A material transportation management method and system based on artificial intelligence

Abstract

The present invention relates to a material transportation management method and system based on artificial intelligence, the method comprising determining the standard loading position of material bags according to the parameter information of a truck compartment; obtaining the stacking image corresponding to each layer of material bags in the truck compartment and the actual loading position of each material bag; calculating the overall center of gravity offset according to the standard loading position and the actual loading position; binarizing the stacking image to obtain the overall tipping degree of the corresponding layer of material bags; calculating the position correction value according to the overall center of gravity offset and the overall tipping degree of at least two layers of material bags below the current layer to be stacked, so as to adjust the loading of the material bags of the current layer to be stacked according to the position correction value. The method according to the present invention solves the current problems of low efficiency and instability in loading material bags.

Description

Technical Field

[0001] The present invention generally relates to the field of automation technology. More specifically, the present invention relates to a material transportation management method and system based on artificial intelligence. Background Art

[0002] In the process of processing grains, it is often necessary to bag and pack the materials before loading them onto trucks for transportation to the next node. Traditionally, material bags are usually loaded into truck boxes manually, which requires a lot of labor and is inefficient. However, automated intelligent loading can be achieved through mechanical automation, which greatly reduces the employment risks of enterprises, while also reducing labor intensity and storage costs.

[0003] The application number is 202010322864.0 and the name of the invention is "A bagged goods palletizing planning system and method for fully automatic loading." It discloses determining the information required for loading, calculating the number of layers of each specification of bags in the car, placing each specification of bags horizontally in the same area, calculating the length of the occupied car area, and arranging them horizontally from front to back according to the actual placement height of the bags. Finally, rationally planning and utilizing the remaining horizontal and vertical space to ensure stable loading.

[0004] However, this solution only determines the amount of cargo that can be accommodated in the compartment based on the information of the vehicle model, and does not involve the dumping problem caused by unreasonable stacking technology during cargo stacking. Bagged cargo often dumps during stacking because the packaging bag material is relatively smooth. If the cargo is stacked only according to the amount of cargo that can be accommodated without stacking adjustments, it may cause the cargo to dump and require reloading, which will seriously reduce the loading efficiency.

[0005] Therefore, how to solve the problem that the existing bagged goods are easy to tip over when loaded, thus resulting in low loading efficiency is a problem that needs to be solved urgently. Summary of the invention

[0006] In order to solve the problem that bagged goods are prone to tipping over when being loaded, the present invention proposes to provide stacking guidance for the current layer to be stacked by calculating the overall center of gravity offset and overall tipping degree corresponding to each layer of material bags in the truck compartment. To this end, the present invention provides solutions in the following aspects.

[0007] In the first aspect, the present invention provides an artificial intelligence-based material transportation management method, comprising: determining a standard loading position of material bags according to parameter information of a truck compartment; obtaining a stacking image corresponding to each layer of material bags in the truck compartment and an actual loading position of each material bag; calculating an overall center of gravity offset according to the standard loading position and the actual loading position; binarizing the stacking image to obtain an overall tipping degree of the corresponding layer of material bags; calculating a position correction value according to the overall center of gravity offset and the overall tipping degree of at least two layers of material bags below the current layer to be stacked, so as to adjust the loading of the material bags in the current layer to be stacked according to the position correction value.

[0008] Beneficial effect: According to the scheme of the present invention, the loading guidance of the current stacking layer can be carried out according to the overall center of gravity offset and the overall tipping degree corresponding to each layer in the truck compartment, so as to realize automatic loading and realize zero-dropping of goods, which can greatly reduce the employment risk of the enterprise, reduce labor intensity, reduce storage costs, and be more efficient when loading.

[0009] Preferably, the control method further comprises: in response to the current layer to be stacked being the second layer, determining the placement position of the material bags of the second layer according to the overall center of gravity offset and overall tilting degree of the material bags of the first layer.

[0010] Beneficial effect: When stacking the second layer, the material bags can be stacked directly according to the conditions of the bottom layer, thereby simplifying the control method of the material loading process and effectively improving the loading efficiency.

[0011] Preferably, determining the placement position of the material bags of the second layer according to the overall center of gravity offset and the overall dumping degree of the material bags of the first layer includes: loading according to a stacking method with the same magnitude, opposite direction and opposite overall dumping degree as the center of gravity offset of the first layer of grain bags; or loading according to the standard loading position.

[0012] Beneficial effect: By providing two different stacking methods, flexible adjustments can be made according to actual conditions when loading materials, effectively improving the flexibility of the application of the control method.

[0013] Preferably, the method of calculating the position correction value based on the overall center of gravity offset and the overall dumping degree of at least two layers of material bags below the current layer to be stacked, and adjusting the loading of the material bags in the current layer to be stacked according to the position correction value includes: in response to the current layer to be stacked being greater than or equal to the third layer, calculating the difference in the overall center of gravity offset of the material bags in the two adjacent layers below the current layer to be stacked, and the difference in the overall dumping degree, so as to determine the loading position of the material bags in the current layer to be stacked.

[0014] Beneficial effect: For material stacking layers above the third layer, stacking guidance can be provided according to the conditions of at least two layers below it, thereby effectively improving the stability of material stacking and improving the loading efficiency of the truck compartment.

[0015] Preferably, the method of determining the loading position of the material bags of the current layer to be stacked includes: if the center of gravity offsets of two adjacent layers below the current layer to be stacked are different in size, opposite in direction and opposite in overall tilting degree, then calculating the current center of gravity offset according to the difference in the overall center of gravity offset, and calculating the current overall tilting degree according to the difference in the overall tilting degree; adjusting the loading position of the material bags of the current layer to be stacked according to the current center of gravity offset and the current overall tilting degree.

[0016] Preferably, calculating the current center of gravity offset based on the difference in the overall center of gravity offsets, and calculating the current overall tipping degree based on the difference in the overall tipping degree include: calculating the average of the overall center of gravity offsets of the material bags in the two adjacent layers below the current layer to be stacked to obtain the current center of gravity offset; and calculating the sum vector of the overall tipping degrees of the material bags in the two adjacent layers below the current layer to be stacked to obtain the current overall tipping degree.

[0017] Preferably, the binarization processing of the stacked image to obtain the overall tipping degree of the corresponding layer of material bags includes: using the Sobel operator to calculate the gradient amplitude and direction of each pixel point to obtain the edge of each material bag in the stacked image; determining the binarized image of the corresponding layer of material bags according to the edge of each material bag; and determining the outline of the material bag according to the binarized image to determine the tipping degree of each material bag.

[0018] Beneficial effect: The image processing process can accurately determine the dumping direction of the material bags in the corresponding layer, which can effectively improve the stability of the material stacking in the layer and improve the loading efficiency.

[0019] Preferably, determining the contour of the material bag based on the binarized image to determine the tipping degree of each material bag includes: judging whether the contour corresponding to each material bag in the binarized image matches the standard contour; in response to the contour corresponding to each material bag not matching the standard contour, determining the tipping degree based on the difference between the contour of each material bag in the binarized image and the standard contour.

[0020] Preferably, calculating the overall center of gravity offset based on the standard loading position and the actual loading position includes: comparing the difference between the standard loading position and the actual loading position of each material bag to determine the center of gravity offset of each material bag; calculating the overall center of gravity offset based on the center of gravity offset of all material bags in the corresponding layer.

[0021] In a second aspect, the present invention also provides an artificial intelligence-based material conveying management system, comprising: a processor; and a memory storing computer instructions for artificial intelligence-based material conveying management, wherein when the computer instructions are executed by the processor, the device executes the artificial intelligence-based material conveying management method described in the foregoing and following texts.

[0022] Beneficial effects of the present invention:

[0023] The loading guidance of the current stacking layer can be carried out according to the overall center of gravity offset and overall tipping degree corresponding to each layer in the truck compartment, so as to control the corresponding mechanical arm or robot for automatic loading and realize zero-drop loading of goods, which can greatly reduce the employment risk of the enterprise, reduce labor intensity, reduce storage costs, and be more efficient when loading. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0025] Figure 1 is a schematic diagram schematically illustrating an application scenario of the material transportation management method based on artificial intelligence according to the present invention;

[0026] Figure 2 is a flow chart schematically illustrating a material transportation management method based on artificial intelligence according to an embodiment of the present invention;

[0027] Figure 3 is a flow chart schematically illustrating a method for stacking control of different layers according to an embodiment of the present invention;

[0028] Figure 4 is a flow chart schematically illustrating a control method when the current layer to be stacked is above the third layer according to an embodiment of the present invention;

[0029] Figure 5 is a flow chart schematically illustrating the use of image processing technology to determine the dumping direction according to an embodiment of the present invention;

[0030] Figure 6 is a schematic diagram schematically illustrating an artificial intelligence-based material transportation management system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0032] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0033] Figure 1 Schematic diagram schematically illustrating an application scenario 100 of the material transportation management method based on artificial intelligence according to the present invention.

[0034] like Figure 1 As shown, after the truck arrives, the vehicle scanning system scans the vehicle (for example, using 3D radar) to locate it and obtain the compartment information (for example, the vehicle license plate number can be photographed by a camera to determine the vehicle model and compartment information). It is suitable for low-barrier vehicles and high-barrier vehicles. After the scanning is completed, different types of chops are generated according to different types of vehicles. Furthermore, the parameter information of the compartment can also be directly input through the manual input device. After the material is bagged by the automatic packaging scale, it passes through the belt conveyor line and enters the oscillation leveling line. After leveling, the material is divided into 2 bags and 1 group, and enters the multi-section conveyor line to be caught.

[0035] The system platform can determine the corresponding stacking type in the carriage based on the acquired vehicle model, carriage information, order information, etc., such as the standard loading position of material bags in the carriage. Then, the next material bags to be stacked are accurately placed according to the actual loading situation of the material bags, thereby ensuring the stability of the material bag stacking and improving the loading efficiency.

[0036] The waiting-to-grab conveyor line transports the grouped materials to the waiting-to-grab station, and the robot grabs them. Each robot grabs 2 bags of materials at a time to load them onto the truck. The two robots load the truck in sections, and the truck drives away after loading. The suspension system under the truck compartment can evenly connect pressure sensors to each spring to determine the stacking situation in the truck.

[0037] The factory entrance and exit no longer need to check paper documents to verify vehicle order information, and there is no need to manually open the gate for the vehicle. Everything is handled automatically by the platform. The vehicle will receive a system reminder when it can enter the factory, and the gate at the factory gate will automatically lift the bar to let it pass.

[0038] Furthermore, there is no need for manual judgment on whether the vehicle is underloaded or overloaded. The platform automatically calculates and judges. If it exceeds the preset threshold, the driver will be reminded, the order process will be blocked, and it will be recorded in the exception log.

[0039] At the same time, corresponding monitoring equipment can be set up in the factory area, and the monitoring information can be uploaded to the monitoring service center, so that the system platform can obtain the monitoring information and monitor the situation in the factory area. Furthermore, the system platform can also exchange information with the data application center to update the latest order information, vehicle model information, factory area situation, etc. At the same time, the situation in the factory area can be managed through the data application center, and interaction with external personnel can be established through web services, such as truck drivers, customers who place orders, etc.

[0040] Next, the AI-based material transport management principle implemented in this system platform will be described in detail.

[0041] Figure 2 2 is a flow chart schematically showing a material transportation management method 200 based on artificial intelligence according to an embodiment of the present invention. According to the context of the present invention, the present invention only shows the material bag as a grain bag for the purpose of example, and in actual application, it can also be other forms of bagged materials. Based on this, the method of the present invention can be used in any production of bagged materials.

[0042] like Figure 2 As shown, at step S201, the standard loading position of the material bags is determined according to the parameter information of the truck compartment. When the truck arrives at the factory gate, the commercial truck license plate is scanned and matched with the body data in the database (including the truck load and cargo box height). The truck stops at the designated location, automatically scans the body contour, and outputs the position coordinates to transmit to the robot arm control central system. At the same time, the standard loading position can be automatically generated according to the corresponding order information and compartment information to facilitate the stacking of material bags. In some embodiments, the standard loading position may include a position determined according to the parameter information of the compartment, or it may be a standard loading position comprehensively generated based on the stacked material bags, or it may be a standard loading position for each layer determined according to the stamping type.

[0043] At step S202, the stacking image corresponding to each layer of material bags in the truck compartment and the actual loading position of each material bag are obtained. After the truck arrives at the designated position, the manipulator begins to grab the grain bags and load them. Although according to the set stacking method, the manipulator needs to grab the grain bags to the set position (such as the standard loading position), the irregularity and fluidity of the bagged materials may cause the center to deviate and fall in a certain direction during actual placement. Therefore, there will be a difference between the actual loading position and the standard loading position, which is also the main factor leading to stacking instability.

[0044] At step S203, the overall center of gravity offset is calculated based on the standard loading position and the actual loading position. In some embodiments, the difference between the standard loading position and the actual loading position of each material bag can be compared to determine the center of gravity offset of each material bag, and the overall center of gravity offset is calculated based on the center of gravity offsets of all material bags in the corresponding layer.

[0045] In some embodiments, a first quadrant coordinate system can be established based on the lower left corner of the carriage as the origin and the two adjacent sides of the carriage as the x-axis and y-axis. The position of the grain bag specified before loading is recorded, and the coordinates of the center of gravity of each bag of grain are determined. The grain bag is generally a regular rectangle, and its center of gravity coordinates are located at the intersection of the two diagonals. Use an industrial camera to take pictures of the positions of the grain bags after the first layer of grain bags are loaded. Since the position of the grain bag may be offset from the specified position during the loading process, the actual coordinates of the center of gravity of the grain bag after loading are collected at this time to construct a single grain bag center of gravity offset vector.

[0046] The starting points of the offset vectors of all grain bags are translated to the coordinates of the theoretical center of gravity of the first layer of grain bags. Based on the idea of ​​force synthesis, the resultant vector of the offset vectors of all grain bags can be obtained. The end point coordinates of the resultant vector are the actual center of gravity coordinates of the first layer of grain bags as a whole, and the modulus of the vector is the offset of the center of gravity of the entire grain bag.

[0047] At step S204, the stacked image is binarized to obtain the overall dumping degree of the corresponding layer of material bags. In some embodiments, the image of each layer of grain bags is processed to obtain the gathering direction of grain particles inside the grain bag, thereby determining the dumping direction of the entire grain bag as the overall dumping degree.

[0048] At step S205, a position correction value is calculated based on the overall center of gravity offset and overall dumping degree of at least two layers of material bags below the current layer to be stacked, so as to adjust the loading of the material bags of the current layer to be stacked according to the position correction value. In some embodiments, the loading of the next layer of grain bags can be guided according to the center of gravity offset and overall dumping degree of the previous layer of grain bags.

[0049] Figure 3 is a flow chart schematically illustrating a method 300 for stacking control of different layers according to an embodiment of the present invention.

[0050] like Figure 3 As shown, in step S301, in response to the current layer to be stacked being the second layer, the placement position of the material bags of the second layer is determined according to the overall center of gravity offset and overall dumping degree of the material bags of the first layer. In some embodiments, loading is performed according to a stacking method with the same center of gravity offset as the first layer of grain bags, opposite direction, and opposite overall dumping degree, or loading is performed according to the standard loading position.

[0051] In step S302, in response to the current layer to be stacked being greater than or equal to the third layer, the difference in overall center of gravity offset and overall dumping degree of material bags in two adjacent layers below the current layer to be stacked are calculated to determine the loading position of the material bags in the current layer to be stacked.

[0052] In some embodiments, taking the stacking of the third layer as an example, the center of gravity offset and the overall tilting degree after the second layer of grain bags are loaded can be measured by the same method as in step S203 and step S204. If the center of gravity offset of the second layer and the first layer of grain bags are the same in magnitude and opposite in direction and the overall tilting degree is opposite, then the stacking is considered stable at this time, and the grain bags are subsequently placed according to the corrected position.

[0053] If the center of gravity offset of the second layer and the first layer of grain bags are different in size, direction and overall tipping degree, it is necessary to calculate the current center offset and overall tipping degree based on the results of this loading, and continue to guide the loading of the third layer until the offset is 0 or the loading is completed.

[0054] Figure 4 4 is a flow chart schematically illustrating a control method 400 when the current layer to be stacked is above the third layer according to an embodiment of the present invention.

[0055] like Figure 4 As shown, at step S401, if the gravity center offsets of the two adjacent layers below the current layer to be stacked are different in size, opposite in direction and opposite in overall tilting degree, the current gravity center offset is calculated according to the difference in the overall gravity center offset, and the current overall tilting degree is calculated according to the difference in overall tilting degree. In some embodiments, the mean of the overall gravity center offsets of the material bags in the two adjacent layers below the current layer to be stacked is calculated to obtain the current gravity center offset. The sum vector of the overall tilting degrees of the material bags in the two adjacent layers below the current layer to be stacked is calculated to obtain the current overall tilting degree.

[0056] At step S402, the loading position of the material bags of the current layer to be stacked is adjusted according to the current center of gravity offset and the current overall dumping degree. In some embodiments, the material bags can be stacked in a manner such that the center of gravity offset is 0 according to the mean value of the calculated center variation, thereby reducing the continuous offset of the overall center of gravity during stacking.

[0057] Figure 5 FIG. 5 is a flow chart schematically illustrating a method of determining a falling direction 500 by using image processing technology according to an embodiment of the present invention.

[0058] like Figure 5 As shown, at step S501, the gradient magnitude and direction of each pixel point are calculated using the Sobel operator to obtain the edge of each material bag in the stacking image.

[0059] At step S502, the binary image of the corresponding layer of material bags is determined according to the edge of each material bag. In some embodiments, the whole grain bag can be photographed with a high-resolution digital camera, and the contour of each grain bag image can be obtained using Canny edge detection.

[0060] Specifically, the size of the carriage can be proportionally reduced to the image of the entire grain bag, and the image of a single grain bag can be determined by the actual size of the grain bag. One of the grain bag images is selected, and the original image is Gaussian filtered to remove noise. Then, the Sobel operator is applied to the filtered image to calculate the gradient magnitude and direction of each pixel. In this embodiment, the Sobel operator is an image processing algorithm used to detect edges in an image. It is a discrete differential operator that determines the gradient magnitude and direction of a point by calculating the difference in pixel values ​​around the pixel.

[0061] According to the gradient direction, non-maximum suppression is performed on each pixel to retain the pixel with the maximum gradient magnitude and suppress those pixels that are not on the edge. The basic idea of ​​non-maximum suppression is to traverse each pixel after edge detection and compare it with the surrounding pixels, and only retain the pixel with the maximum gradient magnitude as the true edge.

[0062] Select a high threshold and a low threshold. Pixels are divided into three categories: strong edge, weak edge, and non-edge. Pixels with gradient magnitude greater than the high threshold are marked as strong edges, those less than the low threshold are marked as non-edges, and those between the two are marked as weak edges. Pixels with gradient magnitudes lower than the low threshold are suppressed and not considered edge points; pixels higher than the high threshold are defined as strong edges and retained as edge points; pixels between the high and low thresholds are defined as weak edges and reserved for further processing.

[0063] Use strong edges to filter weak edges. By performing connectivity analysis on weak edge pixels, weak edge pixels connected to strong edges are also marked as edges, i.e., true edge points. If the weak edge is an isolated edge, it is a non-edge. The final result is a binary image, where white represents an edge and black represents a non-edge.

[0064] Specifically, in step S503, it is determined whether the contour corresponding to each material bag in the binary image matches the standard contour.

[0065] At step S504, in response to the fact that the contour corresponding to each material bag does not match the standard contour, the degree of tipping is determined according to the difference between the contour of each material bag in the binary image and the standard contour. For example, a normally stacked material bag will present a relatively regular rectangle at the edge of the binary image. If a corner of the rectangle is no longer a straight structure, it can be determined that the material bag is tilted in the irregular direction, that is, the tipping direction of the material bag. Further, based on the combined effect of the force, the tipping direction of the corresponding layer as a whole can be determined.

[0066] Figure 6 Schematic diagram schematically illustrating an artificial intelligence-based material transportation management system 600 according to an embodiment of the present invention.

[0067] In another aspect of the present invention, there is also provided an artificial intelligence-based material conveying management system, comprising: a processor; and a memory storing computer instructions for artificial intelligence-based material conveying management, wherein when the computer instructions are executed by the processor, the device executes the artificial intelligence-based material conveying management method described in one or more of the foregoing embodiments.

[0068] Furthermore, the control system may also include a vehicle scanning device, a grabbing device, an order parsing device, a monitoring device, etc., so that the acquired information can be integrated to perform artificial intelligence-based material transportation management. Since all of the above devices can be implemented through existing technologies, they will not be repeated in this embodiment.

[0069] like Figure 6 As shown in , the core of the control system includes a device 601. The device 601 may include a CPU 6011, which may be a general-purpose CPU, a dedicated CPU, or other information processing and program execution unit. Further, the device 601 may also include a large-capacity memory 6012 and a read-only memory ROM 6013, wherein the large-capacity memory 6012 may be configured to store various types of data and various programs required for the multimedia network, and the ROM 6013 may be configured to store the power-on self-test of the device 601, the initialization of each functional module in the system, the basic input / output driver of the system, and the data required to boot the operating system.

[0070] Further, the device 601 also includes other hardware platforms or components, such as the TPU (Tensor Processing Unit) 6014, GPU (Graphic Processing Unit) 6015, FPGA (Field Programmable Gate Array) 6016 and MLU (Memory Logic Unit) 6017. It is understood that although a variety of hardware platforms or components are shown in the device 601, they are only exemplary and not restrictive, and those skilled in the art can add or remove corresponding hardware according to actual needs. For example, the device 601 may only include a CPU as a well-known hardware platform and another hardware platform as a test hardware platform of the present invention.

[0071] The device 601 of the present invention further includes a communication interface 6018, so that it can be connected to a local area network / wireless local area network (LAN / WLAN) 605 through the communication interface 6018, and then connected to a local server 606 or to the Internet ("Internet") 607 through the LAN / WLAN. Alternatively or additionally, the device 601 of the present invention can also be directly connected to the Internet or a cellular network through the communication interface 6018 based on wireless communication technology, such as wireless communication technology based on the third generation ("3G"), the fourth generation ("4G") or the fifth generation ("5G") . In some application scenarios, the device 601 of the present invention can also access a server 608 and a possible database 609 of an external network as needed.

[0072] The peripheral devices of the device 601 may include a display device 602, an input device 603, and a data transmission interface 604. In one embodiment, the display device 602 may include, for example, one or more speakers and / or one or more visual displays. The input device 603 may include, for example, a keyboard, a mouse, a microphone, a gesture capture camera, or other input buttons or controls, which are configured to receive input of data or user instructions. The data transmission interface 604 may include, for example, a serial interface, a parallel interface or a universal serial bus interface ("USB"), a small computer system interface ("SCSI"), a serial ATA, a FireWire ("FireWire"), a PCI Express, and a high-definition multimedia interface ("HDMI"), etc., which are configured for data transmission and interaction with other devices or systems.

[0073] The CPU 6011, the mass storage 6012, the read-only memory ROM 6013, the TPU 6014, the GPU 6015, the FPGA 6016, the MLU 6017 and the communication interface 6018 of the device 601 of the present invention can be connected to each other through a bus 6019, and data interaction with peripheral devices can be achieved through the bus. In one embodiment, through the bus 6019, the CPU 6011 can control other hardware components in the device 601 and its peripheral devices.

[0074] During operation, the processor CPU 6011 of the device 601 of the present invention can obtain a media data packet through the input device 603 or the data transmission interface 604, and retrieve the computer program instructions or codes stored in the memory 6012 to calculate the center of gravity offset and dumping direction of the material bag.

[0075] As can be seen from the above description of the modular design of the present invention, the system of the present invention can be flexibly arranged according to the application scenario or demand without being limited to the architecture shown in the accompanying drawings. Further, it should be understood that any module, unit, component, server, computer or device that performs the operation of the present invention example may include or otherwise access a computer-readable medium, such as a storage medium, a computer storage medium or a data storage device (removable) and / or non-removable) such as a disk, an optical disk or a tape. Computer storage media may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules or other data.

[0076] Based on this, the present invention also discloses a computer-readable storage medium, on which computer-readable instructions for artificial intelligence-based material transportation management are stored. When the computer-readable instructions are executed by one or more processors, the artificial intelligence-based material transportation management method as described in one or more embodiments above is implemented.

[0077] Although this specification has shown and described a plurality of embodiments of the present invention, it is apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, modifications and alternatives without departing from the thought and spirit of the present invention. It should be understood that in the process of practicing the present invention, various alternatives to the embodiments of the present invention described herein may be adopted. The attached claims are intended to define the scope of protection of the present invention, and therefore cover the modular composition, equivalent or alternatives within the scope of these claims.

[0078] Although this specification has shown and described a plurality of embodiments of the present invention, it is apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, modifications and alternatives without departing from the thought and spirit of the present invention. It should be understood that in the process of practicing the present invention, various alternatives to the embodiments of the present invention described herein may be adopted. The attached claims are intended to define the scope of protection of the present invention, and therefore cover the modular composition, equivalent or alternatives within the scope of these claims.

Claims

1. A material transportation management method based on artificial intelligence, characterized in that: include: Determine the standard loading position of the material bags according to the parameter information of the truck compartment; Obtaining a stacking image corresponding to each layer of material bags in a truck compartment and an actual loading position of each material bag; the material bags are used to load grains; Calculate the overall center of gravity offset according to the standard loading position and the actual loading position; Binarization is performed on the stacking image to obtain the overall dumping degree of the material bags in the corresponding layer; In response to the current layer to be stacked being the second layer, determining the placement position of the material bags of the second layer according to the overall center of gravity offset and the overall tilting degree of the material bags of the first layer; In response to the current layer to be stacked being greater than or equal to the third layer, a position correction value is calculated based on the overall center of gravity offset and overall tipping degree of at least two layers of material bags below the current layer to be stacked, so as to adjust the loading of the material bags in the current layer to be stacked according to the position correction value.

2. The material transportation management method based on artificial intelligence according to claim 1 is characterized in that: The step of determining the placement position of the material bags of the second layer according to the overall center of gravity offset and overall tilting degree of the material bags of the first layer comprises: The loading is performed according to a stacking method with the same magnitude of center of gravity offset, opposite direction and opposite overall dumping degree as the first layer of material bags; or the loading is performed according to the standard loading position.

3. The material transportation management method based on artificial intelligence according to claim 1 is characterized in that: In response to the current layer to be stacked being greater than or equal to the third layer, calculating a position correction value according to the overall center of gravity offset and overall tilting degree of at least two layers of material bags below the current layer to be stacked, and adjusting the loading of the material bags of the current layer to be stacked according to the position correction value includes: In response to the current layer to be stacked being greater than or equal to the third layer, the difference in overall center of gravity offset and overall dumping degree of material bags in two adjacent layers below the current layer to be stacked are calculated to determine the loading position of the material bags in the current layer to be stacked.

4. The material transportation management method based on artificial intelligence according to claim 3 is characterized in that: Determining the loading position of the material bags of the current layer to be stacked includes: If the gravity center offsets of the two adjacent layers below the current layer to be stacked are different in size, opposite in direction and opposite in overall tilting degree, the current gravity center offset is calculated according to the difference in the overall gravity center offset, and the current overall tilting degree is calculated according to the difference in the overall tilting degree; The loading position of the material bags of the current layer to be stacked is adjusted according to the current center of gravity offset and the current overall dumping degree.

5. The material transportation management method based on artificial intelligence according to claim 4 is characterized in that: The calculating of the current center of gravity offset according to the difference in the overall center of gravity offset, and the calculating of the current overall tilting degree according to the difference in the overall tilting degree include: Calculate the mean of the overall center of gravity offset of the material bags in the two adjacent layers below the current layer to be stacked to obtain the current center of gravity offset; and calculate the sum vector of the overall dumping degree of the material bags in the two adjacent layers below the current layer to be stacked to obtain the current overall dumping degree.

6. The material transportation management method based on artificial intelligence according to claim 1 is characterized in that: The binarization process of the stacking image to obtain the overall dumping degree of the corresponding layer of material bags includes: The Sobel operator is used to calculate the gradient magnitude and direction of each pixel to obtain the edge of each material bag in the stacking image; Determine the binary image of the corresponding layer of material bags according to the edge of each material bag; The contour of the material bag is determined according to the binary image to determine the pouring degree of each material bag.

7. The material transportation management method based on artificial intelligence according to claim 6 is characterized in that: Determining the contour of the material bag according to the binary image to determine the dumping degree of each material bag includes: Determine whether the contour corresponding to each material bag in the binary image matches the standard contour; In response to the contour corresponding to each material bag not matching the standard contour, the dumping degree is determined according to the difference between the contour of each material bag in the binarized image and the standard contour.

8. The material transportation management method based on artificial intelligence according to claim 1 is characterized in that: The calculating of the overall center of gravity offset according to the standard loading position and the actual loading position comprises: Compare the difference between the standard loading position and the actual loading position of each material bag to determine the center of gravity offset of each material bag; The overall center of gravity offset is calculated based on the center of gravity offsets of all material bags in the corresponding layer.

9. A material transportation management system based on artificial intelligence, characterized in that: include: processor; and a memory storing computer instructions for artificial intelligence-based material transportation management, wherein when the computer instructions are executed by the processor, the device executes the artificial intelligence-based material transportation management method according to any one of claims 1-8.

Images