Express return method, device and equipment for automatic express station and storage medium

Abstract

The invention discloses an express return method, device and equipment for an automatic express courier station and a storage medium, relates to the technical field of Internet of Things, and discloses the express return method for the automatic express courier station, and the method comprises the steps: obtaining the image information of each to-be-stored express in real time in the transmission process of the to-be-stored express; based on the image information, judging whether the to-be-stored express is a non-standard express; and if the to-be-stored express is a non-standard express, distributing and transmitting the non-standard express from the main transmission line to a target storage area. According to the method and the device, the non-standard express is identified according to the image information of the to-be-stored express, and the non-standard express is shunted and transmitted to the target storage area from the main transmission line, so that the situation that a transmission machine is stuck due to the non-standard express is avoided, and the operation stability of the automatic express station is improved.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to a courier return method, device, equipment and storage medium of an automatic courier station. Background Art

[0002] In the operation of automated express delivery stations, the handling of non-standard express parcels has become a technical problem that needs to be solved urgently. With the booming e-commerce industry, the shapes and sizes of packages have become more diverse, and many packages do not meet the standard specifications of traditional transmission equipment. These non-standard express parcels are prone to cause the equipment to get stuck when passing through automated transmission equipment, which in turn affects the normal operation of the entire station. For example, in some automated express delivery stations, the size of non-standard express parcels exceeds the handling range of the equipment, which can cause the parcel to get stuck during transmission or even damage the equipment.

[0003] In addition, transmission machine jams require manual intervention, which not only increases maintenance costs but also reduces the efficiency of express delivery processing. This problem is particularly prominent during peak business periods, leading to package backlogs and pickup delays. Therefore, how to effectively solve the transmission problem of non-standard express parcels and improve the operating efficiency and stability of automated express stations has become an important technical challenge facing the current express logistics industry.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a courier return method for an automatic courier station, aiming to solve the technical problem that non-standard express parcels are prone to cause equipment jamming when passing through automated transmission equipment, thereby affecting the normal operation of the automated courier station.

[0006] To achieve the above-mentioned purpose, the present application proposes a courier return method of an automatic courier station, and the courier return method of the automatic courier station comprises: During the transmission process of the express to be stored, the image information of each express to be stored is obtained in real time; Based on the image information, determining whether the express to be stored is a non-standard express; If the express to be stored is a non-standard express, the non-standard express is diverted from the main transmission line and transmitted to the target storage area.

[0007] Optionally, if the express to be stored is a non-standard express, the step of transferring the non-standard express from the main transmission line to the target storage area includes: If the express to be stored is a non-standard express, after the non-standard express is transmitted to the return flow elevator through the main transmission line, the transmission of the main transmission line is stopped, and the preset return flow elevator is started; The non-standard express is diverted from the main transmission line to the return conveyor belt by the return elevator, and the non-standard express is transmitted to the target storage area by the return conveyor belt.

[0008] Optionally, the step of acquiring the image information of each express to be stored in real time during the transmission process of the express to be stored includes: During the transmission process of the express to be stored, determining whether the express to be stored is packed in an express box, wherein there is an express chip on the express box, and the express chip contains various information of the express to be stored; If the express to be stored is packed in an express box, the express chip on the express box is scanned to obtain the express information of the express to be stored, and based on the express information, it is determined whether the express to be stored in the express box is a non-standard express. If the express to be stored in the express box is a non-standard express, a prompt message is sent to the management end to prompt the management to take out the express box. If it is not taken out within a preset time, the express box is diverted from the main transmission line and transmitted to the target storage area; If the express items to be stored are not packed in express boxes, image information of each express item to be stored is acquired in real time.

[0009] Optionally, the step of judging whether the express to be stored is a non-standard express based on the image information includes: Extracting spatial features of the express to be stored based on the image information, wherein the spatial features include size data and posture information; Based on the spatial features, non-standard express delivery is identified and judged through a preset express recognition model to obtain a judgment result, wherein the express recognition model is obtained by iteratively training a preset model to be trained based on express spatial feature samples and recognition result labels of the express spatial feature samples.

[0010] Optionally, before the step of identifying and judging non-standard express delivery based on the spatial features by using a preset express delivery recognition model to obtain a judgment result, the method includes: Obtaining a courier space feature sample and a recognition result label of the courier space feature sample; Based on the express space feature samples and the recognition result labels, the preset model to be trained is iteratively trained to obtain an express recognition model.

[0011] Optionally, the step of iteratively training a preset model to be trained based on the express space feature sample and the recognition result label to obtain an express recognition model includes: Obtaining packaging surface and material information corresponding to the express space feature sample; Determining packaging characteristic weights corresponding to the packaging surface and material information; Based on the express space feature samples, the recognition result labels and the packaging characteristic weights, the preset model to be trained is iteratively trained to obtain an express recognition model.

[0012] Optionally, the step of iteratively training a preset model to be trained based on the express space feature sample, the recognition result label and the packaging characteristic weight to obtain the express recognition model includes: Based on the express space feature samples and the packaging characteristic weights, the non-standard express is identified and judged by a preset model to be trained to obtain a prediction result; Calculate the difference between the prediction result and the recognition result label to obtain an error result; Based on the error result, determining whether the error result meets an error standard indicated by a preset error threshold range; If the error result does not meet the error standard indicated by the preset error threshold range, the model to be trained is updated, and the step of identifying and judging non-standard express based on the express space feature sample and the packaging characteristic weight by the preset model to be trained is returned to obtain a prediction result, and the training is stopped until the error result meets the error standard indicated by the preset error threshold range to obtain an express recognition model.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a courier return device for an automatic courier station, the courier return device for an automatic courier station comprising: An acquisition module, used to acquire image information of each express to be stored in real time during the transmission process of the express to be stored; A judgment module, used for judging whether the express to be stored is a non-standard express based on the image information; The diversion module is used for diverting the non-standard express from the main transmission line to the target storage area if the express to be stored is a non-standard express.

[0014] In addition, to achieve the above-mentioned objectives, the present application also proposes a courier return device for an automatic courier station, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the courier return method for the automatic courier station as described above.

[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the express return method of the automatic express station as described above are implemented.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: Compared with the related art that non-standard express parcels are prone to cause equipment jamming when passing through automated transmission equipment, thereby affecting the normal operation of the entire post station, the present application proposes to obtain image information of each express parcel to be stored in real time during the transmission process of the express parcel to be stored; based on the image information, determine whether the express parcel to be stored is a non-standard express parcel; if the express parcel to be stored is a non-standard express parcel, the non-standard express parcel is diverted from the main transmission line to the target storage area. It is understandable that the present application identifies non-standard express parcels based on the image information of the express parcel to be stored, and diverts the non-standard express parcel from the main transmission line to the target storage area, thereby avoiding the jamming of the transmission machine caused by non-standard express parcels and improving the operational stability of the automatic express post station. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 A flow chart of the first embodiment of the express return method of the automatic express post of the present application; Figure 2 A flow chart of the second embodiment of the express return method of the automatic express post of the present application; Figure 3 This is a schematic diagram of the module structure of the express return device of the automatic express station in the embodiment of the present application; Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the express return method of the automatic express station in the embodiment of the present application.

[0020] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of the embodiment of the present application is: in the transmission process of the express to be stored, the image information of each express to be stored is obtained in real time; based on the image information, it is determined whether the express to be stored is a non-standard express; if the express to be stored is a non-standard express, the non-standard express is diverted from the main transmission line and transmitted to the target storage area.

[0024] In this embodiment, the express return device of the automatic express station is used as the executing body. For the convenience of description, it will be explained below as "device".

[0025] Due to the increasingly diverse shapes and sizes of parcels in related technologies, many parcels do not meet the standard specifications of traditional transmission equipment. These non-standard express parcels are prone to cause the equipment to jam when passing through the automated transmission equipment, thus affecting the normal operation of the entire post station.

[0026] The present application provides a solution to realize the non-standard express return flow of automatic express stations, thereby improving the operational stability of automatic express stations.

[0027] It can be seen from the above embodiments that the present application identifies non-standard express delivery based on the image information of the express delivery to be stored, and diverts the non-standard express delivery from the main transmission line to the target storage area, thereby avoiding the transmission machine being stuck due to non-standard express delivery and improving the operating stability of the automatic express delivery station.

[0028] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a terminal system, etc. that can realize the above functions. The following takes the express return device of the automatic express post as an example to illustrate this embodiment and the following embodiments.

[0029] Based on this, the embodiment of the present application provides a method for returning express delivery to an automatic express delivery station, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the express return method of the automatic express station of the present application.

[0030] In this embodiment, the express return method of the automatic express post includes steps S100 to S300: Step S100, during the transmission process of the express to be stored, image information of each express to be stored is obtained in real time; It should be noted that the express to be stored refers to the express parcel placed on the main conveyor belt of the automatic express station, waiting for the automatic express station to transfer it to the designated storage area; image information refers to the package appearance data obtained by the image acquisition device, including but not limited to the shape and size of the express; the posture of the express (such as placement angle, direction); the surface features of the express (such as label, color, material); the integrity of the express (such as whether it is damaged).

[0031] In a specific implementation, the application scenario of the present application is that the express to be stored is in the stage of being transferred from the receiving point (such as the sorting area) to the storage area (such as the shelf, warehouse), which is the process of the express moving on the conveyor belt. During the dynamic movement of the express, the image acquisition device preset on the device can instantly capture the image of the express.

[0032] For example, a courier package is moving on a conveyor belt with a high-speed camera installed above it. When the package passes by the camera, the camera will take images of the package in real time and transmit the image data to the back-end system. The back-end system can quickly identify the size, posture and surface features of the package through image analysis algorithms, determine whether the package meets standard specifications, and decide whether it needs to be diverted to a special processing area.

[0033] In a specific implementation, the step of obtaining the image information of each express to be stored in real time during the transmission process of the express to be stored includes: During the transmission process of the express to be stored, it is determined whether the express to be stored is packed in an express box, wherein there is an express chip on the express box, and the express chip contains various information of the express to be stored; if the express to be stored is packed in an express box, the express chip on the express box is scanned to obtain the express information of the express to be stored, and based on the express information, it is determined whether the express to be stored in the express box is a non-standard express; if the express to be stored in the express box is a non-standard express, a prompt message is sent to the management end to prompt the management personnel to take out the express box; if it is not taken out within a preset time, the express box is diverted from the main transmission line and transmitted to the target storage area; if the express to be stored is not packed in an express box, the image information of each express to be stored is acquired in real time.

[0034] It should be noted that the express is packed in a courier box, which is a standardized packaging container, specifically an environmentally friendly recycling courier box, which is specially designed for express storage and transportation. In addition, an electronic chip is installed on the courier box. This chip is a small electronic device that can store data. The information contained in the courier chip includes but is not limited to the size, description of the express content, transportation requirements, logistics tracking number, etc. This information is very important for the storage, sorting, transportation and final delivery of the express.

[0035] In a specific implementation, during the transmission of the express, the device needs to detect whether the current express is in a courier box or not, which can be detected by a sensor or scanning device, such as by reading a chip signal to confirm the existence of the courier box. That is, the present application proposes that during the storage and transmission of the express, the device needs to detect whether the express is in a courier box with an express chip, which stores various information about the express, which is necessary for the management and tracking of the express.

[0036] In a specific implementation, if the device detects that the express to be stored is packed in an express box, the device can scan the express chip on the express box to read the express information stored therein. This information includes the size, weight, content type, whether it is fragile, whether it requires special treatment, etc. The device determines whether the express in the express box is a non-standard express based on the acquired express information.

[0037] In the specific implementation, if the express is judged as non-standard express, the device will send a prompt message to the management end, notifying the management that the express box needs to be specially handled. If the management does not take out the express box within a preset time (for example, 10 minutes), the device will automatically divert the express box from the main transmission line and transfer it to a special target storage area.

[0038] That is, this application proposes an automated logistics processing process to ensure that non-standard express deliveries can be processed in a timely manner to prevent them from interfering with the transmission and storage of normal express deliveries. If the management personnel fail to process them in time, the device will automatically divert these express deliveries to a dedicated area to ensure the efficient operation of the entire logistics system.

[0039] Step S200, based on the image information, determining whether the express to be stored is a non-standard express; It should be noted that the image information includes the size, shape, posture, surface features, etc. of the express delivery. This information is obtained through an image acquisition device (such as a 3D camera or an ordinary camera) and used for subsequent analysis.

[0040] In a specific implementation, the device determines whether the express to be stored is a non-standard express. Specifically, the standards for determining non-standard express include but are not limited to: 1. Exceeding the size. The length, width, and height of the package exceed the transmission range designed for the device. 2. Irregular shape. The package has an irregular shape, which causes rolling, sliding, or getting stuck during transmission. 3. Abnormal posture. The package is placed at an inappropriate angle on the conveyor belt, which may affect transmission or sorting. 4. Surface characteristics. The surface of the package is too smooth or rough, which affects the friction with the conveyor belt. 5. Other abnormalities. The package is damaged, the label is unclear, or has other characteristics that may cause transmission problems.

[0041] In the specific implementation, the device uses image analysis technology (such as Halcon, OCR, etc.) to process and analyze images. Through preprocessing (such as binarization, threshold segmentation), feature extraction and recognition algorithms, it determines whether the package meets the standards. Through real-time image analysis, non-standard express delivery can be quickly identified and diverted to avoid jamming or damage to automated transmission equipment, thereby improving the stability and efficiency of the system.

[0042] In a specific implementation, the step of determining whether the express to be stored is a non-standard express based on the image information includes: Based on the image information, the spatial features of the express to be stored are extracted, wherein the spatial features include size data and posture information; based on the spatial features, identification and judgment of non-standard express are performed through a preset express recognition model to obtain a judgment result, wherein the express recognition model is obtained by iteratively training a preset model to be trained based on express spatial feature samples and recognition result labels of the express spatial feature samples.

[0043] It should be noted that image information refers to the package image data obtained through a camera or other image acquisition device; spatial features include the size data (such as length, width, height) and posture information (such as placement angle, direction, etc.) of the express package. These features describe the physical state of the express package in three-dimensional space.

[0044] In a specific implementation, the device extraction process may be to use image processing technology (such as 3D reconstruction, edge detection, deep learning algorithm, etc.) to extract the size and posture information of the package from the image.

[0045] In the specific implementation, the express recognition model is a pre-trained algorithm model used to identify whether the package is a non-standard express. The recognition judgment is that the device inputs the extracted spatial features into the recognition model. The model will judge whether the package meets the standard specifications based on these features. The result of the model output indicates whether the package is a non-standard express. That is, this application extracts the spatial features of the package through image processing technology, and uses a trained model to judge whether the package is a non-standard express. This technical process can improve the efficiency and accuracy of the automated express processing system and reduce manual intervention.

[0046] Step S300: If the express to be stored is a non-standard express, the non-standard express is diverted from the main transmission line and transmitted to the target storage area.

[0047] It should be noted that the main transmission line refers to the normal transmission path of express parcels in the automated system, which is usually used to process parcels of standard size and shape. The main transmission line is designed to process most parcels efficiently and quickly; diversion transmission refers to separating parcels that do not meet the processing requirements of the main transmission line (i.e. non-standard express) from the main transmission path and guiding them to another transmission path or a specific processing area. This process is usually automated and achieved through mechanical devices (such as diverters, slides) or intelligent control systems; the target storage area is an area specially set up for non-standard express delivery, used to store these parcels that do not meet standard transmission requirements. This area can be equipped with special processing equipment or manual operation tables to allow further processing of non-standard express, such as repackaging, manual posture adjustment or special storage.

[0048] In the specific implementation, the device has determined whether a package is a non-standard express delivery through image information and recognition models. If the package is determined to be a non-standard express delivery, it will trigger the subsequent diversion operation. Specifically, the diversion device on the conveyor belt will automatically start to guide the package from the main transmission line to a dedicated processing area (target storage area).

[0049] In a specific implementation, if the express to be stored is a non-standard express, the step of diverting the non-standard express from the main transmission line to the target storage area includes: If the express to be stored is a non-standard express, the non-standard express is transmitted to the return flow elevator through the main transmission line, the transmission of the main transmission line is stopped, and the preset return flow elevator is started; the non-standard express is diverted from the main transmission line to the return flow conveyor belt through the return flow elevator, and the non-standard express is transmitted to the target storage area through the return flow conveyor belt.

[0050] It should be noted that the return elevator is a special device used to divert parcels from the main transmission line to another transmission path (return conveyor belt). It is located at a fixed position on the main transmission line. When non-standard express delivery is detected, the device will control the main transmission line to transfer the parcel to the location of the return elevator.

[0051] In a specific implementation, when the package reaches the return elevator position, the device controls the main transmission line to stop transmission. The device stops the transmission of the main transmission line to avoid affecting other packages on the main transmission line, or to prevent non-standard express delivery from colliding with other packages during the diversion process.

[0052] In the specific implementation, the device controls the return flow elevator to start, lifts the parcel from the horizontal transmission path of the main transmission line to the height of the return flow conveyor belt, and realizes the diversion of non-standard express from the main transmission line to the return flow conveyor belt. Among them, the return flow conveyor belt is a transmission path specially used for handling non-standard express, which is separated from the main transmission line. The return flow conveyor belt transfers non-standard express to the target storage area to complete the diversion and storage operations.

[0053] In a specific implementation, non-standard express delivery may cause the main transmission equipment to jam or be damaged due to its size, shape or posture not meeting the standard transmission requirements. These problems can be avoided through diversion operations to ensure the smooth operation of the main transmission line. Furthermore, non-standard express delivery requires special processing, such as repackaging, adjusting posture or special storage. This application diverts these packages to the target storage area, which can centrally handle these problems and improve overall efficiency. Finally, by diverting non-standard express delivery, the automation system can handle standard packages more efficiently and reduce downtime caused by abnormal packages, thereby improving the stability and reliability of the system.

[0054] In the specific implementation, this application proposes an automated processing flow for diverting non-standard express delivery from the main transmission line to the target storage area. Through the coordinated operation of the main transmission line, the return hoist and the return conveyor belt, the system can efficiently process non-standard express delivery, avoid equipment jamming and damage, and improve the stability and efficiency of the overall system.

[0055] Compared with the related art that non-standard express parcels are prone to cause equipment jamming when passing through automated transmission equipment, thereby affecting the normal operation of the entire post station, the present application proposes to obtain image information of each express parcel to be stored in real time during the transmission process of the express parcel to be stored; based on the image information, determine whether the express parcel to be stored is a non-standard express parcel; if the express parcel to be stored is a non-standard express parcel, the non-standard express parcel is diverted from the main transmission line to the target storage area. It is understandable that the present application identifies non-standard express parcels based on the image information of the express parcel to be stored, and diverts the non-standard express parcel from the main transmission line to the target storage area, thereby avoiding the jamming of the transmission machine caused by non-standard express parcels and improving the operational stability of the automatic express post station.

[0056] Based on the above first embodiment, the present application also proposes another embodiment, referring to Figure 2 The express return method of the automatic express post includes: In a specific implementation, the device performs identification and judgment of non-standard express delivery based on the spatial features by using a preset express delivery identification model. Before the step of obtaining the judgment result, the method includes: Step A100, obtaining a courier space feature sample and a recognition result label of the courier space feature sample; It should be noted that the express spatial feature samples refer to the sample data of express parcels used to train the model. Each sample includes the spatial features of the parcel, such as size (length, width, height), posture (placement angle, direction), etc. These sample data are usually obtained through image acquisition equipment (such as 3D cameras, ordinary cameras), and the spatial features of the parcel are extracted through image processing technology; the "label" of each sample parcel refers to the known classification result of whether the parcel is a non-standard express. For example, the label can be "standard express" or "non-standard express". These labels are usually generated by manual annotation or pre-set rules to tell the model the correct classification of each sample.

[0057] In the specific implementation, the purpose of collecting these sample data and labels is to train a model that can automatically identify whether a package is a non-standard express delivery. Sample data provides the basis for model learning, while labels are the goal of model learning.

[0058] Step A200, based on the express space feature samples and the recognition result labels, iteratively train the preset model to be trained to obtain an express recognition model.

[0059] It should be noted that the preset model to be trained is a pre-designed algorithm model, usually a machine learning or deep learning model (such as a neural network). The structure and parameters of this model have been defined before training, but the specific weights and parameters need to be optimized through the training process.

[0060] In the specific implementation, iterative training means that the model gradually optimizes its own parameters by learning sample data and labels multiple times to improve the accuracy and robustness of recognition. In each iteration, the model predicts the sample based on the current parameters, and then adjusts the parameters based on the difference between the predicted result and the true label (loss function) to reduce the error. After multiple iterative training, the parameters of the model gradually converge, and finally a model that can accurately identify the spatial characteristics of express delivery is obtained. This model can determine whether the package is a non-standard express based on the input package spatial characteristics (such as size, posture, etc.).

[0061] In a specific implementation, the device iteratively trains a preset model to be trained based on the express space feature sample and the recognition result label to obtain the express recognition model, including: Acquire the packaging surface and material information corresponding to the express space feature sample; determine the packaging characteristic weight corresponding to the packaging surface and material information; iteratively train the preset model to be trained based on the express space feature sample, the recognition result label and the packaging characteristic weight to obtain the express recognition model.

[0062] It should be noted that the package surface and material information refers to the surface features and material properties of the package, such as: surface smoothness, texture, color; type of packaging material (such as cartons, plastic bags, foam boxes); material hardness, elasticity, friction coefficient, etc. This information can help the model understand the physical properties of the package more comprehensively, so as to more accurately determine whether the package is a non-standard express. For example, a package with a smooth surface is more likely to slide during transportation, and some materials require special handling methods.

[0063] It should be emphasized that the packaging material and surface characteristics of the package will also affect its transmission performance. For example, a package with a surface that is too smooth or too rough may not generate enough friction with the conveyor belt or sorting equipment, causing the conveyor machine to get stuck and affecting the operating stability of the automatic express station.

[0064] In the specific implementation, weight refers to the importance of different features to the final judgment result during the model training process. For example, the size data may be very important for judging whether the package is a non-standard express, so it is assigned a higher weight; the surface smoothness may have an impact on the transmission stability, but it is less important than the size, so it is assigned a lower weight. By assigning weights to different features, the model can more reasonably evaluate the impact of each feature on the package classification, thereby improving the accuracy and robustness of recognition.

[0065] In the specific implementation, the iterative training process uses sample data containing spatial features, packaging surface and material information, as well as corresponding labels and weights to train the preset model multiple times. During each training process, the model adjusts parameters based on the input data and weights to minimize the difference between the predicted results and the true labels. The trained and optimized model can comprehensively consider the spatial features and packaging characteristics of the package and accurately determine whether the package is a non-standard express.

[0066] For example, in the data preparation phase, image data of 1,000 packages are collected, and the size (length, width, height) and posture (placement angle) of each package are extracted. At the same time, the surface characteristics (such as smoothness, texture) and material (such as carton, plastic bag) of the package are recorded, and each package is manually labeled to determine whether it is a non-standard express delivery. The weight distribution includes: size feature weight: 0.6; surface smoothness weight: 0.2; material type weight: 0.4. The model training process first designs a deep learning model (such as convolutional neural network, CNN), and then trains the model using the above data and weights. In each iteration, the model calculates the classification result of the package based on the input features and weights, and adjusts the parameters based on the difference between the predicted result and the true label. After multiple iterations of training, the performance of the model gradually improves, and finally a courier recognition model that can comprehensively consider spatial features and packaging characteristics is obtained.

[0067] It is understandable that the present application also proposes to further optimize the training process of the express recognition model by introducing the packaging surface and material information of the package and assigning weights to this information. This allows the model to more comprehensively evaluate the physical characteristics of the package, thereby more accurately determining whether the package is a non-standard express.

[0068] In a specific implementation, the device iteratively trains a preset model to be trained based on the express space feature sample, the recognition result label, and the packaging characteristic weight to obtain the express recognition model, including: Based on the express space feature samples and the packaging characteristic weights, the non-standard express is identified and judged by the preset model to be trained to obtain a prediction result; the prediction result is difference calculated with the identification result label to obtain an error result; based on the error result, it is judged whether the error result meets the error standard indicated by the preset error threshold range; if the error result does not meet the error standard indicated by the preset error threshold range, the model to be trained is updated, and the step of identifying and judging the non-standard express based on the express space feature samples and the packaging characteristic weights by the preset model to be trained is returned to obtain the prediction result, and the training is stopped until the error result meets the error standard indicated by the preset error threshold range to obtain the express recognition model.

[0069] In a specific implementation, the device uses a preset model to be trained to identify and judge non-standard express delivery based on the express space feature sample and the packaging characteristic weight, and obtains a prediction result. The prediction result refers to the model's prediction of whether each express sample is a non-standard express delivery.

[0070] In the specific implementation, the device calculates the difference between the predicted detection result and the true label, and usually uses a loss function (such as mean square error, cross entropy loss, etc.) to quantify this difference. The error result refers to the result of the difference calculation, which indicates the gap between the accuracy of the model prediction and the true label. That is, it verifies whether the results obtained by the model in training are consistent with the known results, and calculates the difference between the results to obtain the error result.

[0071] It should be noted that the device determines whether the error result meets the error standard indicated by the preset error threshold range based on the error result. Specifically, since there is an error between the result after model training and the actual result, the error result is allowed to be within the preset error threshold range, so as to further determine whether the error result meets the error standard indicated by the preset error threshold range.

[0072] It is understandable that if the error result does not meet the error standard indicated by the preset error threshold range, it means that the error of the model in this training is too large, and the device needs to update the parameters of the model, which is usually achieved through a back-propagation algorithm and an optimizer (such as gradient descent, etc.). After updating the model parameters, re-perform the safety test and recalculate the difference between the predicted test result and the true label until the error result meets the preset error threshold range. That is, iterative training is performed until the error result meets the error standard indicated by the preset error threshold range, and then the training is stopped to obtain the express recognition model. Through this iterative training and optimization process, the present application can ensure that the express recognition model gradually improves the prediction accuracy on the training data, and finally reaches the predetermined performance standard, so as to more effectively determine non-standard express delivery.

[0073] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the express return method of the automatic express station of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0074] This application also provides a courier return device for an automatic courier station, please refer to Figure 3 The express return device of the automatic express post includes: The acquisition module 10 is used to acquire the image information of each express to be stored in real time during the transmission process of the express to be stored; A judgment module 20, configured to judge whether the express to be stored is a non-standard express based on the image information; The diversion module 30 is used to divert the non-standard express from the main transmission line to the target storage area if the express to be stored is a non-standard express.

[0075] Optionally, the diversion module 30 includes: A starting module, for, if the express to be stored is a non-standard express, transmitting the non-standard express to the return flow elevator through the main transmission line, stopping the transmission of the main transmission line, and starting the preset return flow elevator; The transmission module is used to divert the non-standard express from the main transmission line to the return flow conveyor belt through the return flow elevator, and transmit the non-standard express to the target storage area through the return flow conveyor belt.

[0076] Optionally, the acquisition module 10 includes: A courier judgment module, used to judge whether the courier to be stored is packed in a courier box during the transmission process of the courier to be stored, wherein there is a courier chip on the courier box, and the courier chip contains various information of the courier to be stored; A scanning module is used for scanning the express chip on the express box if the express to be stored is packed in the express box, obtaining the express information of the express to be stored, and judging whether the express to be stored in the express box is a non-standard express based on the express information. If the express to be stored in the express box is a non-standard express, a prompt message is sent to the management end to prompt the management to take out the express box. If the express is not taken out within a preset time, the express box is diverted from the main transmission line and transmitted to the target storage area; The image acquisition module is used to acquire the image information of each express to be stored in real time if the express to be stored is not packaged in an express box.

[0077] Optionally, the judging module 20 includes: An extraction module, configured to extract the spatial features of the express to be stored based on the image information, wherein the spatial features include size data and posture information; The recognition module is used to identify and judge non-standard express delivery based on the spatial features through a preset express recognition model to obtain a judgment result, wherein the express recognition model is obtained by iteratively training a preset model to be trained based on express spatial feature samples and recognition result labels of the express spatial feature samples.

[0078] Optionally, the express return device of the automatic express post further includes: A sample acquisition module, used to acquire a courier space feature sample and an identification result label of the courier space feature sample; The training module is used to iteratively train the preset model to be trained based on the express space feature samples and the recognition result labels to obtain the express recognition model.

[0079] Optionally, the training module includes: An information acquisition module, used to obtain packaging surface and material information corresponding to the express space feature sample; A weight determination module, used to determine the packaging characteristic weight corresponding to the packaging surface and material information; The iterative training module is used to iteratively train the preset model to be trained based on the express space feature sample, the recognition result label and the packaging characteristic weight to obtain the express recognition model.

[0080] Optionally, the iterative training module includes: A prediction module, used to identify and judge non-standard express delivery based on the express space feature samples and the packaging characteristic weights through a preset model to be trained to obtain a prediction result; A difference calculation module, used to calculate the difference between the prediction result and the recognition result label to obtain an error result; An error judgment module, used to judge whether the error result meets the error standard indicated by a preset error threshold range based on the error result; The express recognition model training module is used to update the model to be trained if the error result does not meet the error standard indicated by the preset error threshold range, and return to the step of identifying and judging non-standard express based on the express space feature sample and the packaging characteristic weight through the preset model to be trained to obtain the prediction result, and stop training until the error result meets the error standard indicated by the preset error threshold range to obtain the express recognition model.

[0081] The express return device of the automatic express post provided by the present application adopts the express return method of the automatic express post in the above embodiment, which can solve the technical problem of express return of the automatic express post. Compared with the prior art, the express return device of the automatic express post provided by the present application has the same beneficial effect as the express return method of the automatic express post provided by the above embodiment, and the other technical features of the express return device of the automatic express post are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0082] The present application provides an express return device for an automatic express station, the express return device for the automatic express station comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the express return method for the automatic express station in the above-mentioned embodiment one.

[0083] Reference below Figure 4 , which shows a schematic diagram of the structure of the express return equipment of the automatic express post station suitable for implementing the embodiment of the present application. The express return equipment of the automatic express post station in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The express return equipment of the automatic express station shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0084] like Figure 4As shown, the express return equipment of the automatic express post may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the express return equipment of the automatic express post are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the express return equipment of the automatic express post to communicate wirelessly or wired with other devices to exchange data. Although the express return equipment of the automatic express post with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0085] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0086] The express return device of the automatic express post provided by the present application adopts the express return method of the automatic express post in the above embodiment, which can solve the technical problem of express return of the automatic express post. Compared with the prior art, the express return device of the automatic express post provided by the present application has the same beneficial effect as the express return method of the automatic express post provided by the above embodiment, and the other technical features of the express return device of the automatic express post are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0087] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0088] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0089] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the express return method of the automatic express station in the above-mentioned embodiment.

[0090] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0091] The above-mentioned computer-readable storage medium may be included in the express return equipment of the automatic express station; or it may exist independently without being assembled into the express return equipment of the automatic express station.

[0092] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the express return device of the automatic express station, the express return device of the automatic express station enables: express return of the automatic express station.

[0093] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0094] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0095] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0096] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the express return method of the above-mentioned automatic express post, and can solve the technical problems of express return of the automatic express post. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the express return method of the automatic express post provided in the above-mentioned embodiment, and will not be repeated here.

[0097] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the express return method of the automatic express station as described above.

[0098] The computer program product provided by this application can solve the technical problem of express return flow of automatic express post. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the express return flow method of the automatic express post provided by the above embodiment, which will not be repeated here.

[0099] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for returning express delivery to an automatic express delivery station, characterized in that: The express return method of the automatic express post includes: During the transmission process of the express to be stored, the image information of each express to be stored is obtained in real time; Based on the image information, determining whether the express to be stored is a non-standard express; If the express to be stored is a non-standard express, the non-standard express is diverted from the main transmission line and transmitted to the target storage area.

2. The express return method of the automatic express post as claimed in claim 1, characterized in that: If the express to be stored is a non-standard express, the step of transferring the non-standard express from the main transmission line to the target storage area comprises: If the express to be stored is a non-standard express, after the non-standard express is transmitted to the return flow elevator through the main transmission line, the transmission of the main transmission line is stopped, and the preset return flow elevator is started; The non-standard express is diverted from the main transmission line to the return conveyor belt by the return elevator, and the non-standard express is transmitted to the target storage area by the return conveyor belt.

3. The express return method of the automatic express post as claimed in claim 1, characterized in that: The step of acquiring the image information of each express to be stored in real time during the transmission process of the express to be stored comprises: During the transmission process of the express to be stored, determining whether the express to be stored is packed in an express box, wherein there is an express chip on the express box, and the express chip contains various information of the express to be stored; If the express to be stored is packed in an express box, the express chip on the express box is scanned to obtain the express information of the express to be stored, and based on the express information, it is determined whether the express to be stored in the express box is a non-standard express. If the express to be stored in the express box is a non-standard express, a prompt message is sent to the management end to prompt the management to take out the express box. If it is not taken out within a preset time, the express box is diverted from the main transmission line and transmitted to the target storage area; If the express items to be stored are not packed in express boxes, image information of each express item to be stored is acquired in real time.

4. The express return method of the automatic express post as claimed in claim 1, characterized in that: The step of judging whether the express to be stored is a non-standard express based on the image information comprises: Extracting spatial features of the express to be stored based on the image information, wherein the spatial features include size data and posture information; Based on the spatial features, non-standard express delivery is identified and judged through a preset express recognition model to obtain a judgment result, wherein the express recognition model is obtained by iteratively training a preset model to be trained based on express spatial feature samples and recognition result labels of the express spatial feature samples.

5. The express return method of the automatic express post as claimed in claim 4, characterized in that: Before the step of identifying and judging the non-standard express delivery based on the spatial features by using a preset express delivery recognition model to obtain a judgment result, the method includes: Obtaining a courier space feature sample and a recognition result label of the courier space feature sample; Based on the express space feature samples and the recognition result labels, the preset model to be trained is iteratively trained to obtain an express recognition model.

6. The express return method of the automatic express post as claimed in claim 5, characterized in that: The step of iteratively training a preset model to be trained based on the express space feature sample and the recognition result label to obtain an express recognition model includes: Obtaining packaging surface and material information corresponding to the express space feature sample; Determining packaging characteristic weights corresponding to the packaging surface and material information; Based on the express space feature samples, the recognition result labels and the packaging characteristic weights, the preset model to be trained is iteratively trained to obtain an express recognition model.

7. The express return method of the automatic express post as claimed in claim 6, characterized in that: The step of iteratively training the preset model to be trained based on the express space feature sample, the recognition result label and the packaging characteristic weight to obtain the express recognition model includes: Based on the express space feature samples and the packaging characteristic weights, the non-standard express is identified and judged by a preset model to be trained to obtain a prediction result; Calculate the difference between the prediction result and the recognition result label to obtain an error result; Based on the error result, determining whether the error result meets an error standard indicated by a preset error threshold range; If the error result does not meet the error standard indicated by the preset error threshold range, the model to be trained is updated, and the step of identifying and judging non-standard express based on the express space feature sample and the packaging characteristic weight by the preset model to be trained is returned to obtain a prediction result, and the training is stopped until the error result meets the error standard indicated by the preset error threshold range to obtain an express recognition model.

8. An express return device for an automatic express post, characterized in that: The device comprises: An acquisition module, used to acquire image information of each express to be stored in real time during the transmission process of the express to be stored; A judgment module, used for judging whether the express to be stored is a non-standard express based on the image information; The diversion module is used for diverting the non-standard express from the main transmission line to the target storage area if the express to be stored is a non-standard express.

9. An express return device for an automatic express post, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the express return method of the automatic express station as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the express return method of the automatic express station as described in any one of claims 1 to 7 are implemented.

Images