Consignment processing method, device, computer equipment and storage medium

Abstract

The present application relates to a method, device, computer equipment and storage medium for processing consignment, the method comprising: receiving the consignment information; obtaining a target object image taken of the consignment; performing image detection on the target object image, and generating a waybill number if the target object image meets the preset image requirements; and storing the target object image in correspondence with the waybill number and the consignment information. The above method requires uploading an image taken of the consignment during the collection process, and generates a waybill number when the image meets certain conditions, and stores the image together with the waybill number and the consignment information. If the specific location of the consignment needs to be found during the subsequent transportation process and delivery process, it can be searched in combination with the stored consignment image, which provides useful information for finding the consignment when it is lost.

Description

Technical Field

[0001] The present application relates to the field of logistics technology, and in particular to a consignment processing method, device, computer equipment and storage medium. Background Art

[0002] Relying on the rapid development of the Internet, the express delivery industry has also grown rapidly. With the explosive growth of the number of parcels, terminal delivery services are facing tremendous pressure. The industry has generated a huge demand for express delivery practitioners, but the number of delivery personnel has always been in a state of shortage and in short supply; and in many cases, due to the reasons of the recipient, door-to-door delivery is prone to unsuccessful delivery. On the one hand, the express delivery volume is constantly rising, and on the other hand, there is a shortage of delivery personnel. The door-to-door service that used to be difficult to fully guarantee is difficult to fully guarantee.

[0003] Due to the heavy pressure on delivery personnel to deliver parcels, delivery personnel often leave parcels at collection points without permission, resulting in a high rate of parcel loss. Currently, a parcel is usually only associated with the waybill number, consignee and sender information, and routing information. Once lost, it is difficult and time-consuming to locate the lost item based on the routing information. Summary of the invention

[0004] Based on this, it is necessary to provide a consignment processing method, device, computer equipment and storage medium that can facilitate the search for express parcels in response to the above technical problems.

[0005] A consignment handling method, the method comprising:

[0006] Receive the consignment information;

[0007] Acquire a target object image photographed for the consignment;

[0008] Performing image detection on the target object image, and generating a waybill number if the target object image meets preset image requirements;

[0009] The target object image is stored correspondingly with the waybill number and the shipping information.

[0010] In one embodiment, after the target object image is stored in correspondence with the waybill number and the shipping information, the method further includes:

[0011] When receiving the delivery information for the consignment, sending the delivery scene confirmation information to the consignee according to the consignment information;

[0012] Receiving delivery scenario target information based on the delivery scenario confirmation information feedback;

[0013] Acquire actual information of the delivery scene when delivering the consignment;

[0014] If it is determined based on the delivery scenario target information that the actual information of the delivery scenario meets the delivery requirements, delivery completion information of the consignment is generated.

[0015] In one embodiment, the actual information of the delivery scene includes: an actual image of the delivery scene; the method further includes:

[0016] Performing scene classification on the delivery scene image based on the scene classification model determined through training, and determining the scene category corresponding to the actual image of the delivery scene;

[0017] The scene corresponding to the actual image of the delivery scene is compared with the target information of the delivery scene. If the actual image of the delivery scene conforms to the target information of the delivery scene, it is determined that the actual image of the delivery scene meets the delivery requirements.

[0018] In one embodiment, performing image detection on the target object image includes:

[0019] Performing consignment recognition on the target object image to obtain a consignment recognition result;

[0020] Performing image quality classification on the target object image to obtain a quality classification result;

[0021] If it is determined that the target object image contains the consignment according to the consignment identification result, and the quality classification result meets the preset quality requirement, it is determined that the target object image meets the preset image requirement.

[0022] In one embodiment, the method comprises at least one of the following:

[0023] The first item,

[0024] The performing consignment recognition on the target object image comprises: performing consignment recognition on the target object image based on a target detection model determined through training;

[0025] The second item,

[0026] The performing image quality classification on the target object image includes: performing image quality classification on the target object image based on a classification network determined through training.

[0027] In one embodiment, the method further comprises:

[0028] Performing face detection on the target object image based on the target detection model determined through training to obtain a face detection result;

[0029] If it is determined according to the face detection result that the target object image contains a face, blurring is performed on the face region in the face detection result.

[0030] In one embodiment, after receiving the consignment information of the consignment and before acquiring the target object image photographed for the consignment, the method further includes:

[0031] Determine the corresponding collection personnel according to the mailing information;

[0032] A collection task is generated according to the mailing information and sent to the terminal of the collection personnel.

[0033] A consignment handling device, comprising:

[0034] A receiving module, used for receiving the shipping information of the consignment;

[0035] An image acquisition module, used to acquire an image of a target object photographed for the consignment;

[0036] An image detection module is used to perform image detection on the target object image, and generate a waybill number if the target object image meets the preset image requirements;

[0037] The storage module is used to store the target object image in correspondence with the waybill number and the shipping information.

[0038] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0039] Receive the consignment information;

[0040] Acquire a target object image photographed for the consignment;

[0041] Performing image detection on the target object image, and generating a waybill number if the target object image meets preset image requirements;

[0042] The target object image is stored correspondingly with the waybill number and the shipping information.

[0043] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0044] Receive the consignment information;

[0045] Acquire a target object image photographed for the consignment;

[0046] Performing image detection on the target object image, and generating a waybill number if the target object image meets preset image requirements;

[0047] The target object image is stored correspondingly with the waybill number and the shipping information.

[0048] After receiving the consignment information, the above-mentioned consignment processing method, device, computer equipment and storage medium obtain the target object image taken by the collection personnel when collecting the consignment, perform image detection on the target object image, and determine whether the target object image meets the preset image requirements. If it does, a waybill number can be generated, and the target object image is stored in correspondence with the consignment information and the waybill number to complete the collection process. The above-mentioned method requires uploading the image taken of the consignment during the collection process, and generates a waybill number when the image meets certain conditions, and stores the image together with the waybill number and the consignment information. If the specific location of the consignment needs to be found in the subsequent transportation process and delivery process, it can be searched in combination with the stored consignment image, which provides useful information for finding the consignment when it is lost. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is an application environment diagram of a consignment handling method in one embodiment;

[0050] Figure 2 Schematic diagram of a flow chart of a consignment handling method in one embodiment;

[0051] Figure 3 is a schematic flow chart of a consignment handling method according to another embodiment;

[0052] FIG4(1) is a schematic diagram of a specific embodiment in which the actual image of the delivery scene is only the consignment;

[0053] FIG4(2) is a schematic diagram showing a specific embodiment in which the actual image of the delivery scene is a resident's door;

[0054] FIG4(3) is a schematic diagram showing a specific embodiment in which the actual image of the delivery scene is a store entrance;

[0055] FIG4 (4) is a schematic diagram of a specific embodiment in which the actual image of the delivery scene is a courier cabinet;

[0056] FIG4(5) is a schematic diagram showing an actual image of a delivery scene that is an abnormal scene in a specific embodiment;

[0057] Figure 5 A schematic diagram of the structure of an Efficientnet-b0 network in a specific embodiment;

[0058] Figure 6 is a schematic diagram of a process of performing image detection on the target object image in one embodiment;

[0059] Figure 7 A schematic diagram of the structure of a PP-YOLO network in a specific embodiment;

[0060] Figure 8 A schematic diagram of a collection process in a specific embodiment;

[0061] Fig. 9 It is a flowchart of the delivery process in a specific embodiment;

[0062] Fig.10 is a structural block diagram of a consignment handling device in one embodiment;

[0063] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0065] The consignment handling method provided in this application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 and the terminal 103 communicate with the server 104 through the network. After receiving the consignment information of the consignment, the server 104 obtains the target object image taken by the collection personnel for the consignment when collecting the consignment, performs image detection on the target object image, and determines whether the target object image meets the preset image requirements. If it meets the requirements, a waybill number can be generated, and the target object image is stored in correspondence with the consignment information and the waybill number to complete the collection process. Among them, the consignment information can be sent by the consumer through the terminal 102. Among them, the terminal 102 and the terminal 103 can be, but are not limited to, various personal computers, laptops, smart phones, tablet computers and portable wearable devices. In one embodiment, the terminal 102 can represent a consumer terminal, and the terminal 103 can represent a courier practitioner terminal; the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0066] In one embodiment, Figure 2 As shown, a consignment handling method is provided, which is applied to Figure 1 The server in is taken as an example to illustrate, including steps S210 to S240.

[0067] Step S210, receiving the shipping information of the consignment.

[0068] Among them, consignment refers to items that need to be transported by a logistics company. The shipping information is the information that must be included when sending the consignment. In one embodiment, the shipping information includes the sender information, the recipient information and the consignment information; wherein the sender information may include the sender's name and the sender's address; the recipient information may include the recipient's name and the recipient's address; the consignment information may include relevant information of the consignment, such as the specific content of the consignment (or the category to which the specific content belongs), the weight of the consignment, the size of the consignment, and so on. In another embodiment, when the sender initiates the shipping request not in person, the shipping information may also include the expected collection location, the expected collection time, the expected collection method, and so on. In one embodiment, the shipping information of the consignment is usually sent by the sender. In other embodiments, the shipping information of the consignment may also include other information.

[0069] Step S220: acquiring a target object image photographed for the consignment.

[0070] In one embodiment, obtaining the target object image photographed for the consignment occurs during the collection process; the target object image photographed for the consignment may be uploaded by the sender or by the collection staff.

[0071] In one embodiment, after receiving the consignment information and before obtaining the target object image taken of the consignment, it also includes: determining the corresponding collection personnel according to the consignment information; generating a collection task according to the consignment information and sending it to the terminal of the collection personnel.

[0072] This embodiment is a situation where the sender does not send the mailing request in person; when the sender does not send the mailing request in person, the logistics company needs to assign the corresponding collection personnel to the address agreed with the sender to collect the consigned items according to the mailing information. In one embodiment, determining the corresponding collection personnel according to the mailing information includes: determining the corresponding collection personnel according to the mailing address in the mailing information. Usually, the logistics company divides different responsible areas for the collection personnel. When receiving the mailing request, the responsible area to which it belongs is determined according to the mailing address, so that the mailing request can be assigned to the corresponding collection personnel. In another embodiment, determining the corresponding collection personnel according to the mailing information can also include: announcing the mailing information to the collection personnel responsible for the nearby area, and receiving the active order acceptance request from the collection personnel to determine the corresponding collection personnel. In another embodiment, determining the corresponding collection personnel according to the mailing information can also be combined with other information in the mailing information to determine the collection personnel, for example, the mailing information contains the collection time and collection address expected by the sender, then in this embodiment, the appropriate collection personnel can also be determined in combination with the collection time and collection address expected by the sender. Furthermore, in one embodiment, the pick-up personnel may be determined based on the pick-up time period expected by the sender in the mail information, the current location of the pick-up personnel, and the pick-up task plan; or the pick-up personnel may be determined based on the weight, size, and other information of the consigned items in the mail information. In other embodiments, the pick-up personnel corresponding to the mail information may be determined in any other feasible manner.

[0073] Furthermore, after the corresponding collection personnel are assigned to the shipment information, a corresponding collection task is generated according to the shipment information and forwarded to the collection personnel, who then follows up and handles the shipment task.

[0074] In this embodiment, when a delivery request is received, a suitable collection person is assigned to the sender based on the delivery information carried in the delivery request. This can be applicable to a scenario where, for example, the sender sends a delivery request at home and expects the collection person to pick up the delivery at home, thus bringing convenience to the sender.

[0075] Step S230: perform image detection on the target object image, and generate a waybill number if the target object image meets the preset image requirements.

[0076] In one embodiment, performing image detection on the target object image may include performing size detection, resolution detection, detection of whether the image contains a specific object, etc. The specific process of performing image detection on the target object image will be described in detail in the following embodiments and will not be repeated here.

[0077] In this embodiment, after the image of the target object is detected, if the detection result shows that the image of the target object meets the preset image requirements, it means that the collection meets the requirements, the collection is completed, and the transportation stage can be entered; wherein, the preset image requirements can be set according to the actual situation, for example, when the image detection includes detecting the image size, the preset image requirements may include a specified image size; when the image detection includes detecting the image resolution, the preset image requirements may include a specified resolution range; when the image detection includes detecting whether the image contains a specified object, the preset image requirements may include that the specified object must be included, or that the specified object must not be included, etc. In other embodiments, the preset image requirements may be set to other requirements.

[0078] Furthermore, in this embodiment, when the target object image meets the preset image requirements, a waybill number corresponding to the consignment is also generated. The waybill number is a unique code on the express waybill, and the transportation status of the corresponding consignment can be queried in the logistics management system through the waybill number.

[0079] Step S240, storing the target object image in correspondence with the waybill number and the shipping information.

[0080] After determining that the target object image meets the preset image requirements, the target object image is stored together with the waybill number and the consignment information, so as to facilitate the search for relevant information of the consignment in the subsequent process.

[0081] In one embodiment, during the transportation of the consignment, the method further includes: obtaining logistics information related to the consignment, and storing the logistics information in correspondence with the waybill number, the target object image, and the consignment information. The logistics information may be uploaded by the logistics practitioners who handle the consignment during the transportation process, so that consumers and logistics companies can query and understand the transportation status of the consignment.

[0082] After receiving the consignment information of the consignment, the above-mentioned consignment processing method obtains the target object image taken by the collection personnel when collecting the consignment, performs image detection on the target object image, and determines whether the target object image meets the preset image requirements. If it does, a waybill number can be generated, and the target object image is stored in correspondence with the consignment information and the waybill number to complete the collection process. The above-mentioned method requires uploading the image taken of the consignment during the collection process, and generates a waybill number when the image meets certain conditions, and stores the image together with the waybill number and the consignment information. If the specific location of the consignment needs to be found in the subsequent transportation process and delivery process, it can be searched in combination with the stored consignment image, which provides useful information for finding the consignment when it is lost.

[0083] In one embodiment, Figure 3As shown, after the target object image is stored in correspondence with the waybill number and the shipping information, steps S310 to S340 are also included.

[0084] Step S310, when the delivery information for the consignment is received, the delivery scenario confirmation information is sent to the consignee according to the consignment information.

[0085] Among them, the delivery information refers to the relevant information when the consignment is delivered. In one embodiment, after the consignment arrives at the last logistics outlet of the consignee's address, a delivery person needs to be assigned to the consignment. In this embodiment, the logistics information generated when the consignment is assigned to a specific delivery person is determined to be the delivery information received for the consignment. In another embodiment, after the consignment has been assigned to a specific delivery person, receiving a delivery request sent by the delivery person to the system is determined to be the receipt of the delivery information for the consignment. In other embodiments, the receipt of the delivery information for the consignment can also be determined by other means.

[0086] In this embodiment, after determining that the consignment transportation process is finished and the delivery process can be started, before the delivery personnel deliver the consignment, it is necessary to send delivery scene confirmation information to the consignee to confirm the expected delivery address (optional within the preset range of the consignment address), the expected delivery time (optional within the specified time period), the expected delivery method (optional within the specified delivery method), etc. to the consignee. In one embodiment, the delivery scene confirmation information sent to the consignee includes reminding the user that the consignment has entered the delivery process, so that the user can feedback the expected delivery address, delivery time and delivery method, etc. when receiving the delivery scene confirmation information. In another embodiment, the delivery scene confirmation information sent to the consignee includes: the candidate delivery address, candidate delivery time, and candidate delivery method selected by the delivery personnel. In this embodiment, the consignee can confirm whether the delivery can be carried out according to the candidate method based on the delivery scene confirmation information. In other embodiments, the delivery scene confirmation information can also include other information, such as whether it is necessary to deliver as soon as possible, etc.

[0087] Step S320, receiving delivery scenario target information based on delivery scenario confirmation information feedback.

[0088] It can be seen from the above steps that before the consignment is delivered, the delivery scene confirmation information is sent to the consignee. The delivery scene target information in this embodiment is the expected delivery scene information fed back by the consignee. In one embodiment, the delivery scene target information includes the delivery address, delivery time and delivery method expected by the consignee. Among them, the expected delivery address can be longitude and latitude information or the name of the expected delivery address (for example, ** collection point, ** express cabinet); further, in one embodiment, the expected delivery address also includes a scene image of the expected delivery address, such as a photo taken of a collection point, an express cabinet, etc. In other embodiments, the delivery scene target information may also include other information corresponding to the delivery scene confirmation information.

[0089] Step S330, obtaining actual information of the delivery scene when delivering the consignment.

[0090] Among them, the actual information of the delivery scene refers to the scene-related information uploaded by the delivery personnel when delivering the consignment, and the scene-related information is specifically the information of the location where the delivery personnel drops the consignment. In one embodiment, the actual information of the delivery scene may include the name of the delivery location (e.g., ** collection point, ** express cabinet), the longitude and latitude information of the delivery location, or a photo taken of the delivery location. In one embodiment, the photo taken of the delivery location includes the consignment. Furthermore, in one embodiment, the content contained in the actual information of the delivery scene corresponds to the target information of the delivery scene. For example, if the target information of the delivery scene includes longitude and latitude information, the actual information of the delivery scene should also include the longitude and latitude information of the actual delivery location, and other information is similar.

[0091] Step S340: If it is determined based on the delivery scenario target information that the actual information of the delivery scenario meets the delivery requirements, the delivery completion information of the consignment is generated.

[0092] After obtaining the actual information of the delivery scene transmitted back by the delivery personnel, the actual information of the delivery scene is compared with the target information of the delivery scene fed back by the recipient to confirm whether the delivery personnel meets the delivery requirements during delivery; if the actual information of the delivery scene transmitted back by the delivery personnel meets the delivery requirements, it means that the delivery personnel has not violated any regulations in accordance with the delivery symbol requirements for the consignment.

[0093] Among them, the delivery requirements can be set according to the content of the actual delivery scene target information. In one embodiment, if the delivery scene target information and the delivery scene actual information contain the target longitude and latitude information and the actual longitude and latitude information of the delivery location, it is determined whether the actual longitude and latitude information is within the preset range of the target longitude and latitude information. In another embodiment, if the delivery scene target information contains the name of the delivery location and / or a photo of the target delivery location, the delivery scene actual information contains the name of the delivery location and / or a photo of the actual delivery location; the judgment of the delivery scene actual information includes: judging whether the names of the target delivery location and the actual delivery location are the same, and / or judging whether the photo of the actual delivery location is consistent with the location in the photo of the target delivery location, and / or judging whether the location in the photo of the actual delivery location belongs to the location corresponding to the name of the target delivery location. In other embodiments, judging whether the delivery meets the delivery requirements can also be set to other judgment conditions.

[0094] In this embodiment, in the delivery scenario of consigned items, the delivery location, delivery time, delivery method, etc. expected by the consignee are obtained by sending delivery scenario confirmation information to the consignee, and the delivery personnel are required to perform delivery in combination with the delivery scenario target information fed back by the consignee, and the actual delivery location of the delivery personnel is checked by the actual delivery scenario information returned by the delivery personnel, and the delivery personnel is allowed to complete the operation only when the actual delivery scenario information meets the delivery requirements; on the one hand, delivery is performed in combination with the actual situation of the consignee, which can reduce the problem of delivery failure that occurs when the consignee is not at home, cannot get through the phone, etc., and improve the delivery completion rate, and from the user's perspective, the user can choose the delivery location, method and time, etc. expected by the user according to the actual situation, which can improve the user experience; on the other hand, the actual delivery scenario system of the delivery personnel is checked, which can reduce the occurrence of situations such as the delivery personnel delivering the consigned items to other locations without the operation of the consignee, and can also improve the user experience to a certain extent.

[0095] Furthermore, in one embodiment, the actual information of the delivery scene includes: an actual image of the delivery scene; in this embodiment, the above method also includes: performing scene classification on the delivery scene image based on a scene classification model determined through training, and determining the scene category corresponding to the actual image of the delivery scene; in this embodiment, the scene corresponding to the actual image of the delivery scene is compared with the delivery scene target information, and if the actual image of the delivery scene conforms to the delivery scene target information, it is determined that the actual image of the delivery scene meets the delivery requirements.

[0096] In this embodiment, taking the delivery scene actual information including the delivery scene actual image as an example, when determining whether the delivery scene actual image meets the delivery requirements, the delivery scene actual image is classified using a scene classification model to determine the scene category corresponding to the scene image. In a specific embodiment, the scene categories include only consignments, being placed at the door of a resident, at the door of a store, at a courier cabinet, an abnormal scene, etc.; the delivery scene actual image is scene classified by the scene classification model to determine the corresponding scene category, and then the determined scene category is compared with the delivery scene target information to determine whether it meets the delivery scene target information. If so, it is determined that the delivery scene actual image meets the delivery requirements. Further, in one embodiment, if it is determined that the delivery scene actual image meets the delivery requirements, qualified delivery information is fed back to the delivery personnel terminal; in another embodiment, if the scene classification corresponding to the delivery scene actual image is an abnormal scene, or the scene category of the delivery scene actual image does not meet the delivery scene target information (such as the target information is a collection point, and the actual image shows that the actual delivery location is a courier cabinet), it is determined that it does not meet the delivery requirements, and unqualified information is fed back to the delivery personnel terminal.

[0097] The scene classification model is determined in advance through training, and can be determined by training the classification model using scene-related sample image data. In a specific embodiment, the scene classification model uses the Efficientnet-b0 network (a neural network proposed by Google Brain), and the network is trained using scene-related sample image data, so that the trained Efficientnet-b0 network classifies the input image into scene categories such as consignment, resident door, store door, express cabinet, and abnormal scene (such as street scene). As shown in Figure 4 (1), the actual image of the delivery scene is a schematic diagram of only consignment, Figure 4 (2) shows a schematic diagram of the actual image of the delivery scene is a resident door, Figure 4 (3) shows a schematic diagram of the actual image of the delivery scene is a store door, Figure 4 (4) shows a schematic diagram of the actual image of the delivery scene is a express cabinet, and Figure 4 (5) shows a schematic diagram of the actual image of the delivery scene is an abnormal scene.

[0098] In other embodiments, the images can be classified into other categories, and the samples used in training also include the above categories. It can be understood that in other embodiments, other classification neural networks can also be used to implement scene classification of the delivery scene images. Figure 5 FIG. 4 is a schematic diagram of the structure of an Efficientnet-b0 network in a specific embodiment.

[0099] In this embodiment, the actual image of the delivery scene is detected through the scene classification network determined by training to determine whether it meets the scene in the delivery scene target information, and the delivery of the delivery personnel is restricted. This can reduce the situation where the delivery personnel deliver the consignment to other locations without permission, thereby improving the user experience.

[0100] In one embodiment, Figure 6 As shown, performing image detection on a target object image includes steps S610 to S630.

[0101] Step S610, performing consignment recognition on the target object image to obtain a consignment recognition result.

[0102] Among them, identifying the consignment in the target object image means determining whether the target object image contains the consignment. In one embodiment, performing consignment identification on the target object image includes: performing consignment identification on the target object image based on a target detection model determined through training.

[0103] After the target detection model is trained, it can detect whether the input image contains the target object, and output the area corresponding to the target object when the detection result is yes. In a specific embodiment, the target detection object is implemented using the PP-YOLO network. The network is trained using sample image data of the consignment, so that the PP-YOLO network determined by the training performs target detection on the input image; further, if the network detects the target, it divides the target into categories including single packages, letter packages, plastic packaging packages, multiple (more than 2) packages, and the like. In other embodiments, it can also be divided into other categories, and the samples used in training also include the above categories. It can be understood that in other embodiments, other target detection neural networks can also be used to implement target detection for delivery scene images. As Figure 7 FIG. 4 is a schematic diagram of the structure of a PP-YOLO network in a specific embodiment.

[0104] Step S620: classify the target object image by image quality to obtain a quality classification result.

[0105] In one embodiment, the image quality includes the size, resolution, and shooting quality of the image, etc. The quality of the image can be determined by classifying the image quality of the target object image. In one embodiment, classifying the image quality of the target object image includes: classifying the image quality of the target object image based on a classification network determined by training.

[0106] The classification network is used to classify the input image. In this embodiment, the classification network is used to classify the image quality of the target object image. In a specific embodiment, the classification network is implemented using the Efficientnet-b0 network, and the network is trained using sample image data of different image qualities, so that the Efficientnet-b0 network determined by the training can classify the image quality of the input image; further, in one embodiment, the image quality is divided into normal, blurred, too bright, too dark, occluded and other categories. In other embodiments, it can also be divided into other categories, and the samples used in training also include the above categories. It can be understood that in other embodiments, other classification neural networks can also be used to implement the image quality classification of the target object image.

[0107] Step S630: If it is determined according to the consignment identification result that the target object image contains the consignment and the quality classification result meets the preset quality requirement, it is determined that the target object image meets the preset image requirement.

[0108] According to the consignment recognition result, it can be determined whether the target object image contains consignments, and according to the quality classification result, the image quality classification result of the target object image can be determined. In this embodiment, the target object image is detected, specifically including determining that the target object image contains consignments and the quality meets the preset quality requirements, and then it is determined that the preset image requirements are met. Among them, the preset quality requirements can be set according to actual conditions. For example, if the quality classification results output by the quality classification result include normal, blurred, too bright, too dark, occluded and other categories, it can be set that the preset quality requirements are met when the quality classification result is normal; in another embodiment, if the quality classification results output by the quality classification result include quality scores, it can be set that the preset quality requirements are met when the quality classification results reach the preset score, and so on. The consignment recognition result is that a single parcel, a letter parcel, a plastic packaging parcel, a plurality of (more than 2) parcels, etc. are identified, and it can be determined that the consignment is identified in the target object image.

[0109] In another embodiment, if the target object image does not meet the preset image requirements, a prompt message indicating that the image is unqualified is sent to the terminal of the collection personnel, so that the collection personnel can re-upload the target object image taken for the consignment.

[0110] In this embodiment, when performing image detection on the target object image, it is mainly detected whether the target object image contains the consignment and whether the image quality meets the requirements. This can ensure that the target object image taken of the consignment and uploaded by the collection personnel when collecting the consignment meets the requirements, and the shape of the consignment can be seen normally, which is convenient for providing information when there is a search need.

[0111] Furthermore, in one embodiment, the above method also includes: performing face detection on the target object image based on the target detection model determined through training to obtain a face detection result; if it is determined according to the face detection result that the target object image contains a face, blurring the face area in the face detection result.

[0112] In this embodiment, the target detection model is trained to recognize faces to determine whether the target object image contains a face, and when a face is detected in the image, the face area is output. Furthermore, if a face is recognized in the target object image, the face area is blurred. The main consideration here is that when the collection personnel take the image of the consignment, the sender's face may be captured in the image. In order to protect the privacy of the user, in this embodiment, the face area is determined according to the face detection result output by the target detection model, and the face area is blurred to solve the situation where the target object image contains a face. Among them, blurring the face area can be achieved in any way, such as Gaussian blurring, etc.

[0113] In a specific embodiment, the target detection model used for face detection on the target object image can be a PP-YOLO network. In one of the embodiments, the target object image can be simultaneously detected whether it contains consignments and faces, and the network can be trained using sample image data containing faces and consignments, so that the trained PP-YOLO network performs target detection on the input image, and the output results include: whether it contains faces and / or consignments, and outputs the corresponding target area when it contains faces and / or consignments. Furthermore, when it is determined that a face is contained according to the output result, the face area is blurred; when it is determined that the consignment is contained according to the output result, whether the target object image meets the preset image requirements is determined in combination with whether the image quality meets the standards. For example, input a picture as follows Figure 7 In the PP-YOLO network shown, the face detection frame is output ( Figure 7 solid line frame) and consignment detection frame ( Figure 7 shown in dashed box).

[0114] In this embodiment, when performing image detection on a target object image, if a face is detected therein, the face area is blurred, which can protect the user's privacy and improve the user experience.

[0115] In a specific embodiment, the above-mentioned consignment handling method is described with a detailed example, including the following steps:

[0116] First, the application system framework of the above-mentioned consignment processing method is introduced. The system mainly includes consumer client, courier handheld device, and cloud data service center. The consumer client is used to send and receive relevant information; the courier handheld device is used to receive instruction information sent by the cloud data service center and to take and upload pictures; the cloud data service center is used to store the express delivery information database, including consignments and photos of the place of receipt.

[0117] Secondly, the above-mentioned consignment handling method mainly includes two processes: collecting consignment and delivering consignment.

[0118] 1. Collection process, such as Figure 8 As shown:

[0119] Consumers place orders for shipments through the client and upload the shipment information in advance, such as the delivery address, type, weight, etc. of the mailed items.

[0120] The cloud data service center receives the mailing information, allocates the appropriate collection personnel based on the sender's address information in the mailing information, and dispatches the collection task to the corresponding collection personnel.

[0121] The collection personnel go to the sender's address to collect the items according to the collection task instructions assigned by the service center. During the collection process, the collection personnel need to take photos of the consignment (the above-mentioned target object images) through a handheld device. In one embodiment, the photos of the consignment include two clear front photos of the consignment with the packaging and the back. After uploading the photos of the consignment to the cloud data service center, the image quality estimation module in the cloud data service center evaluates the image quality. After the quality assessment is qualified, it enters the detection module to detect whether the image contains the consignment. If the quality is qualified and the image contains the consignment, the photo of the consignment is stored in the warehouse. At the same time, the cloud data service center returns the image qualification instruction to the collection personnel's handheld device. The collection personnel collect the express and enter the transportation process.

[0122] 2. When the consignment is transported, it will enter the delivery process, such as Fig. 9 As shown:

[0123] When the consignment arrives at the courier distribution point where the consignment is located, the cloud data service center receives the delivery information of the consignment and sends delivery scenario confirmation information to the consignee's client. The delivery scenario confirmation information may include: signature by the consignee, placement at the recipient's address, collection point, and express cabinet.

[0124] The cloud data service center obtains the delivery scenario target information fed back by the consignee, and forwards the delivery scenario target information to the handheld device of the delivery personnel assigned to the consignment.

[0125] The delivery personnel will deliver the parcel to the designated location according to the delivery scene target information. After delivery, they need to take a photo of the actual delivery scene and upload it to the cloud data service center. If the parcel is signed for by the person himself, only the packaged consignment will be uploaded. If it is other delivery options, the actual delivery scene image must also include the delivery scene. The cloud data service center will also estimate the image quality of the actual delivery scene image to determine whether it meets the delivery scene target information and whether it contains the consignment in the target object image uploaded when the parcel is collected to determine whether the delivery is compliant.

[0126] In the above-mentioned consignment handling method, computer vision is used to collect images, detect and monitor the operations of collection and delivery personnel. In the process of express collection and delivery, clear photos of the package are uploaded and reviewed multiple times to meet the flexible signing wishes of consumers. It has more flexible platform adaptability. The client can use WeChat applet, and the cloud can be placed on Alibaba platform or cloud platforms such as Tencent. In addition, since three-dimensional information of the package, waybill number and consignment photo is established, it is of great significance to use image comparison to find when the express is lost.

[0127] It should be understood that, although each step in each flow chart involved in the above-described embodiment is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have strict order restrictions, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each flow chart involved in the above-described embodiment may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps.

[0128] In one embodiment, Fig.10 As shown, a consignment handling device is provided, comprising: a receiving module 1010, an image acquisition module 1020, an image detection module 1030 and a storage module 1040, wherein:

[0129] Receiving module 1010, used for receiving the shipping information of the consignment;

[0130] An image acquisition module 1020 is used to acquire an image of a target object photographed for the consignment;

[0131] The image detection module 1030 is used to perform image detection on the target object image and generate a waybill number if the target object image meets the preset image requirements;

[0132] The storage module 1040 is used to store the target object image in correspondence with the waybill number and the shipping information.

[0133] After receiving the consignment information of the consignment, the above-mentioned consignment processing device obtains the target object image taken by the collection personnel when collecting the consignment, performs image detection on the target object image, and determines whether the target object image meets the preset image requirements. If it does, it can generate a waybill number, and store the target object image in correspondence with the consignment information and the waybill number to complete the collection process. The above-mentioned device requires uploading the image taken of the consignment during the collection process, and generates a waybill number when the image meets certain conditions, and stores the image together with the waybill number and the consignment information. If the specific location of the consignment needs to be found in the subsequent transportation process and delivery process, it can be searched in combination with the stored consignment image, which provides useful information for finding the consignment when it is lost.

[0134] In one embodiment, the above-mentioned device also includes: a confirmation information sending module, which is used to send delivery scenario confirmation information to the recipient according to the mailing information when receiving the delivery information for the consignment; a feedback information receiving module, which is used to receive the delivery scenario target information based on the delivery scenario confirmation information feedback; an actual information acquisition module, which is used to obtain the actual information of the delivery scenario when the consignment is delivered; and a judgment module, which is used to generate delivery completion information of the consignment if it is determined that the actual information of the delivery scenario meets the delivery requirements based on the delivery scenario target information.

[0135] In one embodiment, the actual information of the delivery scene includes: an actual image of the delivery scene; in this embodiment, the above-mentioned device also includes: a scene classification module, which is used to classify the delivery scene image based on the scene classification model determined by training, and determine the scene category corresponding to the actual image of the delivery scene; the above-mentioned judgment module is also used to: compare the scene corresponding to the actual image of the delivery scene with the delivery scene target information, if the actual image of the delivery scene conforms to the delivery scene target information, it is determined that the actual image of the delivery scene meets the delivery requirements.

[0136] In one embodiment, the image detection module 1030 of the above-mentioned device includes: a consignment identification unit, which is used to perform consignment identification on the target object image to obtain a consignment identification result; a quality classification unit, which is used to perform image quality classification on the target object image to obtain a quality classification result; and a judgment unit, which is used to determine that the target object image meets the preset image requirements if it is determined that the target object image contains consignment based on the consignment identification result and the quality classification result meets the preset quality requirements.

[0137] In one embodiment, the consignment identification unit of the above-mentioned device is specifically used to: perform consignment identification on the target object image based on the target detection model determined through training.

[0138] In one embodiment, the quality classification unit of the above device is specifically used to: perform image quality classification on the target object image based on a classification network determined through training.

[0139] In one embodiment, the above-mentioned device also includes: a face detection module, which is used to perform face detection on the target object image based on the target detection model determined through training to obtain a face detection result; and a blur processing module, which is used to blur the face area in the face detection result if it is determined that the target object image contains a face according to the face detection result.

[0140] In one embodiment, the above-mentioned device also includes: a collection personnel determination module, which is used to determine the corresponding collection personnel according to the mailing information; and a task allocation module, which is used to generate a collection task according to the mailing information and send it to the collection personnel's terminal.

[0141] For the specific definition of the consignment handling device, please refer to the definition of the consignment handling method above, which will not be repeated here. Each module in the above-mentioned consignment handling device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0142] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.11 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as consignment information, image information and logistics information. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a consignment processing method is implemented.

[0143] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0144] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0145] Receive the consignment information; obtain the target object image taken for the consignment; perform image detection on the target object image, and if the target object image meets the preset image requirements, generate a waybill number; store the target object image in correspondence with the waybill number and the consignment information.

[0146] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0147] When receiving the delivery information for the consignment, the delivery scenario confirmation information is sent to the consignee according to the mailing information; the delivery scenario target information based on the feedback of the delivery scenario confirmation information is received; the delivery scenario actual information when the consignment is delivered is obtained; if it is determined based on the delivery scenario target information that the delivery scenario actual information meets the delivery requirements, the delivery completion information of the consignment is generated.

[0148] In one embodiment, when the processor executes the computer program, the following steps are also implemented: classifying the delivery scene image based on the scene classification model determined through training, and determining the scene category corresponding to the actual image of the delivery scene; comparing the scene corresponding to the actual image of the delivery scene with the delivery scene target information, and if the actual image of the delivery scene conforms to the delivery scene target information, determining that the actual image of the delivery scene meets the delivery requirements.

[0149] In one embodiment, when the processor executes the computer program, the following steps are also implemented: performing consignment identification on the target object image to obtain a consignment identification result; performing image quality classification on the target object image to obtain a quality classification result; if it is determined that the target object image contains consignment based on the consignment identification result, and the quality classification result meets the preset quality requirements, it is determined that the target object image meets the preset image requirements.

[0150] In one embodiment, when the processor executes the computer program, the following steps are further implemented: performing consignment recognition on the target object image based on the target detection model determined through training.

[0151] In one embodiment, when the processor executes the computer program, the following steps are further implemented: classifying the image quality of the target object image based on the classification network determined by training.

[0152] In one embodiment, when the processor executes the computer program, the following steps are also implemented: performing face detection on the target object image based on the target detection model determined through training to obtain a face detection result; if it is determined according to the face detection result that the target object image contains a face, blurring the face area in the face detection result.

[0153] In one embodiment, when the processor executes the computer program, the following steps are also implemented: determining the corresponding collection personnel according to the mailing information; generating a collection task according to the mailing information and sending it to the terminal of the collection personnel.

[0154] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0155] Receive the consignment information; obtain the target object image taken for the consignment; perform image detection on the target object image, and if the target object image meets the preset image requirements, generate a waybill number; store the target object image in correspondence with the waybill number and the consignment information.

[0156] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when receiving delivery information for consignment, sending delivery scenario confirmation information to the consignee according to the mailing information; receiving delivery scenario target information based on feedback of the delivery scenario confirmation information; obtaining actual delivery scenario information when the consignment is delivered; if it is determined based on the delivery scenario target information that the actual delivery scenario information meets the delivery requirements, generating delivery completion information for the consignment.

[0157] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: classifying the delivery scene image based on the scene classification model determined through training, and determining the scene category corresponding to the actual image of the delivery scene; comparing the scene corresponding to the actual image of the delivery scene with the delivery scene target information, and if the actual image of the delivery scene conforms to the delivery scene target information, determining that the actual image of the delivery scene meets the delivery requirements.

[0158] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: performing consignment identification on the target object image to obtain a consignment identification result; performing image quality classification on the target object image to obtain a quality classification result; if it is determined that the target object image contains consignment based on the consignment identification result, and the quality classification result meets the preset quality requirements, it is determined that the target object image meets the preset image requirements.

[0159] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: performing consignment recognition on the target object image based on the target detection model determined through training.

[0160] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: classifying the image quality of the target object image based on the classification network determined by training.

[0161] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: face detection is performed on the target object image based on the target detection model determined through training to obtain a face detection result; if it is determined according to the face detection result that the target object image contains a face, blurring the face area in the face detection result.

[0162] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the corresponding collection personnel according to the mailing information; generating a collection task according to the mailing information and sending it to the terminal of the collection personnel.

[0163] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0164] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0165] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for handling consignment, characterized in that: The method comprises: Receive the consignment information; Acquire a target object image photographed for the consignment; Performing image detection on the target object image, and generating a waybill number if the target object image meets preset image requirements; Storing the target object image, the waybill number, and the shipping information in correspondence with each other; When receiving the delivery information for the consignment, sending the delivery scene confirmation information to the consignee according to the consignment information; Receiving delivery scenario target information based on the delivery scenario confirmation information feedback; Acquire actual information of the delivery scene when delivering the consignment; If it is determined based on the delivery scenario target information that the actual information of the delivery scenario meets the delivery requirements, delivery completion information of the consignment is generated.

2. The method according to claim 1, characterized in that The actual information of the delivery scene includes: an actual image of the delivery scene; The method further comprises: Performing scene classification on the delivery scene image based on the scene classification model determined through training, and determining the scene category corresponding to the actual image of the delivery scene; The scene corresponding to the actual image of the delivery scene is compared with the target information of the delivery scene. If the actual image of the delivery scene conforms to the target information of the delivery scene, it is determined that the actual image of the delivery scene meets the delivery requirements.

3. The method according to claim 1, characterized in that The performing image detection on the target object image comprises: Performing consignment recognition on the target object image to obtain a consignment recognition result; Performing image quality classification on the target object image to obtain a quality classification result; If it is determined that the target object image contains the consignment according to the consignment identification result, and the quality classification result meets the preset quality requirement, it is determined that the target object image meets the preset image requirement.

4. The method according to claim 3, characterized in that The method comprises at least one of the following: The first item, The performing consignment recognition on the target object image comprises: performing consignment recognition on the target object image based on a target detection model determined through training; The second item, The performing image quality classification on the target object image includes: performing image quality classification on the target object image based on a classification network determined through training.

5. The method according to claim 3, characterized in that: The method further comprises: Performing face detection on the target object image based on the target detection model determined through training to obtain a face detection result; If it is determined according to the face detection result that the target object image contains a face, blurring is performed on the face region in the face detection result.

6. The method according to any one of claims 1 to 5, characterized in that: After receiving the consignment information of the consignment and before acquiring the target object image photographed for the consignment, the method further includes: Determine the corresponding collection personnel according to the mailing information; A collection task is generated according to the mailing information and sent to the terminal of the collection personnel.

7. A consignment handling device, characterized in that: The device comprises: A receiving module, used for receiving the shipping information of the consignment; An image acquisition module, used to acquire an image of a target object photographed for the consignment; An image detection module is used to perform image detection on the target object image, and generate a waybill number if the target object image meets the preset image requirements; A storage module, used for storing the target object image, the waybill number, and the shipping information in correspondence with each other; A confirmation information sending module, configured to send delivery scene confirmation information to the recipient according to the consignment information when receiving the delivery information for the consignment; A feedback information receiving module, used for receiving delivery scenario target information based on the delivery scenario confirmation information feedback; An actual information acquisition module, used to acquire actual information of a delivery scene when delivering the consignment; A judgment module is used to generate delivery completion information of the consignment if it is determined that the actual information of the delivery scene meets the delivery requirements based on the delivery scene target information.

8. The device according to claim 7, characterized in that The actual information of the delivery scene includes: an actual image of the delivery scene; the device also includes a scene classification module, which is used to: classify the delivery scene image based on a scene classification model determined through training, and determine the scene category corresponding to the actual image of the delivery scene; The judgment module is also used to compare the scene corresponding to the actual image of the delivery scene with the target information of the delivery scene, and if the actual image of the delivery scene conforms to the target information of the delivery scene, determine that the actual image of the delivery scene meets the delivery requirements.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images