A method, device, equipment and medium for sorting and conveying equipment directly distributed from a power supply station

Abstract

The present application discloses a method, device, equipment and medium for sorting and conveying equipment directly distributed by a power supply station. The present application obtains a barcode collision probability model for each first transmission path; the barcode collision probability model is obtained based on the historical equipment transportation data statistics of all the first transmission paths; the first equipment to be packaged is classified, and the first equipment is placed on the corresponding conveyor belt according to the classification result; the classification result includes the position to be placed of the first equipment; with the conveyor belt as the starting point and the position to be placed as the end point, the optimal transmission path for the first equipment is searched from all the first transmission paths according to the barcode collision probability model. Through the present application, the equipment transportation efficiency can be improved while reducing the probability of the barcode falling or being damaged due to collision, thereby improving the accuracy of equipment sorting.

Description

Technical Field

[0001] The present application relates to the field of logistics automation, and in particular to a method, device, equipment and medium for sorting and conveying equipment directly distributed from a power supply station. Background Art

[0002] In order to improve the delivery efficiency of direct distribution equipment from power stations and reduce labor costs, existing technologies have achieved a certain degree of automation.

[0003] However, to prevent barcode collisions during conveyor belt transport, current equipment dispatch from power stations requires serial dispatch routes for each type of equipment, or requires a small amount of manual real-time inspection. This serial assembly line not only wastes the utilization of sorting and conveying equipment, but also significantly impacts the normal operation of the assembly line if a single piece of equipment fails, resulting in low sorting efficiency.

[0004] Therefore, how to plan parallel and cross-sectional production lines to improve the equipment transportation efficiency while reducing the risk of barcodes falling or being damaged due to collision has become a technical problem that needs to be solved. Summary of the Invention

[0005] The present application provides a method, device, equipment and medium for sorting and conveying equipment directly distributed by a power supply station, so as to solve the technical problem of how to improve the equipment conveying efficiency while reducing the risk of barcodes falling or being damaged due to collision by planning parallel and cross-sectional assembly lines.

[0006] In order to solve the above technical problems, in a first aspect, an embodiment of the present application provides a method for sorting and conveying equipment directly distributed from a power supply station, comprising:

[0007] Obtaining a barcode collision probability model for each first transmission path; the barcode collision probability model is obtained based on historical device transmission data statistics of all first transmission paths;

[0008] Classifying the first devices to be packaged and placing the first devices on corresponding conveyor belts according to the classification results; the classification results include the positions of the first devices to be placed;

[0009] With the conveyor belt as a starting point and the position to be placed as an end point, an optimal transmission path of the first device is searched from all the first transmission paths according to the barcode collision probability model.

[0010] Compared with the existing technology, the embodiments of the present application have the following beneficial effects: through historical equipment transportation data, the probability of barcode collision in each first transmission path of the equipment during the assembly line transportation is obtained, so as to predict and avoid high-risk paths where barcode collisions may occur, thereby greatly reducing the frequency of barcode collisions and ensuring that the information of the equipment is accurate during the transportation process; based on the classification results, the corresponding conveyor belt is used to transport the equipment, and the equipment is transported through the optimal transmission path, which improves the transportation efficiency while improving the accuracy of equipment sorting.

[0011] In some embodiments of the first aspect of the present application, the barcode collision probability model is obtained based on statistics of historical device transmission data of all the first transmission paths, and includes:

[0012] Obtaining a first probability model of overlap between a first transmission path and another transmission path based on the historical device transmission data, wherein the first transmission path is any feasible transmission path;

[0013] Acquire, based on the historical device transport data, a second probability model of the barcode being on the side of the corresponding surface of the device when the device is on the first transmission path;

[0014] The barcode collision probability model of the first transmission path is constructed according to the first probability model and the second probability model.

[0015] Compared to existing technologies, the above embodiment has the following advantages: Factors influencing barcode collisions include whether the corresponding surface of the barcode is tilted due to transport bumps during transport, and the degree of congestion on the same transport section. Therefore, by establishing the probability of overlap between the first transport path and other transport paths and the probability of the corresponding surface of the barcode being tilted, the probability of barcode collision during transport can be accurately estimated, effectively reducing the probability of subsequent barcode collisions.

[0016] In some embodiments of the first aspect of the present application, constructing the barcode collision probability model of the first transmission path according to the first probability model and the second probability model includes:

[0017] The barcode collision probability model is specifically:

[0018] P(collision) = P(overlap) * P(side)

[0019] Among them, P (collision) is a barcode collision probability model when the barcode of the device on the first transmission path is collided; P (overlap) is a first probability model; and P (side) is a second probability model.

[0020] In some embodiments of the first aspect of the present application, classifying the first devices to be packaged and placing the first devices on corresponding conveyor belts according to the classification results includes:

[0021] Acquiring first image data of the first device through an image acquisition unit;

[0022] Inputting the first image data into a pre-trained graph convolutional network to obtain the classification result; the classification result also includes the category of the first device;

[0023] According to the category, the first device is placed on the corresponding conveyor belt.

[0024] Compared with the existing technology, the above embodiment has the following beneficial effects: through image recognition technology, the first device is automatically classified, and the first device is placed on the corresponding conveyor belt according to the classification result, thereby improving the degree of automation of the equipment sorting process and reducing the manual utilization rate.

[0025] In some embodiments of the first aspect of the present application, before placing the first device on the corresponding conveyor belt according to the category, the method further includes:

[0026] The classification result also includes the location where the first device corresponds to the barcode to be attached;

[0027] generating a barcode for the first device according to the category;

[0028] The barcode is placed at the to-be-attached position of the first device.

[0029] Compared with the existing technology, the above embodiment has the following beneficial effects: after obtaining the classification result of the first device through image recognition technology, a barcode of the corresponding device is generated, and the specific location of the barcode in the device is identified, thereby realizing automatic barcode generation and barcode affixing operations, improving the degree of automation of the equipment sorting process and reducing the manual utilization rate.

[0030] In some embodiments of the first aspect of the present application, searching for an optimal transmission path for the first device from all first transmission paths based on the barcode collision probability model with the conveyor belt as the starting point and the to-be-placed position as the end point includes:

[0031] Constructing a cost function according to the barcode collision probability model, and obtaining a path network graph consisting of all the first transmission paths;

[0032] The path network graph is recursively searched starting from the starting point by using the A* algorithm in combination with the cost function until the optimal transmission path is obtained from all the first transmission paths.

[0033] Compared with the existing technology, the above embodiment has the following beneficial effects: by constructing a cost function through a barcode collision probability model, the impact of barcode collision on path selection can be considered in the process of optimizing the transportation path, thereby reducing the barcode collision probability while ensuring transportation efficiency.

[0034] In some embodiments of the first aspect of the present application, constructing a cost function according to the barcode collision probability model includes:

[0035] The cost function is specifically:

[0036] f(n)=g(n)+α×P(n)+h(n)

[0037] Among them, f(n) is the total cost value corresponding to the current recursive node n; g(n) is the cost value from the starting point to the current recursive node n; α is the weight coefficient; P(n) is the barcode collision probability model of the first transmission path corresponding to the previous recursive node to the current recursive node n; h(n) is the cost value from the current recursive node n to the end point.

[0038] In a second aspect, an embodiment of the present application further provides a sorting and conveying device for directly distributing equipment from a power supply station, comprising: a barcode collision probability model acquisition module, an equipment classification module, and a path optimization module;

[0039] The barcode collision probability model acquisition module is used to acquire the barcode collision probability model of each first transmission path; the barcode collision probability model is acquired based on the historical device transmission data statistics of all the first transmission paths;

[0040] The device classification module is used to classify the first devices to be packaged and place the first devices on corresponding conveyor belts according to the classification results; the classification results include the positions of the first devices to be placed;

[0041] The path optimization module is configured to use the conveyor belt as a starting point and the position to be placed as an end point, and to search for an optimal transmission path for the first device from all the first transmission paths according to the barcode collision probability model.

[0042] In a third aspect, the present application also provides a terminal device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the above-mentioned method for sorting and conveying direct distribution equipment of a power supply station is implemented.

[0043] In a fourth aspect, the present application also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned method for sorting and conveying direct distribution equipment of a power supply station. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of a method for sorting and conveying equipment directly distributed from a power station provided in some embodiments of the present application;

[0045] Figure 2 This is a structural schematic diagram of a sorting and conveying device for direct distribution equipment of a power supply station provided in some embodiments of the present application. DETAILED DESCRIPTION

[0046] To prevent barcode collisions during conveyor belt transport, current equipment dispatched directly from power stations requires serial dispatch routes for each type of equipment, or requires a small amount of manual real-time inspection. This serial assembly line not only wastes the utilization of sorting and conveying equipment, but also significantly impacts the normal operation of the assembly line if a single piece of equipment fails, resulting in low sorting efficiency.

[0047] In order to solve the above technical problems, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of this application.

[0048] Example 1

[0049] Please refer to Figure 1 , which is a method for sorting and conveying direct distribution equipment of a power supply station provided in an embodiment of the present application, including S10 to S30, specifically:

[0050] S10: Obtaining a barcode collision probability model for each first transmission path; the barcode collision probability model is obtained based on statistics of historical device transmission data of all the first transmission paths.

[0051] Furthermore, in some embodiments of the present application, the barcode collision probability model is obtained based on statistics of historical device transmission data of all the first transmission paths, and includes:

[0052] Obtaining a first probability model of overlap between a first transmission path and another transmission path based on the historical device transmission data, wherein the first transmission path is any feasible transmission path;

[0053] Acquire, based on the historical device transport data, a second probability model of the barcode being on the side of the corresponding surface of the device when the device is on the first transmission path;

[0054] The barcode collision probability model of the first transmission path is constructed according to the first probability model and the second probability model.

[0055] Factors that influence barcode collisions include whether the corresponding side of the barcode is tilted due to bumps during transport, and the degree of congestion on the same transport section. Therefore, by building the probability of overlap between the first transport path and other transport paths and the probability of the corresponding side of the barcode being tilted, we can accurately estimate the probability of barcode collisions during transport, effectively reducing the probability of subsequent barcode collisions.

[0056] Furthermore, in some embodiments of the present application, constructing the barcode collision probability model of the first transmission path according to the first probability model and the second probability model includes:

[0057] The barcode collision probability model is specifically:

[0058] P(collision) = P(overlap) * P(side)

[0059] Among them, P (collision) is a barcode collision probability model when the barcode of the device on the first transmission path is collided; P (overlap) is a first probability model; and P (side) is a second probability model.

[0060] Preferably, in some embodiments of the present application, the first probability model and the second probability model are obtained by the following preferred implementations:

[0061] During the transportation process, by real-time monitoring of the average transportation density of equipment between every two nodes in the first transportation path (that is, the total number of equipment on the transportation section between the two nodes at any time), when the transportation density of a certain transportation section suddenly increases relative to the previous transportation section, the current transportation section is determined to be an overlapping section, thereby obtaining the number of all overlapping sections in the entire first transportation path, further obtaining the probability that the first transportation path overlaps with other transportation paths, and obtaining a first probability model.

[0062] During the transportation process, the real-time detection device detects the position of the barcode during the transportation process. Specifically, the barcode target can be identified through a barcode scanner or an image recognition device. Furthermore, the statistical device counts the frequency of the barcode being on the side in the overlapping part with other transportation paths during the transportation of the first transportation path, thereby obtaining a second probability model.

[0063] S20: Classify the first devices to be packaged, and place the first devices on corresponding conveyor belts according to the classification results; the classification results include the positions where the first devices are to be placed.

[0064] Preferably, in some embodiments of the present application, the first device includes but is not limited to: an electric energy meter, a smart terminal, a low-voltage transformer and other devices.

[0065] Furthermore, in some embodiments of the present application, classifying the first devices to be packaged and placing the first devices on corresponding conveyor belts according to the classification results includes:

[0066] Acquiring first image data of the first device through an image acquisition unit;

[0067] Inputting the first image data into a pre-trained graph convolutional network to obtain the classification result; the classification result also includes the category of the first device;

[0068] According to the category, the first device is placed on the corresponding conveyor belt.

[0069] Through image recognition technology, the first device is automatically classified and placed on the corresponding conveyor belt according to the classification result, which improves the automation level of the equipment sorting process and reduces the manual utilization rate.

[0070] Preferably, in some embodiments of the present application, an image acquisition unit is provided on a manipulator, and after the first image data of the first device to be packaged is collected by the image acquisition unit, it is necessary to combine a convolutional network to classify the metering assets that need to be sorted. Constructing a convolutional network includes but is not limited to: TensorFlow or PyTorch, designing a network structure, including a convolutional layer, a pooling layer, and a fully connected layer, etc., to extract image features. Further combined with sensors such as weight sensors and other equipment, feature data such as the weight, color, identification, attributes, specifications, and shape of the equipment are obtained, and the image features and the above-mentioned other feature data are input into the convolutional network to obtain classification results. According to the classification results, a control instruction is sent to the manipulator to place the first device on the corresponding conveyor belt, thereby avoiding interference of metering assets in the multi-way transportation process and improving the efficiency and accuracy of classification.

[0071] Preferably, in some embodiments of the present application, after the classification results are obtained, a corresponding number of conveyor belts are started or set according to the classification results.

[0072] Preferably, in some embodiments of the present application, when training a convolutional network, by setting confidence judgment and optimization (such as stochastic gradient descent or cross entropy loss to optimize the performance of the model), even if any image is input into the recognition model, a recognition result within a limited category will be given, and the characteristics and classification rules of different metering assets can be learned, thereby realizing the category recognition of metering assets including electricity meters (in units of boxes), smart terminals (in units of boxes), low-voltage transformers (in units), etc. The training data set can be constructed by photographing the actual first device, obtaining images from an existing database, or using synthetic images.

[0073] Furthermore, in some embodiments of the present application, before placing the first device on the corresponding conveyor belt according to the category, the method further includes:

[0074] The classification result also includes the location where the first device corresponds to the barcode to be attached;

[0075] generating a barcode for the first device according to the category;

[0076] The barcode is placed at the to-be-attached position of the first device.

[0077] Through image recognition technology, after obtaining the classification results of the first device, the barcode of the corresponding device is generated, and the specific location of the barcode in the device is identified, realizing automatic barcode generation and code sticking operations, improving the degree of automation of the equipment sorting process and reducing the manual utilization rate.

[0078] Preferably, in some embodiments of the present application, the classification results output by the convolutional network include but are not limited to: the type of device, the position where the barcode corresponding to the device is to be affixed, and the position where the first device is to be placed.

[0079] Preferably, in some embodiments of the present application, the generated barcode can be printed and pasted to the location to be pasted by, for example, a robotic arm or other automated labeling equipment.

[0080] S30: With the conveyor belt as a starting point and the position to be placed as an end point, searching for an optimal transmission path for the first device from all the first transmission paths according to the barcode collision probability model.

[0081] Furthermore, in some embodiments of the present application, the step of searching for the optimal transmission path of the first device from all the first transmission paths based on the barcode collision probability model with the conveyor belt as the starting point and the position to be placed as the end point includes:

[0082] Constructing a cost function according to the barcode collision probability model, and obtaining a path network graph consisting of all the first transmission paths;

[0083] The path network graph is recursively searched starting from the starting point by using the A* algorithm in combination with the cost function until the optimal transmission path is obtained from all the first transmission paths.

[0084] By constructing a cost function based on the barcode collision probability model, we can consider the impact of barcode collision on path selection in the process of optimizing the transportation path, thereby reducing the barcode collision probability while ensuring transportation efficiency.

[0085] Furthermore, in some embodiments of the present application, constructing a cost function based on the barcode collision probability model includes:

[0086] The cost function is specifically:

[0087] f(n)=g(n)+α×P(n)+h(n)

[0088] Among them, f(n) is the total cost value corresponding to the current recursive node n; g(n) is the cost value from the starting point to the current recursive node n; α is the weight coefficient; P(n) is the barcode collision probability model of the first transmission path corresponding to the previous recursive node to the current recursive node n, that is, P(collision); h(n) is the cost value from the current recursive node n to the end point.

[0089] Preferably, in some embodiments of the present application, the cost value h(n) from the current recursive node n to the end point can be obtained by calculating the Euclidean distance or Manhattan distance from the current node to the end point, preferably by using Manhattan distance calculation.

[0090] Preferably, in some embodiments of the present application, the optimal transmission path is planned according to the A* algorithm through the following preferred implementation:

[0091] S31: Initialize an open list and a closed list, wherein the open list is used to store nodes to be processed, and the closed list is used to store processed nodes, and the nodes are all nodes in the path network graph;

[0092] S32: The conveyor belt where the first device is currently planned is used as the starting point, the position to be placed in the classification result is used as the end point, and the starting point is added to the open list;

[0093] S33: Determine whether there is an end point in the closed list. If so, terminate the recursion and return the optimal transmission path. Otherwise, select the node with the smallest f(n) from the open list as the current recursive node n.

[0094] S34: Generate all neighbor nodes n' of the current recursive node n, and recalculate f(n') and g(n') + α × P(n') for each neighbor node. For the convenience of description, g(n')' = g(n') + α × P(n') in the following text.

[0095] S35: If n' is in the open list and g(n')' corresponding to the current starting node reaching n' is smaller, then update f(n') and the parent node of n', where the parent node is the current recursive node n; otherwise, execute S36;

[0096] S36: If n' is not in the open list, add n' to the open list and record the currently calculated f(n') and the currently recursive node n as its parent node;

[0097] S37: Return to S33.

[0098] From the above, it can be seen that the method for sorting and conveying equipment directly distributed from a power supply station provided in an embodiment of the present application has the following beneficial effects: through historical equipment conveying data, the probability of barcode collision of the equipment in each first transmission path during the assembly line conveying process is obtained, so as to predict and avoid high-risk paths where barcode collisions may occur, thereby greatly reducing the frequency of barcode collisions and ensuring that the information of the equipment is accurate during the conveying process; based on the classification results, the corresponding conveyor belt is used to convey the equipment, and it is conveyed through the optimal transmission path, which improves the conveying efficiency while improving the accuracy of equipment sorting.

[0099] Example 2

[0100] refer to Figure 2 , a power supply station direct distribution equipment sorting and conveying device provided in an embodiment of the present application includes: a barcode collision probability model acquisition module 11, an equipment classification module 12 and a path optimization module 13;

[0101] Furthermore, in some embodiments of the present application, the barcode collision probability model acquisition module 11 is used to obtain the barcode collision probability model of each first transmission path; the barcode collision probability model is obtained based on the historical device transportation data statistics of all the first transmission paths; the device classification module 12 is used to classify the first devices to be packaged, and place the first devices on the corresponding conveyor belt according to the classification results; the classification results include the position to be placed of the first devices; the path optimization module 13 is used to use the conveyor belt as the starting point and the position to be placed as the end point, and search for the optimal transmission path for the first device from all the first transmission paths according to the barcode collision probability model.

[0102] Furthermore, in some embodiments of the present application, the barcode collision probability model is obtained based on statistics of historical device transmission data of all the first transmission paths, and includes:

[0103] Obtaining a first probability model of overlap between a first transmission path and another transmission path based on the historical device transmission data, wherein the first transmission path is any feasible transmission path;

[0104] Acquire, based on the historical device transport data, a second probability model of the barcode being on the side of the corresponding surface of the device when the device is on the first transmission path;

[0105] The barcode collision probability model of the first transmission path is constructed according to the first probability model and the second probability model.

[0106] Furthermore, in some embodiments of the present application, constructing the barcode collision probability model of the first transmission path according to the first probability model and the second probability model includes:

[0107] The barcode collision probability model is specifically:

[0108] P(collision) = P(overlap) * P(side)

[0109] Among them, P (collision) is a barcode collision probability model when the barcode of the device on the first transmission path is collided; P (overlap) is a first probability model; and P (side) is a second probability model.

[0110] Furthermore, in some embodiments of the present application, classifying the first devices to be packaged and placing the first devices on corresponding conveyor belts according to the classification results includes:

[0111] Acquiring first image data of the first device through an image acquisition unit;

[0112] Inputting the first image data into a pre-trained graph convolutional network to obtain the classification result; the classification result also includes the category of the first device;

[0113] According to the category, the first device is placed on the corresponding conveyor belt.

[0114] Furthermore, in some embodiments of the present application, before placing the first device on the corresponding conveyor belt according to the category, the method further includes:

[0115] The classification result also includes the location where the first device corresponds to the barcode to be attached;

[0116] generating a barcode for the first device according to the category;

[0117] The barcode is placed at the to-be-attached position of the first device.

[0118] Furthermore, in some embodiments of the present application, the step of searching for the optimal transmission path of the first device from all the first transmission paths based on the barcode collision probability model with the conveyor belt as the starting point and the position to be placed as the end point includes:

[0119] Constructing a cost function according to the barcode collision probability model, and obtaining a path network graph consisting of all the first transmission paths;

[0120] The path network graph is recursively searched starting from the starting point by using the A* algorithm in combination with the cost function until the optimal transmission path is obtained from all the first transmission paths.

[0121] Furthermore, in some embodiments of the present application, constructing a cost function based on the barcode collision probability model includes:

[0122] The cost function is specifically:

[0123] f(n)=g(n)+α×P(n)+h(n)

[0124] Among them, f(n) is the total cost value corresponding to the current recursive node n; g(n) is the cost value from the starting point to the current recursive node n; α is the weight coefficient; P(n) is the barcode collision probability model of the first transmission path corresponding to the previous recursive node to the current recursive node n; h(n) is the cost value from the current recursive node n to the end point.

[0125] It can be understood that the above-mentioned device embodiment corresponds to the method embodiment of the present invention. The power supply station direct distribution equipment sorting and conveying device provided by the embodiment of the present invention can implement any method embodiment of the present invention, that is, the power supply station direct distribution equipment sorting and conveying method provided in Example 1.

[0126] From the above, it can be seen that the sorting and conveying device for equipment directly distributed from a power supply station provided in the embodiment of the present application has the following beneficial effects: through historical equipment conveying data, the probability of barcode collision of the equipment in each first transmission path during the assembly line conveying process is obtained, so as to predict and avoid high-risk paths where barcode collisions may occur, thereby greatly reducing the frequency of barcode collisions and ensuring that the information of the equipment is accurate during the conveying process; based on the classification results, the corresponding conveyor belt is used to convey the equipment, and it is transported through the optimal transmission path, which improves the conveying efficiency while improving the accuracy of equipment sorting.

[0127] Example 3

[0128] Based on the above-mentioned embodiment of the power supply station direct distribution equipment sorting and conveying method, another embodiment of the present application provides a power supply station direct distribution equipment sorting and conveying terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the power supply station direct distribution equipment sorting and conveying method of any embodiment of the present application is implemented.

[0129] For example, in this embodiment, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present application. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program in the sorting and conveying equipment of the power supply station direct distribution equipment.

[0130] The power station direct distribution equipment sorting and conveying equipment can be a computing device such as a desktop computer, a notebook, a handheld computer, a cloud server, etc. The power station direct distribution equipment sorting and conveying terminal equipment can include, but is not limited to, a processor and a memory.

[0131] The processor can be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor serves as the control center for the power station direct distribution equipment sorting and conveying equipment, connecting the various components of the power station direct distribution equipment sorting and conveying equipment using various interfaces and lines. The memory can be used to store the computer programs and / or modules. The processor implements the various functions of the power station direct distribution equipment sorting and conveying equipment by running or executing the computer programs and / or modules stored in the memory and accessing data stored in the memory. The memory can primarily include a program storage area and a data storage area. The program storage area can store an operating system and at least one application required for a function, etc.; the data storage area can store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory and may also include non-volatile memory, such as a hard disk, memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0132] Example 4

[0133] Based on the above-mentioned embodiment of the method for sorting and conveying equipment directly distributed from a power supply station, another embodiment of the present application provides a storage medium, wherein the storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the method for sorting and conveying equipment directly distributed from a power supply station of any embodiment of the present application.

[0134] In this embodiment, the storage medium is a computer-readable storage medium, and the computer program includes computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0135] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of this application. It should be understood that the above descriptions are merely specific embodiments of this application and are not intended to limit the scope of protection of this application. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this application by those skilled in the art should be included within the scope of protection of this application.

Claims

1. A method for sorting and conveying equipment directly distributed by a power supply station, characterized in that: include: Obtaining a barcode collision probability model for each first transmission path; the barcode collision probability model is obtained based on historical device transmission data statistics of all first transmission paths; Classifying the devices to be packaged and placing the devices on corresponding conveyor belts according to the classification results; the classification results include the locations where the devices are to be placed; Taking the conveyor belt as a starting point and the position to be placed as an end point, searching for an optimal transmission path for the device from all the first transmission paths according to the barcode collision probability model; The barcode collision probability model is obtained based on the historical device transmission data statistics of all the first transmission paths, and includes: Obtaining a first probability model of overlap between a first transmission path and another transmission path based on the historical device transmission data, wherein the first transmission path is any feasible transmission path; Acquire, based on the historical device transport data, a second probability model of the barcode being on the side of the corresponding surface of the device when the device is on the first transmission path; Constructing the barcode collision probability model of the first transmission path according to the first probability model and the second probability model; The constructing the barcode collision probability model of the first transmission path according to the first probability model and the second probability model includes: The barcode collision probability model is specifically: in, a barcode collision probability model for a barcode of a device on the first transmission path being collided; is the first probability model; is the second probability model; The method of taking the conveyor belt as a starting point and the position to be placed as an end point and searching for an optimal transmission path for the device from all the first transmission paths according to the barcode collision probability model comprises: Constructing a cost function according to the barcode collision probability model, and obtaining a path network graph consisting of all the first transmission paths; Recursively searching the path network graph from the starting point using an A* algorithm in combination with the cost function until the optimal transmission path is obtained from all the first transmission paths; The cost function is constructed according to the barcode collision probability model, comprising: The cost function is specifically: in, The current recursive node The corresponding total value; From the starting point to the current recursive node The cost value of is the weight coefficient; From the previous recursive node to the current recursive node a barcode collision probability model corresponding to the first transmission path; The current recursive node The cost to the end point.

2. A method for sorting and transporting equipment directly distributed from a power supply station according to claim 1, characterized in that: The process of classifying the devices to be packaged and placing the devices on corresponding conveyor belts according to the classification results includes: Acquiring first image data of the device through an image acquisition unit; Inputting the first image data into a pre-trained graph convolutional network to obtain the classification result; the classification result also includes the category of the device; According to the category, the device is placed on the corresponding conveyor belt.

3. A method for sorting and transporting equipment directly distributed from a power supply station as claimed in claim 2, characterized in that: Placing the device in front of the corresponding conveyor belt according to the category further includes: The classification result also includes the position of the barcode to be attached to the device; generating a barcode for the device according to the category; The barcode is placed on the to-be-attached position of the device.

4. A sorting and conveying device for direct distribution equipment of a power supply station, characterized in that: include: Barcode collision probability model acquisition module, equipment classification module and path optimization module; The barcode collision probability model acquisition module is used to acquire the barcode collision probability model of each first transmission path; the barcode collision probability model is acquired based on the historical device transmission data statistics of all the first transmission paths; The device classification module is used to classify the devices to be packaged and place the devices on corresponding conveyor belts according to the classification results; the classification results include the positions of the devices to be placed; The path optimization module is configured to use the conveyor belt as a starting point and the position to be placed as an end point, and to search for an optimal transmission path for the device from all the first transmission paths according to the barcode collision probability model; The barcode collision probability model is obtained based on the historical device transmission data statistics of all the first transmission paths, and includes: Obtaining a first probability model of overlap between a first transmission path and another transmission path based on the historical device transmission data, wherein the first transmission path is any feasible transmission path; Acquire, based on the historical device transport data, a second probability model of the barcode being on the side of the corresponding surface of the device when the device is on the first transmission path; Constructing the barcode collision probability model of the first transmission path according to the first probability model and the second probability model; The constructing the barcode collision probability model of the first transmission path according to the first probability model and the second probability model includes: The barcode collision probability model is specifically: in, a barcode collision probability model for a barcode of a device on the first transmission path being collided; is the first probability model; is the second probability model; The method of taking the conveyor belt as a starting point and the position to be placed as an end point and searching for an optimal transmission path for the device from all the first transmission paths according to the barcode collision probability model comprises: Constructing a cost function according to the barcode collision probability model, and obtaining a path network graph consisting of all the first transmission paths; Recursively searching the path network graph from the starting point using an A* algorithm in combination with the cost function until the optimal transmission path is obtained from all the first transmission paths; The cost function is constructed according to the barcode collision probability model, comprising: The cost function is specifically: in, The current recursive node The corresponding total value; From the starting point to the current recursive node The cost value of is the weight coefficient; From the previous recursive node to the current recursive node a barcode collision probability model corresponding to the first transmission path; The current recursive node The cost to the end point.

5. A terminal device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a method for sorting and conveying direct distribution equipment of a power supply station as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a method for sorting and conveying direct distribution equipment of a power supply station as described in any one of claims 1 to 3.

Images