Processing and model construction method and device for express parcel missed scanning based on artificial intelligence

Abstract

The application relates to the field of artificial intelligence, in particular to a processing method and a model construction method and equipment for express parcel missing scanning based on artificial intelligence. The method comprises the following steps: obtaining scanning data of a preprocessed express environmental protection bag, wherein the scanning data of the express environmental protection bag comprises a test set, a verification set and a training set; inputting the training set into an initial AI model for training to obtain first data; adjusting model parameters by using the first data to minimize a loss function of the model; and verifying the AI model after the model parameters are adjusted by using the verification set to obtain a trained AI model. By using machine algorithm construction and training the AI model, the trained model is used for identifying parcels in the express environmental protection bag, and problems of unclean parcel unpacking, parcel left express parcels, express parcel delay and wrong delivery are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a processing method and a model construction method for express delivery item missed scanning based on artificial intelligence. BACKGROUND

[0002] In the transfer process of express delivery items, the express delivery items need to be transferred after being packed at the sending network point and unpacked and sorted at the terminal transfer center. Currently, the unpacking operation is manually performed, which may cause the express delivery items to be left in the package, resulting in express delivery item delay and misdelivery.

[0003] Unpacking, as compared with packing or packing, refers to unpacking the package delivered from the previous network point. The package delivered from the previous network point is a large package containing your package and the packages of other people on the same route. Unpacking is the process of re-sorting, scanning and packing the express delivery items according to different places and regions at the transfer station. In other words, unpacking is the process of unpacking the express delivery package by the express delivery company, not by the individual.

[0004] That is, in the prior art, the unpacking operation is manually performed, which may cause the express delivery items to be left in the package, resulting in express delivery item delay and misdelivery. SUMMARY

[0005] To at least partially overcome the problem that the unpacking operation is manually performed, which may cause the express delivery items to be left in the package, resulting in express delivery item delay and misdelivery in the related art, the present application provides a processing method and a model construction method for express delivery item missed scanning based on artificial intelligence.

[0006] The scheme of the present application is as follows:

[0007] In a first aspect, the present application provides a processing model construction method for express delivery item missed scanning based on artificial intelligence, which comprises:

[0008] obtaining scanning data of a preprocessed express delivery environment-friendly bag, wherein the scanning data of the express delivery environment-friendly bag comprises a test set, a validation set and a training set;

[0009] inputting the training set into an initial AI model for training to obtain first data;

[0010] adjusting model parameters using the first data to minimize the loss function of the model;

[0011] verifying the AI model after adjusting the model parameters using the validation set to obtain a trained AI model.

[0012] Further, the obtaining of the scanning data of the preprocessed express delivery environment-friendly bag comprises:

[0013] Obtain scanned images of express parcels inside the eco-friendly express bags, including scanned images of express parcels inside eco-friendly express bags of different sizes;

[0014] The scanned images of express parcels in the eco-friendly express bags with different rules are classified and labeled to obtain pre-processed scan data of the eco-friendly express bags.

[0015] Furthermore, the algorithm in the initial AI model includes:

[0016] Target detection algorithm.

[0017] Furthermore, before classifying and labeling the scanned images of the express parcels in the eco-friendly express bags of different rules to obtain the preprocessed scanned data of the eco-friendly express bags, the method also includes:

[0018] The scanned images of express parcels in the eco-friendly bags of the different types of express parcels are normalized.

[0019] Secondly, this application provides a method for handling missed package scanning based on artificial intelligence, the method comprising:

[0020] The preprocessed scanning data of the express delivery eco-friendly bags is obtained, and the scanning data of the express delivery eco-friendly bags includes: a test set, a validation set, and a training set;

[0021] The test set from the scanned data of the express eco-friendly bags is input into the pre-trained AI model for testing;

[0022] If an abnormal judgment and processing result occurs during the test, the abnormal judgment and processing result will be sent to the warning output device, and the on-site personnel will re-inspect the express delivery eco-friendly bag;

[0023] The pre-trained AI model is constructed using any of the methods described above.

[0024] Thirdly, this application provides an artificial intelligence-based express mail missing scan processing device, the device comprising:

[0025] The processor, memory, and communication bus are used to communicate with each other.

[0026] The memory is used to store computer programs;

[0027] The processor is used to execute the program stored in the memory to implement the above-described AI-based express mail missing scan processing method, or the above-described AI-based express mail missing scan processing model construction method.

[0028] The technical solution provided in this application may include the following beneficial effects:

[0029] This application includes: obtaining preprocessed scan data of reusable express delivery bags, wherein the scan data includes a test set, a validation set, and a training set; inputting the training set into an initial AI model for training to obtain first data; using the first data to adjust the model parameters to minimize the model's loss function; and using the validation set to validate the AI ​​model after adjusting the model parameters to obtain a trained AI model. By using machine algorithms to construct and train an AI model, the trained model is used to identify packages in reusable express delivery bags, helping to solve the problems of incomplete unpacking, leaving packages inside, causing delays and misdeliveries.

[0030] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0031] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0032] Figure 1 This is a flowchart illustrating a method for constructing a processing model for missed parcel scanning based on artificial intelligence, according to an embodiment of this application.

[0033] Figure 2 This is a schematic flowchart of a method for handling missed parcel scanning based on artificial intelligence, provided in one embodiment of this application.

[0034] Figure 3 This is a schematic diagram of an unpacking process at an express delivery transfer center based on artificial intelligence, provided in one embodiment of this application;

[0035] Figure 4 This is a schematic diagram of a visual algorithm recognition process based on artificial intelligence provided in one embodiment of this application;

[0036] Figure 5 This is a schematic diagram of the equipment used for processing missed parcels based on artificial intelligence. Detailed Implementation

[0037] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0038] Example

[0039] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for constructing a processing model for missed package scanning based on artificial intelligence, according to an embodiment of this application. The method includes:

[0040] S1. Obtain the preprocessed scanning data of the eco-friendly express delivery bag, wherein the scanning data of the eco-friendly express delivery bag includes: a test set, a verification set, and a training set;

[0041] S2. Input the training set into the initial AI (Artificial Intelligence) model for training to obtain the first data;

[0042] S3. Using the first data, adjust the model parameters to minimize the model's loss function;

[0043] S4. Use the validation set to validate the AI ​​model after adjusting the model parameters, and obtain the trained AI model.

[0044] In one embodiment, as described in step S1, obtaining the preprocessed scan data of the reusable express delivery bag includes:

[0045] Obtain scanned images of express parcels inside the eco-friendly express bags, including scanned images of express parcels inside eco-friendly express bags of different sizes;

[0046] The scanned images of express parcels in the eco-friendly express bags with different rules are classified and labeled to obtain pre-processed scan data of the eco-friendly express bags.

[0047] Furthermore, the algorithm in the initial AI model includes:

[0048] The target detection algorithm uses the YOLO v8 neural network model.

[0049] In specific implementation, before classifying and labeling the scanned images of express parcels in the eco-friendly express bags of different rules to obtain preprocessed scanned data of the eco-friendly express bags, the method further includes:

[0050] The scanned images of express parcels in the eco-friendly bags of the different types of express parcels are normalized.

[0051] Please see Figure 2 , Figure 2 This is a schematic flowchart of a method for handling missed package scanning based on artificial intelligence, provided in another embodiment of this application. The method includes:

[0052] S1. Obtain the preprocessed scanning data of the eco-friendly express delivery bag, wherein the scanning data of the eco-friendly express delivery bag includes: a test set, a verification set, and a training set;

[0053] S2. Input the test set from the scanned data of the express eco-friendly bag into the pre-trained AI model for testing;

[0054] S3. If an abnormal judgment and processing result occurs during the test, the abnormal judgment and processing result shall be sent to the warning output device, and the on-site personnel shall re-inspect the express delivery eco-friendly bag;

[0055] S4. Wherein, the pre-trained AI model is constructed using the method described in any of the above methods.

[0056] In one embodiment, as described in step S3, if an abnormal judgment and processing result occurs during the test, the abnormal judgment and processing result is sent to the warning output device, and the on-site personnel re-inspect the express delivery eco-friendly bag, including:

[0057] The trained AI model is pre-installed into the host computer of the security inspection machine. The host computer of the security inspection machine performs image segmentation on the received images of packages in the reusable bags. It identifies the images every second, automatically marking images of packages in the reusable bags, and not marking images of packages in the reusable bags.

[0058] The AI ​​model detects whether there are any packages inside the eco-friendly bags. If so, an anomaly judgment result is generated and sent to the warning output device, so that on-site personnel can re-inspect the eco-friendly bags containing packages.

[0059] Please see Figure 3 , Figure 4 In practice, this includes the following two steps:

[0060] Step 1: Scanning the reusable delivery bags. The reusable delivery bags are scanned using an X-ray security scanner to obtain scanned images of the bags and upload them to the security scanner's main unit for visual algorithm recognition, i.e., the algorithm in the AI ​​(Artificial Intelligence) model. The algorithm includes: target detection algorithm, etc. Through the pre-trained visual algorithm, the packages inside the reusable bags are analyzed hierarchically and features are identified. We only need to learn the image features of all empty bags to compare and identify bag images with packages.

[0061] In practice, parcels are usually stacked in eco-friendly bags. The trained model needs to analyze the color and shape of the non-overlapping parts of the parcels to identify their original shape. If the analysis of the images reveals that there are parcels in the eco-friendly bags, it indicates that the manual unpacking was not clean enough, and relevant personnel will be notified to handle the situation.

[0062] Step 2: The abnormal judgment result in the scanned image, i.e., the case where the manual unpacking was not clean, is sent to the warning output device, and the on-site personnel re-inspect the express delivery eco-friendly bag.

[0063] In practice, the AI ​​model training process involves the following steps:

[0064] Preparations before training:

[0065] ① Collect feature information on express parcels with different rules;

[0066] ② Deploy visual algorithms on the security inspection machine host. The algorithms include: target detection algorithm, and the model used is the YOLOv8 model.

[0067] ③ Build a labeling website on the intranet to classify and label express parcels according to different rules;

[0068] AI model training methods:

[0069] ①The AI ​​model automatically labels the collected express parcels;

[0070] ② Manual correction of labeling errors;

[0071] ③ Train twice a month to improve the accuracy of AI model recognition.

[0072] In practical implementation, the visual algorithm processing procedure is as follows:

[0073] The main unit of the security inspection machine segments the images of packages inside the received reusable express bags. It identifies images every second, automatically marking images of packages inside the bags and leaving images of bags without packages unmarked.

[0074] No personnel are required to stand guard at the security inspection machine. The system will send the results of the abnormal judgment and processing in the scanned image to the warning output device, and the on-site personnel will re-inspect the express delivery eco-friendly bags.

[0075] In one embodiment, this application obtains preprocessed scanning data of reusable express delivery bags, the scanning data including a test set, a validation set, and a training set; the training set is input into an initial AI model for training to obtain first data; the model parameters are adjusted using the first data to minimize the model's loss function; the AI ​​model with adjusted parameters is validated using the validation set to obtain a trained AI model. By using machine algorithms to construct and train the AI ​​model, the trained model is used to identify packages in reusable express delivery bags, helping to solve the problem of incomplete unpacking, leaving packages inside, causing delays and misdeliveries.

[0076] Please see Figure 5 , Figure 5 This is a schematic diagram of an AI-based express mail missing detection processing device, which includes:

[0077] The processor 31, memory 32, and communication bus are provided, wherein the processor 31 and memory 32 communicate with each other through the communication bus.

[0078] The memory 32 is used to store computer programs;

[0079] The processor 31 is used to execute the program stored in the memory to implement the above-described AI-based express mail missing scan processing method, or the AI-based express mail missing scan processing model construction method described above.

[0080] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0081] It should be noted that in the description of this application, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means at least two.

[0082] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the function involved, as will be understood by those skilled in the art to which embodiments of this application pertain.

[0083] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0084] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0085] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0086] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0087] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0088] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for constructing a processing model for missed package scanning based on artificial intelligence, characterized in that, The method includes: The preprocessed scanning data of the express delivery eco-friendly bags is obtained, and the scanning data of the express delivery eco-friendly bags includes: a test set, a validation set, and a training set; The training set is input into the initial AI model for training to obtain the first data; Using the first data, adjust the model parameters to minimize the model's loss function; The AI ​​model with adjusted parameters is validated using the validation set to obtain the trained AI model. The pre-processed scan data of the reusable express delivery bag includes: Obtain scanned images of express parcels inside the eco-friendly express bags, including scanned images of express parcels inside eco-friendly express bags of different sizes; The scanned images of express parcels in the eco-friendly express bags with different rules are classified and labeled to obtain pre-processed scan data of the eco-friendly express bags.

2. The method according to claim 1, characterized in that, The algorithms in the initial AI model include: Target detection algorithm.

3. The method according to claim 1, characterized in that, Before classifying and labeling the scanned images of express parcels in the eco-friendly express bags of different rules to obtain preprocessed scanned data of the eco-friendly express bags, the method further includes: The scanned images of express parcels in the eco-friendly bags of the different types of express parcels are normalized.

4. A method for handling missed scans of express parcels based on artificial intelligence, characterized in that: The method includes: The preprocessed scanning data of the express delivery eco-friendly bags is obtained, and the scanning data of the express delivery eco-friendly bags includes: a test set, a validation set, and a training set; The test set from the scanned data of the express eco-friendly bags is input into the pre-trained AI model for testing; If an abnormal judgment and processing result occurs during the test, the abnormal judgment and processing result will be sent to the warning output device, and the on-site personnel will re-inspect the express delivery eco-friendly bag; The pre-trained AI model is constructed using the method described in any one of claims 1 to 3.

5. An AI-based express mail missing scan processing device, characterized in that, The device includes: The processor, memory, and communication bus are used to communicate with each other. The memory is used to store computer programs; The processor is used to execute the program stored in the memory to implement the express mail missing scan processing method based on artificial intelligence as described in claim 4, or the express mail missing scan processing model construction method based on artificial intelligence as described in any one of claims 2 to 3.

Images