transportation based on operational status characteristic data, the event identification module 13 is used to:

[0229] Get the start and end times of each job event.

[0230] Based on the start and end times of each job event, each job event is integrated and processed under different time thresholds to obtain the number of events corresponding to different time thresholds.

[0231] The target curve is obtained by fitting curves to the number of events corresponding to different time thresholds.

[0232] Calculate the second target point with the largest curvature in the target curve, and integrate each job event according to the target time threshold corresponding to the second target point to obtain the optimized job event.

[0233] The operational event identification method provided in this embodiment acquires data on changes in vehicle load during transportation, compares this data with a set target event threshold to obtain vehicle operational status characteristic data, and identifies operational events during vehicle transportation based on this characteristic data. This achieves effective identification of operational events during vehicle transportation, effectively monitors changes in vehicle load rates with high accuracy, and provides a solid foundation for subsequent route planning and optimization.

[0234] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the aforementioned method, and will not be elaborated further here.

[0235] Based on the above, this embodiment also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the job event method described in any of the foregoing embodiments.

[0236] The readable storage medium can be, but is not limited to, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, and other media capable of storing program code.

[0237] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the readable storage medium described above can be referred to the corresponding process in the aforementioned method, and will not be elaborated further here.

[0238] In summary, the operation event identification method, apparatus, electronic device, and readable storage medium provided in this invention acquire load change data during vehicle transportation, compare the load change data with a set target event threshold to obtain vehicle operation status characteristic data, and identify operation events during vehicle transportation based on the operation status characteristic data. Thus, effective identification of operation events during vehicle transportation is achieved, enabling effective monitoring of vehicle load rate changes with high accuracy.

[0239] The above provides a detailed description of a job event method, apparatus, electronic device, and readable storage medium provided by the embodiments of the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the technical solutions and core ideas of the present invention. Those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A work event recognition method characterized by comprising: The method comprises: acquiring loading amount change data of a vehicle during transportation; comparing the loading amount change data with a set target event threshold to obtain work state feature data of the vehicle; the work state feature data comprises a work state corresponding to each time during transportation of the vehicle; identifying a work event of the vehicle during transportation according to the work state feature data; before the comparing of the loading amount change data with the set target event threshold, the method further comprises: acquiring historical loading amount change data of the vehicle; according to the historical loading amount change data, counting work events of the vehicle under different event thresholds to obtain an event quantity corresponding to each event threshold; and performing curve fitting on the event quantity corresponding to each event threshold to obtain a target surface; calculating a first target point with the largest gradient change in the target surface, and setting an event threshold corresponding to the first target point as a target event threshold.

2. The work event recognition method according to claim 1, characterized by, The step of acquiring the loading amount change data of the vehicle during transportation comprises: acquiring loading amount data of the vehicle during transportation, pre-processing the loading amount data to obtain pre-processed loading amount data; differentially processing the pre-processed loading amount data to obtain loading amount change feature data; smoothly processing the loading amount change feature data to obtain loading amount change data.

3. The work event recognition method according to claim 2, characterized by, The step of pre-processing the loading amount data to obtain pre-processed loading amount data comprises: standardizing the loading amount data according to a set time dimension to obtain standardized loading amount data; detecting whether there is missing value in the standardized loading amount data; if there is missing value, performing interpolation processing on the standardized loading amount data, and smoothly processing the interpolated loading amount data to obtain pre-processed loading amount data; if there is no missing value, smoothly processing the standardized loading amount data to obtain pre-processed loading amount data.

4. The work event recognition method according to claim 1, characterized by, The target event threshold comprises a first event threshold and a second event threshold, and the step of comparing the loading amount change data with the set target event threshold to obtain the work state feature data of the vehicle comprises: comparing the loading amount change data with the first event threshold and the second event threshold respectively to obtain comparison results; according to the comparison results, marking the loading amount change data with a work state to obtain the work state feature data of the vehicle.

5. The work event recognition method according to claim 4, characterized by, The step of marking the loading amount change data with a work state according to the comparison results comprises: if the loading amount change data is less than the first event threshold, marking the loading amount change data with a first state; if the loading amount change data is greater than the second event threshold, marking the loading amount change data with a second state; if the loading amount change data is greater than or equal to the first event threshold and less than or equal to the second event threshold, marking the loading amount change data with a third state.

6. The work event recognition method according to claim 1, characterized by, The step of identifying the operation event in the vehicle transportation process according to the operation state feature data comprises: According to the operation state feature data, the change of the operation state of each two adjacent time points in the vehicle transportation process is obtained; According to the change of the operation state of each two adjacent time points and a preset state transition table, the operation event in the vehicle transportation process is identified, wherein the state transition table comprises the corresponding relationship between the change of the operation state of each two adjacent time points and the operation event.

7. The work event recognition method according to claim 1, characterized by, After the operation event in the vehicle transportation process is identified according to the operation state feature data, the method further comprises: Obtaining the start and end time of each operation event; According to the start and end time of each operation event, each operation event is integrated under different time thresholds to obtain the event quantity corresponding to different time thresholds; According to the event quantity corresponding to different time thresholds, a target curve is obtained by curve fitting; The second target point with the maximum curvature in the target curve is calculated, and each operation event is integrated according to the target time threshold corresponding to the second target point to obtain the optimized operation event.

8. A work event recognition device characterized by comprising: The operation event identification device comprises: A data acquisition module for acquiring the load change data in the vehicle transportation process; A data processing module for comparing the load change data with a set target event threshold to obtain the operation state feature data of the vehicle; the operation state feature data comprises the operation state corresponding to each time point in the vehicle transportation process; An event identification module for identifying the operation event in the vehicle transportation process according to the operation state feature data; Before the load change data is compared with the set target event threshold, it further comprises: Acquiring the historical load change data of the vehicle; According to the historical load change data, the operation events of the vehicle are counted under different event thresholds to obtain the event quantity corresponding to different event thresholds; According to the event quantity corresponding to different event thresholds, a target curve surface is obtained by curve fitting; The first target point with the maximum gradient change in the target curve surface is calculated, and the event threshold corresponding to the first target point is set as the target event threshold.

9. An electronic device, comprising: The readable storage medium comprises a memory, a processor and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to realize the operation event identification method of any one of claims 1 to 7.

10. A readable storage medium, characterized by, The readable storage medium comprises a computer program, and the computer program controls the electronic device where the readable storage medium is located to execute the operation event identification method of any one of claims 1 to 7 when running.

Images