Vehicle load status identification method, device, computer equipment and medium

By acquiring and calculating load state recognition parameters and combining with the vehicle load state recognition model, the problem of load data error is solved, and the accuracy and automation of vehicle load state recognition are improved.

CN113128929BActive Publication Date: 2024-11-05SHANGHAI YUNYOU TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110360951.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-04-02
Publication Date
2024-11-05
Estimated Expiration
2041-04-02

AI Technical Summary

Technical Problem

When identifying the load state of a vehicle, the load data is susceptible to various factors, resulting in large errors and reducing the recognition accuracy.

Method used

By obtaining the loading point address, unloading point address, and driving behavior data of the vehicle performing freight tasks, calculate the load status identification parameters, including the average distance between the vehicle and the loading point and the unloading point, the average driving speed and the average load data, enter the vehicle load capacity, and enter the load capacity of the vehicle The state recognition model is used to establish a load state recognition model based on historical data, train and calibrate, and then identify the load state of the vehicle.

Benefits of technology

It improves the accuracy of vehicle load status identification, reduces the impact of load data error on identification results, enhances the degree of automation, and ensures that the identification results are closely related to the vehicle driving characteristics.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113128929B_ABST
    Figure CN113128929B_ABST
Patent Text Reader

Abstract

The present disclosure provides a method, device, computer equipment and medium for identifying the load status of a vehicle. The method includes: obtaining the loading point address, unloading point address and driving behavior data of the freight task performed by the vehicle, wherein the driving behavior data includes the driving speed, load data and vehicle position data of the vehicle during the freight task; obtaining load status identification parameters based on the loading point address, unloading point address and driving behavior data of the freight task performed by the vehicle; inputting the load status identification parameters into the vehicle load status identification model, and obtaining the vehicle load status from the vehicle load status identification model. The embodiments of the present disclosure improve the recognition accuracy of the vehicle load status.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle management technology, and more specifically, to a method, device, computer equipment and medium for identifying a vehicle load status. Background Art

[0002] The vehicle load status refers to the load status of the vehicle during the freight mission. Generally speaking, the vehicle load status includes empty, loaded, fully loaded and unloaded. The purpose of identifying the vehicle load status includes vehicle scheduling, and the arrangement of loading and unloading time during the vehicle's freight mission. At present, when performing load status identification, the vehicle load status is mainly identified by vehicle load data. If the load data is within a low level range, the vehicle load status is empty; if the load data is within a high level range, the vehicle load status is fully loaded. However, the detected load data is affected by many factors. For example, the signal of the load data detected after the vehicle enters a mountainous area or a tunnel is easy to be lost, the load data is too large when the vehicle climbs a slope and too small when it goes downhill, and the load data will increase or decrease suddenly when the road is bumpy. The error of the detected load data can easily lead to the identification result of the vehicle load status not being consistent with the actual load status of the vehicle, which reduces the recognition accuracy of the vehicle load status.

[0003] Public Content

[0004] In view of this, the present disclosure provides a method, apparatus, computer device and medium for identifying the load status of a vehicle, which improves the accuracy of identifying the load status of the vehicle.

[0005] According to one aspect of the present disclosure, a method for identifying a vehicle load state is provided, comprising:

[0006] Obtaining the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle, wherein the driving behavior data includes the driving speed, load data, and vehicle position data of the vehicle during the performance of the freight task;

[0007] Based on the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle, a load state identification parameter is obtained;

[0008] The load state identification parameters are input into a vehicle load state identification model, and the load state of the vehicle is obtained from the vehicle load state identification model.

[0009] Optionally, the obtaining of the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle includes:

[0010] Acquire driving behavior data of the vehicle at a current moment during execution of the freight mission, and driving behavior data of at least one adjacent moment before the current moment;

[0011] The load state identification parameters obtained based on the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle include:

[0012] Based on the location data of the vehicle, the loading point address and the unloading point address, calculate the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point at the current moment, and the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point at at least one adjacent moment before the current moment;

[0013] Calculate the mean of the distance between the vehicle and the loading point, the mean of the distance between the vehicle and the unloading point, the mean of the driving speed, and the mean of the load data at the current moment and at least one adjacent moment before the current moment, and obtain the load status identification parameters at the current moment.

[0014] Optionally, after calculating the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point at the current moment, and the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point at at least one adjacent moment before the current moment based on the location data of the vehicle, the loading point address, the unloading point address, and the driving behavior data of the freight task performed by the vehicle, obtaining the load state identification parameter further includes:

[0015] Calibrate the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point, the driving speed and the load data at the current moment and at least one adjacent moment before the current moment.

[0016] Optionally, before inputting the load state identification parameter into a vehicle load state identification model and obtaining the load state of the vehicle by the vehicle load state identification model, the identification method further comprises:

[0017] A vehicle load state recognition model is established.

[0018] Optionally, the establishing the vehicle load state recognition model includes:

[0019] Establishing a vehicle load state recognition target model for the vehicle;

[0020] Based on the loading point address, unloading point address, and driving behavior data of freight tasks performed by the vehicle in the past, the vehicle load status recognition target model is trained to obtain a vehicle load status recognition model of the vehicle.

[0021] Optionally, the training of the vehicle load state recognition target model based on the loading point address, unloading point address, and driving behavior data of freight tasks performed by the vehicle in the past to obtain the vehicle load state recognition model of the vehicle includes:

[0022] Obtain historical loading point addresses, historical unloading point addresses, and historical driving behavior data of freight tasks performed by the vehicle in the past;

[0023] Based on the historical loading point address, the historical unloading point address, and the historical driving behavior data, a load state recognition training parameter is obtained;

[0024] Obtain the historical load status of the vehicle during the period when the vehicle performed the freight mission in history;

[0025] A training set and a test set are obtained from the historical load status and the load status recognition training parameters, and the vehicle load status recognition model is obtained based on the training set and the test set.

[0026] Optionally, obtaining the load state recognition training parameters based on the historical loading point address, the historical unloading point address, and the historical driving behavior data includes:

[0027] Based on the historical vehicle position data during the period when the vehicle performed the freight mission in the past, the historical loading point address and the historical unloading point address, calculate the distance between the vehicle and the historical loading point and the distance between the vehicle and the historical unloading point during the period when the vehicle performed the freight mission in the past;

[0028] Calculate the mean of the distance between the vehicle and the historical loading point, the mean of the distance between the vehicle and the historical unloading point, the mean of the historical driving speed and the mean of the historical load data at the historical moments during the vehicle's performance of freight missions and at least one adjacent moment before the historical moment, and obtain the load status recognition training parameters at the historical moments.

[0029] Optionally, after calculating the distance between the vehicle and the historical loading point and the distance between the vehicle and the historical unloading point during the period when the vehicle performed the freight mission in history based on the historical vehicle position data, the historical loading point address and the historical unloading point address during the period when the vehicle performed the freight mission in history, the obtaining of the load state recognition training parameters based on the historical loading point address, the historical unloading point address and the historical driving behavior data further includes:

[0030] Calibrate the distance between the vehicle and the historical loading point, the distance between the vehicle and the historical unloading point, the historical driving speed and the historical load data during the period when the vehicle performed the freight mission in history.

[0031] Optionally, the acquiring of the historical load status of the vehicle during the period when the vehicle performed a freight mission in history includes:

[0032] Clustering historical load data of the vehicle during the period of performing freight tasks in the past to obtain cluster labels of the historical load data;

[0033] Obtaining a change trend of the historical load data of the vehicle according to the clustering labels of the historical load data;

[0034] Data fitting is performed on the variation trend of the historical load data of the vehicle, and the historical load status of the vehicle when performing freight tasks in the past is obtained from the fitting curve.

[0035] Optionally, before clustering the historical load data of the vehicle during the period when the vehicle performed the freight mission in the past to obtain the cluster label of the historical load data, obtaining the historical load status of the vehicle during the period when the vehicle performed the freight mission in the past also includes:

[0036] Obtain the estimated task start time and estimated task end time of the vehicle performing the freight task in history;

[0037] Expanding the estimated task start time and the estimated task end time to obtain the effective task execution time of the vehicle performing the freight task in history;

[0038] Based on the maximum load capacity of the vehicle, valid historical load capacity data is screened out from the historical load capacity data within the effective mission execution time of the vehicle.

[0039] According to one aspect of the present disclosure, there is provided a device for identifying a vehicle load status, comprising:

[0040] A load state identification parameter acquisition unit, used to obtain a load state identification parameter based on a loading point address, an unloading point address, and driving behavior data of a freight task performed by a vehicle, wherein the driving behavior data includes a driving speed, load data, and vehicle position data of the vehicle during the performance of the freight task;

[0041] The vehicle load state identification unit is used to input the load state identification parameters into a vehicle load state identification model, and obtain the load state of the vehicle from the vehicle load state identification model.

[0042] According to one aspect of the present disclosure, a computer device is provided, including: a memory for storing computer executable codes; and a processor for executing the computer executable codes to implement the method described above.

[0043] According to one aspect of the present disclosure, a computer-readable medium is provided, comprising a computer-executable code, wherein the computer-executable code implements the method described above when executed by a processor.

[0044] In the disclosed embodiment, the load state identification parameter is input into the vehicle load state identification model, and the vehicle load state is obtained by the vehicle load state identification model. The load state identification parameter is obtained based on the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle. The driving behavior data includes the driving speed, load data, and vehicle position data of the vehicle during the freight task. In the process of obtaining the vehicle load state from the vehicle load state identification model, it does not rely on manual labor, which improves the degree of automation. Since the identification of the vehicle load state depends not only on the vehicle load data, but also on the driving speed and vehicle position data of the vehicle during the freight task, as well as the loading point address and unloading point address corresponding to the freight task, the identified load state is more closely related to the vehicle driving characteristics (load data, driving speed, and vehicle position data) during the freight task, and is more targeted, thereby improving the accuracy of the identified vehicle load state. Compared with identifying the vehicle load status by relying solely on the vehicle load data, the vehicle load status identification method of the disclosed embodiment reduces the impact of the vehicle load data error on the vehicle load status identification result, thereby improving the accuracy of the identified vehicle load status. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and other objects, features and advantages of the present disclosure will become more apparent through the description of the embodiments of the present disclosure with reference to the following drawings, in which:

[0046] Figure 1 A system architecture diagram is shown for use in a method for identifying a vehicle load status according to an embodiment of the present disclosure.

[0047] Figure 2 A diagram showing the interaction of internal modules of a data acquisition module according to one embodiment of the present disclosure.

[0048] Figure 3 A flow chart of a method for identifying a vehicle load status according to an embodiment of the present disclosure is shown.

[0049] Figure 4 A flow chart of a method for establishing a vehicle load status recognition model according to an embodiment of the present disclosure is shown.

[0050] Figure 5 A flow chart of a method for establishing a vehicle load status recognition model according to an embodiment of the present disclosure is shown.

[0051] Figure 6 A flow chart of a method for acquiring historical load status according to an embodiment of the present disclosure is shown.

[0052] Figure 7 A visualization diagram of historical load status according to one embodiment of the present disclosure is shown.

[0053] Figure 8 A schematic structural diagram of a vehicle load status identification device according to an embodiment of the present disclosure is shown.

[0054] Fig. 9 A schematic structural diagram of a vehicle load status identification and control device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0055] The present disclosure is described below based on embodiments, but the present disclosure is not limited to these embodiments. In the detailed description of the present disclosure below, some specific details are described in detail. It is possible for a person skilled in the art to fully understand the present disclosure without the description of these details. In order to avoid confusing the essence of the present disclosure, well-known methods, processes, and procedures are not described in detail. In addition, the drawings are not necessarily drawn to scale.

[0056] Figure 1 The system architecture diagram of the vehicle load state recognition method according to the embodiment of the present disclosure is shown. The system architecture 100 includes a vehicle load state recognition server 110 and a database 120. The vehicle load state recognition server 110 includes a data acquisition module 111, a model training module 112 and a vehicle load state recognition module 113.

[0057] The vehicle load status is the loading condition of the vehicle during the execution of the freight task. The freight task refers to the task of transporting the specified freight object from the loading point address to the unloading point address. In the execution of the freight task, the vehicle's load status includes empty, loaded, fully loaded and unloaded. Empty is the load status of the vehicle before the vehicle goes to the loading point or after leaving the unloading point when the vehicle is not loaded with the freight object. Fully loaded is the load status of the vehicle during the process of transporting the freight object from the loading point to the unloading point when the vehicle is fully loaded with the freight object. Loading is the process of the vehicle loading the freight object at the loading point, during which the vehicle's load status changes from empty to fully loaded. Unloading is the process of the vehicle unloading the freight object at the unloading point, during which the vehicle's load status changes from fully loaded to empty. In the execution of the freight task, the vehicle generates driving behavior data, and the database 120 is used to store the driving behavior data generated by the vehicle.

[0058] The vehicle load state recognition server 110 is used to identify the load state of the vehicle. Among them, the data collection module 111 is used to collect the driving behavior data of the vehicle during the execution of the freight task, and store the collected driving behavior data in the database 120. The model training module 112 is used to obtain the historical load state of the vehicle based on the historical load data of the vehicle during the execution of the freight task in the past, and store the historical load state in the database 120. It is also used to establish a vehicle load state recognition model for the vehicle based on the historical loading point address, historical unloading point address, historical driving behavior data and historical load state of the freight tasks performed by the vehicle in the past. The vehicle load state recognition module 113 is used to identify the vehicle load state at the current moment based on the loading point address and unloading point address corresponding to the freight task being performed by the vehicle, as well as the driving behavior data during the execution of the freight task, using the vehicle load state recognition model.

[0059] The above-mentioned vehicle load status recognition server 110 can be embodied in the form of a single computer, or a collection of multiple computers, or in the form of a cloud. When the vehicle load status recognition server 110 is embodied as a collection of multiple computers, the multiple computers cooperate with each other and each completes a part of the vehicle load status recognition work. When the vehicle load status recognition server 110 is embodied in the form of a cloud, it is composed of a series of computers or parts of computers on the cloud.

[0060] The above-mentioned data acquisition module 111, model training module 112 and vehicle load state recognition module 113 can be a single computer, or a part of a single computer, such as a virtual machine partitioned from a single physical machine. In some cases, the vehicle load state recognition server 110 can be a single computer, and the data acquisition module 111, model training module 112 and vehicle load state recognition module 113 can be virtual machines partitioned from the computer.

[0061] Figure 2 FIG. 1 shows the interaction of the internal modules of the data acquisition module according to one embodiment of the present disclosure. Figure 2 As shown, the data acquisition module 111 includes a microprocessor 210 , a weight sensor 220 , a GPS module 230 , a speed sensor 240 , a GPRS communication module 250 , a memory 260 , a communication interface 270 , a Beidou module 280 and an APP program interface 290 .

[0062] The driving behavior data collected by the data acquisition module 111 include the driving speed, load data, and vehicle position data of the vehicle during the freight mission. The microprocessor 210 is a processor for realizing the control of collecting driving behavior data. The weight sensor 220 is used to detect the load data of the vehicle during the freight mission. The GPS module 230 is a positioning model using the global positioning system. The Beidou module 280 is a positioning module using the Chinese Beidou satellite navigation system. The GPS module 230 and the Beidou module 280 are used to collect the vehicle position data during the freight mission. The speed sensor 240 is used to detect the driving speed of the vehicle during the freight mission. The GPRS (General Radio Packet Service) communication module 250 and the communication interface 270 realize the data transmission between the data acquisition module 111 and the database 120. The memory 260 is used to store the driving behavior data collected by the weight sensor 220, the GPS module 230, the Beidou module 280, and the speed sensor 240. For example, the memory 260 is a cache memory. The APP program interface 290 is used to communicate with a local client, and an application APP for viewing the recognition result of the vehicle load status, driving behavior data and other information is installed in the local client.

[0063] Figure 3 A flow chart of a method for identifying a vehicle load state according to an embodiment of the present disclosure is shown. The method for identifying a vehicle load state provided in the embodiment of the present disclosure may be executed by a vehicle load state identification server 110. The method for identifying a vehicle load state provided in the embodiment of the present disclosure specifically comprises the following steps:

[0064] In step 310, the loading point address, unloading point address, and driving behavior data of the freight mission performed by the vehicle are obtained, wherein the driving behavior data includes the driving speed, load data, and vehicle position data of the vehicle during the execution of the freight mission.

[0065] In this step, the loading point address and the unloading point address of the freight task being performed by the vehicle are obtained, and the driving behavior data of the vehicle at the current moment during the performance of the freight task and the driving behavior data of at least one adjacent moment before the current moment are obtained. The driving behavior data includes the driving speed, load data and vehicle position data of the vehicle during the performance of the freight task. This step can be performed by the data acquisition module 111.

[0066] The load state of a vehicle has continuity and mutation. That is, the load state of the vehicle (one of empty, loaded, fully loaded and unloaded) lasts for a long time during the period when the vehicle performs a freight mission, while the change of the load state (for example, from empty to loaded) is a sudden change. Therefore, the load state of the vehicle at the current moment can be predicted in real time with the help of the load state of the vehicle at at least one adjacent moment before the current moment when the vehicle performs the freight mission. Considering the predictability of the vehicle load state recognition model used to identify the vehicle load state, when acquiring the driving behavior data of the freight mission performed by the vehicle, not only the driving behavior data of the vehicle at the current moment during the freight mission is acquired, but also the driving behavior data of at least one adjacent moment before the current moment is acquired.

[0067] In step 320, based on the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle, load state identification parameters are obtained.

[0068] In this step, based on the driving behavior data of the vehicle at the current moment during the execution of the freight task, the driving behavior data of at least one adjacent moment before the current moment, and the loading point address and unloading point address corresponding to the freight task, the load state identification parameter at the current moment is obtained. This step can be performed by the vehicle load state identification module 113.

[0069] In some embodiments, based on the location data of the vehicle, the address of the loading point and the address of the unloading point, the distance between the vehicle and the loading point and the distance between the vehicle and the unloading point at the current moment, and the distance between the vehicle and the loading point and the distance between the vehicle and the unloading point at at least one adjacent moment before the current moment are calculated. The average of the distance between the vehicle and the loading point at the current moment and at least one adjacent moment before the current moment is calculated, the average of the distance between the vehicle and the unloading point at the current moment and at least one adjacent moment before the current moment is calculated, the average of the driving speed at the current moment and at least one adjacent moment before the current moment is calculated, and the average of the load data at the current moment and at least one adjacent moment before the current moment is calculated. The load state identification parameter at the current moment is obtained by the average of the distance between the vehicle and the loading point, the average of the distance between the vehicle and the unloading point, the average of the driving speed and the average of the load data.

[0070] In some embodiments, based on the location data of the vehicle, the address of the loading point and the address of the unloading point, after calculating the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point at the current moment, and the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point at at least one adjacent moment before the current moment, then calibrate the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point, the driving speed and the load data at the current moment, and the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point, the driving speed and the load data at at least one adjacent moment before the current moment. For example, the distance between the vehicle and the loading point at the current moment is calibrated as the distance between the vehicle and the loading point at the current moment divided by the distance between the loading point and the unloading point. The distance between the vehicle and the loading point at at least one adjacent moment before the current moment is calibrated as the distance between the vehicle and the loading point at at least one adjacent moment before the current moment divided by the distance between the loading point and the unloading point. The distance between the vehicle and the unloading point at the current moment is calibrated as the distance between the vehicle and the unloading point at the current moment divided by the distance between the loading point and the unloading point. The distance between the vehicle and the unloading point at at least one adjacent moment before the current moment is calibrated as the distance between the vehicle and the unloading point at at least one adjacent moment before the current moment divided by the distance between the loading point and the unloading point. The driving speed of the vehicle at the current moment is calibrated as the driving speed divided by the first calibration value, the unit of the driving speed is kilometers per hour, and the first calibration value is, for example, 80. The driving speed of the vehicle at at least one adjacent moment before the current moment is calibrated as the driving speed divided by the first calibration value. The load data of the vehicle at the current moment is calibrated as the driving speed divided by the second calibration value, the unit of the load data is kilograms, and the second calibration value is, for example, 3200. The load data of the vehicle at at least one adjacent moment before the current moment is calibrated as the load data divided by the second calibration value.

[0071] In some embodiments, before executing step 330, the method for identifying the vehicle load status further includes: establishing a vehicle load status identification model. Figure 4 A flowchart of a method for establishing a vehicle load state recognition model according to an embodiment of the present disclosure is shown. The method for establishing a vehicle load state recognition model provided in the embodiment of the present disclosure can be executed by the model training module 112. The method for establishing a vehicle load state recognition model provided in the embodiment of the present disclosure specifically includes the following steps:

[0072] In step 410, a vehicle load status recognition target model of the vehicle is established.

[0073] In this step, a vehicle load state recognition target model of the vehicle is established based on a machine learning algorithm. For example, the machine learning algorithm is a random forest algorithm. Since the random forest algorithm is an existing technology, it will not be described in detail here.

[0074] In step 420, based on the loading point address, unloading point address, and driving behavior data of freight tasks performed by the vehicle in the past, the vehicle load status recognition target model is trained to obtain a vehicle load status recognition model of the vehicle.

[0075] In this step, based on the driving behavior data of the vehicle during the historical freight missions, the loading point addresses and unloading point addresses corresponding to the freight missions performed by the vehicle in the past, the vehicle load state recognition target model is trained to obtain the vehicle load state recognition model of the vehicle. It should be noted that, considering that the vehicle has a relatively fixed driving route and driving habits, the vehicle load state recognition model is established for different vehicles in the embodiment of the present disclosure, and the recognition of the vehicle load state is also based on the different driving characteristics of different vehicles.

[0076] Figure 5 A flowchart of a method for establishing a vehicle load state recognition model according to an embodiment of the present disclosure is shown, and specifically discloses a process of training a vehicle load state recognition target model to obtain a vehicle load state recognition model of the vehicle. The method for establishing a vehicle load state recognition model provided by the embodiment of the present disclosure specifically includes the following steps:

[0077] In step S510, historical loading point addresses, historical unloading point addresses, and historical driving behavior data of freight tasks performed by the vehicle in the past are obtained.

[0078] In this step, the historical loading point addresses and historical unloading point addresses of the freight tasks performed by the vehicle in the past are obtained, and the historical driving behavior data of the vehicle at historical moments during the performance of the freight tasks in the past and the historical driving behavior data of at least one adjacent moment before the historical moment are obtained.

[0079] In step S520, based on the historical loading point address, the historical unloading point address, and the historical driving behavior data, load state recognition training parameters are obtained.

[0080] In this step, based on the historical driving behavior data of the vehicle at historical moments during the execution of freight tasks in history, the historical driving behavior data of at least one adjacent moment before the historical moment, and the historical loading point addresses and historical unloading point addresses corresponding to the freight tasks performed by the vehicle in history, the load status recognition training parameters at the historical moment are obtained.

[0081] In some embodiments, based on the historical vehicle position data, historical loading point address and historical unloading point address of the vehicle during the historical period of the vehicle performing the freight mission, the distance between the vehicle and the historical loading point and the distance between the vehicle and the historical unloading point during the historical period of the vehicle performing the freight mission are calculated. The average of the distance between the vehicle and the historical loading point at the historical moment during the historical period of the vehicle performing the freight mission and at least one adjacent moment before the historical moment is calculated, the average of the distance between the vehicle and the historical unloading point at the historical moment during the historical period of the vehicle performing the freight mission and at least one adjacent moment before the historical moment is calculated, the average of the historical driving speed at the historical moment during the historical period of the vehicle performing the freight mission and at least one adjacent moment before the historical moment is calculated, and the average of the historical load data at the historical moment during the historical period of the vehicle performing the freight mission and at least one adjacent moment before the historical moment is calculated. The load state recognition training parameters at the historical moment are obtained by the average of the distance between the vehicle and the historical loading point, the average of the distance between the vehicle and the historical unloading point, the average of the historical driving speed and the average of the historical load data.

[0082] In some embodiments, based on the historical vehicle position data, historical loading point addresses, and historical unloading point addresses of the vehicle during the historical period when the vehicle performed freight tasks, the distance between the vehicle and the historical loading point and the distance between the vehicle and the historical unloading point during the historical period when the vehicle performed freight tasks are calculated, and then the distance between the vehicle and the historical loading point, the distance between the vehicle and the historical unloading point, the historical driving speed, and the historical load data during the historical period when the vehicle performed freight tasks are calibrated. The calibration method of the distance between the vehicle and the historical loading point, the distance between the vehicle and the historical unloading point, the historical driving speed, and the historical load data during the historical period when the vehicle performed freight tasks is the same as Figure 3 The distance between the vehicle and the loading point, the distance between the vehicle and the unloading point, the driving speed and the load data at the current moment described in step 320 are consistent with the calibration method of the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point, the driving speed and the load data at at least one adjacent moment before the current moment, and will not be repeated here.

[0083] In step S530, the historical load status of the vehicle during the period when the vehicle performed the freight mission in the past is obtained.

[0084] In this step, the historical load status of the vehicle during the vehicle's historical performance of freight missions is obtained. Figure 6 A flowchart of a method for obtaining a historical load status according to an embodiment of the present disclosure is shown. The method for obtaining a historical load status provided by the embodiment of the present disclosure specifically includes the following steps:

[0085] In step S610, the estimated task start time and the estimated task end time of the vehicle in performing the freight task in history are obtained; the estimated task start time and the estimated task end time are expanded to obtain the effective task execution time of the vehicle in performing the freight task in history; based on the maximum load weight of the vehicle, the valid historical load data is filtered out from the historical load data within the effective task execution time of the vehicle.

[0086] In this step, the estimated task start time and the estimated task end time of the vehicle's historical freight task are obtained; the estimated task start time is the time when the vehicle is expected to start performing the freight task. The estimated task end time is the time when the vehicle is expected to complete the freight task. Since the estimated task start time and the estimated task end time are usually estimated times filled in manually, there will be a situation where the estimated task end time is earlier than the unloading completion time. In order to avoid the situation where the estimated task end time is earlier than the unloading completion time, the estimated task start time and the estimated task end time are extended to obtain the effective task execution time of the vehicle performing the freight task in history; for example, the estimated task start time is extended forward by 8 hours, and the estimated task end time is extended backward by 8 hours. Since the vehicle transportation efficiency should be maximized as much as possible, that is, the weight of the freight object carried by the vehicle during the execution of the freight task is generally close to the maximum load capacity of the vehicle. Therefore, based on the maximum load capacity of the vehicle, the effective historical load data is screened out from the historical load data within the effective task execution time of the vehicle. For example, if the maximum load capacity of a vehicle is 35,000 kg, you can set the interval [0 kg, 10,000 kg] ∪ [20,000 kg, 40,000 kg] to filter the historical load data of empty vehicles and the historical load data of fully loaded vehicles. In the historical load data within the effective task execution time of the vehicle, filter out the historical load data in the interval [0 kg, 10,000 kg] ∪ [20,000 kg, 40,000 kg] to obtain valid historical load data.

[0087] In step S620, the historical load data of the vehicle during the period of performing freight tasks in the past are clustered to obtain cluster labels of the historical load data.

[0088] In this step, the historical load data of the vehicle during the historical freight mission are clustered to obtain the cluster labels of the historical load data. In some embodiments, the historical load data is clustered using the K-means clustering algorithm. After clustering, the historical load data is classified, and the cluster labels of the historical load data are obtained according to the classification results. For example, the target number of mean centers is 2. After clustering, the historical load data is divided into historical high load data and historical low load data, and the historical high load data is labeled "1" and the historical low load data is labeled "0". Since the K-means clustering algorithm is an existing technology, it will not be described in detail.

[0089] In step S630, the change trend of the historical load data of the vehicle is obtained according to the clustering labels of the historical load data.

[0090] In this step, the change trend of the historical load data of the vehicle is obtained according to the clustering labels of the historical load data. It should be noted that, for a freight task of loading and unloading, the change trend of the load data of the vehicle during the execution of the freight task usually includes a five-stage quasi-trapezoidal change trend of empty-loading-full-unloading-empty. It is easy to understand that the five-stage quasi-trapezoidal change trend of empty-loading-full-unloading-empty can be divided into two change trends of empty-loading-full and full-unloading-empty. Usually, according to the clustering labels of the historical load data, if the clustering labels of the historical load data of the vehicle meet the "low-high-low" three-stage change trend of 0-1-0, then the change trend of the historical load data of the vehicle meets the above-mentioned five-stage quasi-trapezoidal change trend, and then step S640 is executed. If the clustering label of the vehicle's historical load data does not satisfy the "low-high-low" three-stage change trend of 0-1-0, then the change trend of the vehicle's historical load data does not satisfy the above-mentioned five-stage trapezoidal change trend, and it is necessary to return to execute steps S610 to S630, and adjust the extended time of the expected task start time and the expected task end time in step S610 to obtain the effective task execution time of the vehicle's historical freight task.

[0091] In step S640, data fitting is performed on the variation trend of the historical load data of the vehicle, and the historical load status of the vehicle when performing freight tasks in the past is obtained from the fitting curve.

[0092] In this step, data fitting is performed on the change trend of the historical load data of the vehicle, and the historical load state of the vehicle performing freight tasks in history is obtained from the fitting curve. In some embodiments, the change trend data of the historical load data of the vehicle can be fitted into two change trends such as empty-loaded-full-loaded and full-loaded-unloaded. The following formula (1) shows the fitting curve of the change trend of empty-loaded-full-loaded or full-loaded-unloaded.

[0093]

[0094] Among them, w(t) is the historical load data of the vehicle, t represents the moment. If w0 < w1, t0 is the start time of loading, t1 is the completion time of loading, w0 is the historical load data of the vehicle in the unloaded state before loading, and w1 is the historical load data of the vehicle in the fully loaded state after loading; if w0 > w1, t0 is the start time of unloading, t1 is the completion time of unloading, w0 is the historical load data of the vehicle in the fully loaded state before unloading, and w1 is the historical load data of the vehicle in the unloaded state after unloading. Using the least squares fitting method, the estimated values of t0, t1, w0, and w1 can be obtained.

[0095] From the fitting curve shown in formula (1), the historical load states of the vehicle performing freight tasks in history can be obtained. If w0 < w1, the historical load state of the vehicle during t0 < t < t1 is loading, the historical load state of the vehicle during min(t) ≤ t ≤ t0 is unloaded, and the historical load state of the vehicle during t1 ≤ t ≤ max(t) is fully loaded. If w0 > w1, the historical load state of the vehicle during t0 < t < t1 is unloading, the historical load state of the vehicle during min(t) ≤ t ≤ t0 is fully loaded, and the historical load state of the vehicle during t1 ≤ t ≤ max(t) is unloaded.

[0096] In some embodiments, the change trend data of the historical load data of the vehicle can be fitted into a five-segment trapezoidal-like change trend of unloaded - loading - fully loaded - unloading - unloaded. The fitting curve of the change trend of unloaded - loading - fully loaded - unloading - unloaded is shown in formula (2) as follows.

[0097]

[0098] Among them, w(t) is the historical load data of the vehicle, t represents the moment, t0 is the start time of loading, t1 is the completion time of loading, t2 is the start time of unloading, t3 is the completion time of unloading, w0 is the historical load data of the vehicle in the unloaded state before loading, w1 is the historical load data of the vehicle in the fully loaded state after loading; w2 is the historical load data of the vehicle in the unloaded state after unloading. Using the least squares fitting method, the estimated values of t0, t1, t2, t3, w0, w1, and w2 can be obtained.

[0099] From the fitting curve shown in formula (2), the historical load states of the vehicle performing freight tasks in history can be obtained. The historical load state of the vehicle during min(t) ≤ t ≤ t0 is unloaded, the historical load state of the vehicle during t0 < t < t1 is loading, the historical load state of the vehicle during t1 ≤ t ≤ t2 is fully loaded, the historical load state of the vehicle during t2 < t < t3 is unloading, and the historical load state of the vehicle during t3 ≤ t ≤ max(t) is unloaded.

[0100] Figure 7 FIG. 4 shows a visualization diagram of the historical load status according to an embodiment of the present disclosure. Figure 7 As shown, the horizontal axis is the time when the vehicle has performed freight tasks in history, and the vertical axis is the historical load data of the vehicle. The historical load data of the vehicle has a five-stage trapezoidal change trend of empty-loading-full-load-unloading-empty. The historical load data of the vehicle forms a fitting curve after data fitting. From the fitting curve, it can be seen that 11:00 on August 27 is the starting time of loading, 17:00 on August 27 is the ending time of loading, 07:00 on August 29 is the starting time of unloading, and 16:00 on August 29 is the ending time of unloading. Therefore, the historical load status of the vehicle before 11:00 on August 27 is empty, the historical load status of the vehicle from 11:00 on August 27 to 17:00 on August 27 is loading, the historical load status of the vehicle from 17:00 on August 27 to 07:00 on August 29 is full, the historical load status of the vehicle from 07:00 on August 29 to 16:00 on August 29 is unloading, and the historical load status of the vehicle after 16:00 on August 29 is empty.

[0101] In step S540, a training set and a test set are obtained from the historical load status and the load status recognition training parameters, and the vehicle load status recognition model is obtained based on the training set and the test set.

[0102] In this step, the load state recognition training parameters and their corresponding historical load states are divided into a training set and a test set. Each training sample in the training set includes the load state recognition training parameters at historical moments during the period when the vehicle performed the freight mission in history, and the historical load state at the historical moment, and the historical load state at the historical moment is the label of the load state recognition training parameters at the historical moment. Each training sample in the sample set is input into the vehicle load state recognition target model, and the vehicle load state recognition target model outputs the learned vehicle load state recognition result. A confusion matrix is ​​generated by the vehicle load state recognition result and the label. If the prediction accuracy of the vehicle load state recognition target model is greater than a preset value (e.g., 95%) and the recall rate is greater than a preset value (e.g., 90%) for the training set, it means that the vehicle load state recognition target model is successfully trained. Otherwise, the parameters in the vehicle load state recognition target model are adjusted so that the prediction accuracy of the vehicle load state recognition target model is greater than a preset value (e.g., 95%) and the recall rate is greater than a preset value (e.g., 90%). Among them, the adjustable parameters in the vehicle load state recognition target model include the maximum iteration number of weak learners, the maximum depth of the tree, and the minimum number of samples of leaf nodes.

[0103] When the vehicle load state recognition target model is successfully trained, it generally needs to undergo a testing process before it can be officially put into use. Each test sample in the test set includes the load state recognition training parameters at historical moments during the vehicle's freight mission in history, and the historical load state at the historical moment, and the historical load state at the historical moment is the label of the load state recognition training parameters at the historical moment. During the test, the vehicle load state recognition target model outputs the learned vehicle load state recognition result. A confusion matrix is ​​generated by the vehicle load state recognition result and the label. If for the test set, the prediction accuracy of the vehicle load state recognition target model is greater than a preset value (e.g., 95%) and the recall rate is greater than a preset value (e.g., 90%), it is determined that the vehicle load state recognition target model is successfully trained and a vehicle load state recognition model is obtained, otherwise the above training process is repeated.

[0104] The vehicle load state recognition model can be put into use after training. The vehicle load state recognition parameters at the current moment during the period when the vehicle performs the freight mission are input into the model to obtain the vehicle load state at the current moment.

[0105] In step 330, the load state identification parameters are input into a vehicle load state identification model, and the load state of the vehicle is obtained from the vehicle load state identification model.

[0106] In this step, the load state recognition parameters of the vehicle at the current moment during the performance of the freight mission are input into the vehicle load state recognition model, and the vehicle load state recognition model obtains the load state of the vehicle at the current moment. It should be noted that compared with identifying the load state of the vehicle through an image recognition model, the vehicle load state recognition model of the embodiment of the present disclosure only needs to process driving behavior data. The driving behavior data collected during the performance of the freight mission is less susceptible to the impact of road bumps, environmental humidity, etc. than images, and it requires less computing power and is more efficient.

[0107] Figure 8 The schematic diagram of the structure of the vehicle load state identification device according to one embodiment of the present disclosure is shown. The vehicle load state identification device 800 comprises: a load state identification parameter acquisition unit 810 and a vehicle load state identification unit 820.

[0108] The load status identification parameter acquisition unit 810 is used to obtain the load status identification parameters based on the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle, wherein the driving behavior data includes the driving speed, load data, and vehicle position data of the vehicle during the execution of the freight task; the vehicle load status identification unit 820 is used to input the load status identification parameters into a vehicle load status identification model, and obtain the load status of the vehicle from the vehicle load status identification model.

[0109] Since the implementation details of the above device have been described in the detailed introduction of the method embodiment above, they will not be repeated here for the sake of saving space.

[0110] Fig. 9 A schematic diagram of the structure of a vehicle load status identification and control device according to an embodiment of the present disclosure is shown. Fig. 9 The device shown is only an example and should not constitute any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0111] refer to Fig. 9 , the device includes a processor 910, a memory 920 and an input-output device 930 connected by a bus. The memory 920 includes a read-only memory (ROM) and a random access memory (RAM). The memory 920 stores various computer instructions and data required to perform system functions. The processor 910 reads various computer instructions from the memory 920 to perform various appropriate actions and processes. The input-output device 930 includes an input part such as a keyboard, a mouse, etc.; an output part such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage part such as a hard disk; and a communication part such as a network interface card such as a LAN card, a modem, etc. The memory 920 also stores computer instructions to complete the operations specified in the identification method of the embodiment of the present disclosure.

[0112] Accordingly, an embodiment of the present disclosure provides a computer device, including: a memory, used to store computer executable codes; and a processor, used to execute the computer executable codes to implement the above method.

[0113] Accordingly, an embodiment of the present disclosure provides a computer-readable medium, including a computer-executable code, and the computer-executable code implements the above method when executed by a processor.

[0114] In the disclosed embodiment, the load state identification parameter is input into the vehicle load state identification model, and the vehicle load state is obtained by the vehicle load state identification model. The load state identification parameter is obtained based on the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle. The driving behavior data includes the driving speed, load data, and vehicle position data of the vehicle during the freight task. In the process of obtaining the vehicle load state by the vehicle load state identification model, it does not rely on manual labor, which improves the degree of automation. Since the identification of the vehicle load state depends not only on the vehicle load data, but also on the driving speed and vehicle position data of the vehicle during the freight task, as well as the loading point address and unloading point address corresponding to the freight task, the identified load state is more closely related to the vehicle driving characteristics (load data, driving speed and vehicle position data) during the freight task, and is more targeted, thereby improving the accuracy of the identified vehicle load state. Compared with identifying the vehicle load status by relying solely on the vehicle load data, the vehicle load status identification method of the disclosed embodiment reduces the impact of the vehicle load data error on the vehicle load status identification result, thereby improving the accuracy of the identified vehicle load status.

[0115] The average of the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point, the driving speed and the load data at the current moment and at least one adjacent moment before the current moment are used as the load state identification parameters at the current moment. Considering that the load state of the vehicle is continuous during the execution of the freight mission, the load state of the vehicle at the current moment is predicted in real time by using the load state of the vehicle at at least one adjacent moment before the current moment during the execution of the freight mission, which reduces the real-time requirements of the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point, the driving speed and the load data, and improves the accuracy of the identified vehicle load state.

[0116] In the process of establishing a vehicle load state recognition model, the estimated task start time and estimated task end time of the vehicle's historical freight tasks are obtained; the estimated task start time and the estimated task end time are expanded to obtain the effective task execution time of the vehicle's historical freight tasks; based on the vehicle's maximum load, the effective historical load data is screened out from the historical load data within the vehicle's effective task execution time. The start time of the effective task execution time is earlier than the estimated task start time, and the end time is later than the estimated task end time, which reduces the time accuracy requirements for the historical load data and reduces the impact of the error of the historical load data on the recognition results of the historical load state, thereby improving the accuracy of the historical load state of the vehicle during the vehicle's historical freight tasks in the disclosed embodiment.

[0117] The historical load data of vehicles performing freight tasks in history are clustered to obtain cluster labels of the historical load data; the changing trend of the historical load data of the vehicle is obtained based on the cluster labels of the historical load data; data fitting is performed on the changing trend of the historical load data of the vehicle, and the loading start time, loading end time, unloading start time and unloading end time are estimated using the least squares fitting method, so as to accurately obtain the historical load status of the vehicle performing freight tasks in history, thereby improving the recognition accuracy of the vehicle load status recognition model established based on the historical load status.

[0118] The flowcharts and block diagrams in the accompanying drawings illustrate the possible system frameworks, functions and operations of the systems, methods and devices of the embodiments of the present disclosure. The boxes on the flowcharts and block diagrams can represent a module, a program segment or just a piece of code, and the modules, program segments and codes are all executable instructions for implementing the specified logical functions. It should also be noted that the executable instructions for implementing the specified logical functions can be recombined to generate new modules and program segments. Therefore, the boxes and the order of the boxes in the accompanying drawings are only used to better illustrate the processes and steps of the embodiments, and should not be used as a limitation on the invention itself.

[0119] The above descriptions are only some embodiments of the present disclosure and are not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for identifying a vehicle load state, comprising: Acquire the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle, wherein the driving behavior data includes the driving speed, load data, and vehicle position data of the vehicle during the period when the vehicle performs the freight task, wherein the load data is the load data of the vehicle collected by a weight sensor during the period when the vehicle performs the freight task; Based on the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle, a load state identification parameter at the current moment is obtained, wherein the load state identification parameter at the current moment includes the average value of the distance between the vehicle and the loading point at the current moment and at least one adjacent moment before the current moment, the average value of the distance between the vehicle and the unloading point, the average value of the driving speed, and the average value of the load data; The load state identification parameter at the current moment is input into the vehicle load state identification model of the vehicle, and the load state of the vehicle at the current moment is obtained from the vehicle load state identification model, wherein the load state includes empty, loaded, fully loaded and unloaded, and different vehicles have different vehicle load state identification models. Among them, the empty load refers to the load state of the vehicle before the vehicle goes to the loading point or after leaving the unloading point when the vehicle is not loaded with freight objects; the fully loaded refers to the load state of the vehicle during the process of transporting freight objects from the loading point to the unloading point when the vehicle is fully loaded with freight objects; the loading refers to the process of the vehicle loading freight objects at the loading point, and the load state of the vehicle changes from empty to fully loaded; the unloading refers to the process of the vehicle unloading freight objects at the unloading point, and the load state of the vehicle changes from fully loaded to empty. The obtaining of the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle includes: obtaining the driving behavior data of the vehicle at the current moment during the performance of the freight task, and the driving behavior data of at least one adjacent moment before the current moment, The load state identification parameters at the current moment obtained based on the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle include: Based on the location data of the vehicle, the loading point address and the unloading point address, calculate the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point at the current moment, and the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point at at least one adjacent moment before the current moment; and Calculate the mean of the distance between the vehicle and the loading point, the mean of the distance between the vehicle and the unloading point, the mean of the driving speed, and the mean of the load data at the current moment and at least one adjacent moment before the current moment, and obtain the load status identification parameters at the current moment.

2. The identification method according to claim 1, wherein: After calculating the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point at the current moment, and the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point at at least one adjacent moment before the current moment based on the location data of the vehicle, the loading point address, the unloading point address, and the driving behavior data of the freight task performed by the vehicle, the load state identification parameter at the current moment is obtained, which further includes: Calibrate the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point, the driving speed and the load data at the current moment and at least one adjacent moment before the current moment.

3. The identification method according to claim 1, wherein: Before inputting the load state recognition parameter at the current moment into the vehicle load state recognition model of the vehicle and obtaining the load state of the vehicle at the current moment by the vehicle load state recognition model, the recognition method further comprises: A vehicle load state recognition model is established.

4. The identification method according to claim 3, wherein: The establishing of the vehicle load state recognition model comprises: Establishing a vehicle load state recognition target model for the vehicle; Based on the loading point address, unloading point address, and driving behavior data of freight tasks performed by the vehicle in the past, the vehicle load status recognition target model is trained to obtain a vehicle load status recognition model of the vehicle.

5. The identification method according to claim 4, wherein: The vehicle load state recognition target model is trained based on the loading point address, unloading point address, and driving behavior data of the freight tasks performed by the vehicle in the past, and the vehicle load state recognition model is obtained, which includes: Obtain historical loading point addresses, historical unloading point addresses, and historical driving behavior data of freight tasks performed by the vehicle in the past; Based on the historical loading point address, the historical unloading point address, and the historical driving behavior data, a load state recognition training parameter is obtained; Obtain the historical load status of the vehicle during the period when the vehicle performed the freight mission in history; A training set and a test set are obtained from the historical load status and the load status recognition training parameters, and the vehicle load status recognition model is obtained based on the training set and the test set.

6. The identification method according to claim 5, wherein: The load state recognition training parameters obtained based on the historical loading point address, the historical unloading point address, and the historical driving behavior data include: Based on the historical vehicle position data during the period when the vehicle performed the freight mission in the past, the historical loading point address and the historical unloading point address, calculate the distance between the vehicle and the historical loading point and the distance between the vehicle and the historical unloading point during the period when the vehicle performed the freight mission in the past; Calculate the mean of the distance between the vehicle and the historical loading point, the mean of the distance between the vehicle and the historical unloading point, the mean of the historical driving speed and the mean of the historical load data at the historical moments during the vehicle's performance of freight missions and at least one adjacent moment before the historical moment, and obtain the load status recognition training parameters at the historical moments.

7. The identification method according to claim 6, wherein: After calculating the distance between the vehicle and the historical loading point and the distance between the vehicle and the historical unloading point during the period when the vehicle performed the freight mission in history based on the historical vehicle position data, the historical loading point address and the historical unloading point address during the period when the vehicle performed the freight mission in history, the load state recognition training parameters obtained based on the historical loading point address, the historical unloading point address and the historical driving behavior data also include: Calibrate the distance between the vehicle and the historical loading point, the distance between the vehicle and the historical unloading point, the historical driving speed and the historical load data during the period when the vehicle performed the freight mission in history.

8. The identification method according to claim 5, wherein: The obtaining of the historical load status of the vehicle during the period when the vehicle performed the freight mission in history includes: Clustering historical load data of the vehicle during the period of performing freight tasks in the past to obtain cluster labels of the historical load data; Obtaining a change trend of the historical load data of the vehicle according to the clustering labels of the historical load data; Data fitting is performed on the variation trend of the historical load data of the vehicle, and the historical load status of the vehicle when performing freight tasks in the past is obtained from the fitting curve.

9. The identification method according to claim 8, wherein: Before clustering the historical load data of the vehicle during the period when the vehicle performed the freight mission in the past to obtain the cluster label of the historical load data, obtaining the historical load status of the vehicle during the period when the vehicle performed the freight mission in the past also includes: Obtain the estimated task start time and estimated task end time of the vehicle performing the freight task in history; Expanding the estimated task start time and the estimated task end time to obtain the effective task execution time of the vehicle performing the freight task in history; Based on the maximum load capacity of the vehicle, valid historical load capacity data is screened out from the historical load capacity data within the effective mission execution time of the vehicle.

10. A vehicle load status recognition device, comprising: a load state identification parameter acquisition unit, used for acquiring the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle, and obtaining the load state identification parameters at the current moment based on the loading point address, unloading point address, and driving behavior data of the freight task performed by the vehicle, wherein the driving behavior data includes the driving speed, load data, and vehicle position data of the vehicle during the period when the vehicle performs the freight task, wherein the load data is the load data of the vehicle collected by a weight sensor during the period when the vehicle performs the freight task, and the load state identification parameters at the current moment include the average of the distance between the vehicle and the loading point at the current moment and at least one adjacent moment before the current moment, the average of the distance between the vehicle and the unloading point, the average of the driving speed, and the average of the load data; The vehicle load state recognition unit is used to input the load state recognition parameters at the current moment into the vehicle load state recognition model of the vehicle, and obtain the load state of the vehicle at the current moment from the vehicle load state recognition model, wherein the load state includes empty, loaded, fully loaded and unloaded, and different vehicles have different vehicle load state recognition models. Among them, the empty load refers to the load state of the vehicle before the vehicle goes to the loading point or after leaving the unloading point when the vehicle is not loaded with freight objects; the fully loaded refers to the load state of the vehicle during the process of transporting freight objects from the loading point to the unloading point when the vehicle is fully loaded with freight objects; the loading refers to the process of the vehicle loading freight objects at the loading point, and the load state of the vehicle changes from empty to fully loaded; the unloading refers to the process of the vehicle unloading freight objects at the unloading point, and the load state of the vehicle changes from fully loaded to empty. The load state identification parameter acquisition unit is used to: acquire the driving behavior data of the vehicle at a current moment during the execution of the freight task, and the driving behavior data of at least one adjacent moment before the current moment, The load status identification parameter acquisition unit is used for: Based on the location data of the vehicle, the loading point address and the unloading point address, calculate the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point at the current moment, and the distance between the vehicle and the loading point, the distance between the vehicle and the unloading point at at least one adjacent moment before the current moment; and Calculate the mean of the distance between the vehicle and the loading point, the mean of the distance between the vehicle and the unloading point, the mean of the driving speed, and the mean of the load data at the current moment and at least one adjacent moment before the current moment, and obtain the load status identification parameters at the current moment.

11. A computer device comprising: A memory for storing computer executable code; A processor, configured to execute the computer executable code to implement the method according to any one of claims 1 to 9.

12. A computer readable medium, characterized in that The invention comprises computer executable codes, which implement the method according to any one of claims 1 to 9 when being executed by a processor.