Method and device for processing a single

Abstract

The present invention discloses a waybill processing method and device, which relate to the field of smart logistics technology. A specific implementation of the method includes: obtaining one or more package information; the package information includes a waybill image and a waybill logo on the package; identifying the waybill image, and determining abnormal package information from the one or more package information; generating an offline task according to the abnormal package information, so as to generate an abnormal data record corresponding to the abnormal package information by using the offline task; and correcting the abnormal package information according to the abnormal data record. This implementation reduces the impact of waybill anomalies on the logistics link, improves transportation efficiency and accuracy, and achieves the purpose of supervising the pasting behavior of waybill.

Description

Technical Field

[0001] The present invention relates to the field of smart logistics technology, and in particular to a waybill processing method and device. Background Art

[0002] The waybill is a document used in logistics to record information about the sender, recipient, and product, and it runs through the entire process of logistics transportation. Irregular pasting of waybills will have a serious impact on important links in logistics such as sorting, transportation, and acceptance. At present, waybills are usually printed and pasted manually, which is prone to irregular pasting. Therefore, there is an urgent need for a method to supervise and improve the standardization of waybill pasting to improve transportation efficiency and accuracy. Summary of the invention

[0003] In view of this, the embodiment of the present invention provides a method and device for processing a delivery bill, which can identify the delivery bill image on the package to determine the abnormal package information, generate corresponding abnormal data records using offline tasks, and then correct the abnormal package information according to the abnormal data records. In this way, packages with abnormal delivery bill pasting can be screened out and corrected in time, reducing the impact of abnormal delivery bill pasting on other subsequent links and improving transportation efficiency and accuracy.

[0004] In addition, by generating positive and negative feedback records and punishing or rewarding the operators and source users corresponding to the abnormal package information, the purpose of supervising the pasting behavior of the waybill can be achieved and the standardization of the pasting of the waybill can be further improved.

[0005] To achieve the above object, according to a first aspect of an embodiment of the present invention, a method for processing a shipping label is provided, comprising:

[0006] Obtain one or more package information; the package information includes a label image and a label logo on the package;

[0007] Identify the label image and determine abnormal package information from the one or more package information;

[0008] Generate an offline task according to the abnormal package information, so as to generate an abnormal data record corresponding to the abnormal package information by using the offline task;

[0009] According to the abnormal data record, the abnormal package information is corrected.

[0010] Optionally, the abnormal data record further includes: the source of the package information and the operator information of the package; after the correction processing of the abnormal package information, it also includes:

[0011] Generate a negative feedback record corresponding to the operator information and / or a positive feedback record corresponding to the source of the package information according to the abnormal data record;

[0012] According to the negative feedback record and / or the positive feedback record, resources are allocated to the user corresponding to the operator information and / or the source end respectively.

[0013] Optionally, when there are multiple pieces of package information,

[0014] Storing the plurality of package information in a first database;

[0015] The stored multiple package information is input into a convolution model, and the convolution model is used to determine the abnormal package information and the abnormal type of the abnormal package information from the multiple package information.

[0016] Optionally, the identifying the waybill image and determining abnormal package information from the one or more package information includes:

[0017] Inputting the waybill image into at least two image processing models respectively, and obtaining the abnormality type of the waybill image outputted by the at least two image processing models respectively;

[0018] Determining whether the abnormality types respectively output by the at least two image processing models are consistent;

[0019] If yes, determine that the package information corresponding to the waybill image is abnormal package information, and use the abnormal type as the abnormal type of the abnormal package information.

[0020] Optionally, correction processing is performed on the abnormal package information according to the abnormal data record and the abnormal type of the abnormal package information.

[0021] Optionally, generating an offline task according to the abnormal package information includes:

[0022] According to a preset period, the metadata corresponding to the abnormal package information in the first database is pushed to the second database; the metadata includes: the source end of the package information, the waybill image and the waybill logo;

[0023] The offline task is generated according to the metadata in the second database.

[0024] Optionally, the generating the abnormal data record corresponding to the abnormal package information by using the offline task includes:

[0025] Determining a shipping type for the package;

[0026] When the distribution type is a delivery type, obtaining operator information of the package from a warehouse data source;

[0027] When the delivery type is a pick-up type, obtaining operator information of the package from a pick-up site data source;

[0028] The metadata is supplemented according to the operator information by using the offline task to generate the abnormal data record.

[0029] According to a second aspect of an embodiment of the present invention, a bill processing device is provided, comprising: an acquisition module, an identification module and a processing module; wherein:

[0030] The acquisition module is used to acquire one or more pieces of package information; the package information includes a label image and a label logo on the package;

[0031] The recognition module is used to recognize the label image and determine abnormal package information from the one or more package information;

[0032] The processing module is used to generate an offline task according to the abnormal package information, so as to generate an abnormal data record corresponding to the abnormal package information by using the offline task; and perform correction processing on the abnormal package information according to the abnormal data record.

[0033] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, including:

[0034] one or more processors;

[0035] a storage device for storing one or more programs,

[0036] When the one or more programs are executed by the one or more processors, the one or more processors implement any method described in the method for processing a shipping label provided in the first aspect above.

[0037] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, any method described in the method for processing a shipping label provided in the first aspect above is implemented.

[0038] One embodiment of the above invention has the following advantages or beneficial effects: it can identify the package image to determine the abnormal package information, generate the corresponding abnormal data record by offline task, and then correct the abnormal package information according to the abnormal data record. In this way, the packages with abnormal label pasting can be screened out and corrected in time, which reduces the impact of abnormal label pasting on other subsequent links and improves transportation efficiency and accuracy.

[0039] In addition, by generating positive and negative feedback records and punishing or rewarding the operators and source users corresponding to the abnormal package information, the purpose of supervising the pasting behavior of the waybill can be achieved and the standardization of the pasting of the waybill can be further improved.

[0040] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0042] Figure 1 It is a flowchart of a method for processing a shipping order provided by an embodiment of the present invention;

[0043] Figure 2 It is a schematic diagram of a process for generating abnormal data records provided by an embodiment of the present invention;

[0044] Figure 3 It is a flow chart of generating positive and negative feedback records provided by an embodiment of the present invention;

[0045] Figure 4 It is a flowchart of another method for processing a shipping order provided by an embodiment of the present invention;

[0046] Figure 5 It is a structural schematic diagram of a bill processing device provided by an embodiment of the present invention;

[0047] Figure 6 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0048] Figure 7 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0050] It should be pointed out that the embodiments of the present invention and the technical features therein may be combined with each other without conflict.

[0051] like Figure 1As shown, the embodiment of the present invention provides a method for processing a shipping order, which may include the following steps S101 to S104

[0052] Step S101: Obtain one or more package information; the package information includes the label image and label logo on the package.

[0053] Among them, the package information can be uploaded manually or automatically uploaded by an integrated shooting device. For example, a person (such as a sorting staff) can scan the QR code on the package with a barcode scanner to obtain the waybill identification and upload it to the background. When the person finds that the waybill on the package is not pasted in accordance with the specifications, the terminal is used to take a picture of the location of the waybill on the current package (that is, the waybill picture), and then manually upload it to the background. In one embodiment of the present invention, it is preferred that the package information is obtained by using an integrated shooting device to simultaneously take a picture of the waybill on the package while scanning the waybill QR code. For example, the integrated shooting machine in the sorting center can automatically take a picture of the waybill on the package when scanning the QR code of the package on the conveyor belt, and then upload it to the background.

[0054] After obtaining one or more package information, in specific implementation, the one or more package information can be stored in a database, for example, in a Mysql database or a Sqlserver database.

[0055] Step S102: Identify the delivery note image and determine abnormal package information from the one or more package information.

[0056] It is understandable that one application scenario of the present invention is to identify situations where the face sheet is not pasted in a standardized manner. For example, the face sheet is not pasted flatly, forming wrinkles; the face sheet is not pasted on the largest surface of the package box; the face sheet is pasted on the seam of the package, etc. These face sheets that are not pasted in a standardized manner may affect other links in the subsequent logistics. These packages that are not pasted in a standardized manner can be determined as abnormal packages, thereby determining the abnormal package information.

[0057] In one embodiment of the present invention, the integrated photographing device usually scans and photographs multiple packages within a period of time, thereby obtaining multiple package information. In the case of multiple package information, the following method can be used to determine abnormal package information: input the stored multiple package information into a convolution model, and use the convolution model to determine the abnormal package information and the abnormal type of the abnormal package information from the multiple package information.

[0058] Among them, the exception type can be pre-set for the above-mentioned irregular pasting behavior, and an exception code can be defined for each exception type. For example, exception code 1001 can correspond to the situation where the face sheet is not pasted evenly; 1002 can correspond to the situation where the face sheet is not pasted on the largest surface of the package box; 1003 can correspond to the situation where the face sheet is pasted on the seam of the package, etc.

[0059] For example, the waybill images in the multiple package information stored in the Mysql database can be input into a convolutional model (convolutional neural network model), and the model predicts whether each waybill image is an abnormal waybill image based on the location where the waybill in each image is pasted on the package, and identifies the abnormal type of each waybill image with abnormal pasting according to the output of the convolutional model. Among them, the convolutional neural network model is obtained after training based on multiple labeled waybill images with abnormal pasting. Therefore, a large number of waybill images can be quickly identified using the convolutional model, so as to determine the abnormal package information and the corresponding abnormal type, which can reduce the workload of manual identification of waybill images, improve the recognition speed of multiple waybill images, and thus improve the efficiency of waybill processing.

[0060] In order to further improve the accuracy of waybill image recognition, an implementation method of step S102 may also be: input the waybill image into at least two image processing models respectively, and obtain the abnormal type of the waybill image output by the at least two image processing models respectively; determine whether the abnormal types output by the at least two image processing models are consistent; if so, determine that the package information corresponding to the waybill image is abnormal package information, and use the abnormal type as the abnormal type of the abnormal package information.

[0061] In one embodiment of the present invention, two image processing models can be selected to identify a face order image. For example, for a face order image X, a convolution model can be used to identify X first. When it is determined to be an abnormal face order image, an abnormal type A corresponding to X is output; a support vector machine (SVM) is used to identify X again. When it is determined that X is an abnormal face order image, an abnormal type B of the face order image X is output, and it is determined whether A and B are consistent. If they are consistent, the package information corresponding to the face order image X is determined to be abnormal package information, and then the abnormal type A (B) is used as the abnormal type of the abnormal package information. In addition, the face order image X can also be marked with an abnormal code a corresponding to the abnormal type A.

[0062] Using at least two image processing models to identify a single face image can improve the accuracy of image recognition, thereby improving the accuracy of abnormal package information.

[0063] After determining the abnormal package information and its corresponding abnormal type, the source end corresponding to the abnormal package information can be obtained, that is, the uploader of the abnormal package information. For example, if the abnormal package information is uploaded by a sorting staff, the employee ID of the sorting staff can be set as the source end ID; if the abnormal package information is uploaded by an integrated camera, the employee ID of the person in charge of the integrated camera can be set as the source end ID; or in any link of the logistics transportation, if the abnormal package information is uploaded by a staff member for the first time, the staff member ID can be used as the source end ID.

[0064] Update the source information and the exception type (exception code) to the data corresponding to the abnormal package information stored in the MySQL database to form metadata corresponding to the abnormal package. For example, the metadata may include the bill identification, bill image URL address, source identification, and exception code corresponding to the abnormal package information.

[0065] Step S103: generating an offline task according to the abnormal package information, so as to generate an abnormal data record corresponding to the abnormal package information by using the offline task.

[0066] When generating an offline task, an implementable method of step S103 may be adopted: according to a preset period, the metadata corresponding to the abnormal package information in the first database is pushed to the second database; the metadata includes: the source of the package information, the waybill image and the waybill logo; and the offline task is generated according to the metadata.

[0067] The first database may be a Mysql database, and the second database may be a hive database in a big data scenario. Metadata is extracted from the first database and pushed to the second database, so that data from different databases can be stored in a targeted manner according to specific usage scenario requirements, which can improve the efficiency of data storage and query.

[0068] Then, the offline task can be a task that pushes metadata from the Mysql database to the hive database and completes the data. It can be understood that offline tasks are different from real-time tasks. The process of completing the metadata corresponding to the abnormal package information does not need to interact with the real-time business, and can be completed using the offline data stored in the hive database. In this way, interference with real-time business and real-time data can be avoided, reducing the impact on real-time business. In addition, you can also select an offline task that generates and executes data completion during idle business hours, such as generating an offline task for data completion every morning. In this way, more computing resources can be obtained for offline tasks, which improves the efficiency of data completion and reduces resource usage during busy business hours.

[0069] Then, when an abnormal data record is generated according to the offline task corresponding to the metadata, an implementable method of step S103 can be adopted: determine the distribution type of the package; when the distribution type is the delivery type, obtain the operator information of the package from the warehouse data source; when the distribution type is the collection type, obtain the operator information of the package from the collection site data source; use the offline task to supplement the metadata according to the operator information to generate the abnormal data record.

[0070] The operator information is the information of the staff who prints and pastes the waybill. For example, in the case of delivery, the operator information may be the information of the packing operator in the warehouse, and in the case of collection, the operator information may be the information of the collection operator.

[0071] While obtaining the operator information, the corresponding originating logistics site information can also be obtained, and then the metadata is supplemented with the logistics site identifier corresponding to the originating logistics site information and the operator identifier corresponding to the operator information. In one embodiment of the present invention, the abnormal data record obtained after completion may include: the waybill identifier corresponding to the abnormal package information, the waybill image URL address, the source end identifier, the abnormal code, the logistics site identifier, and the operator identifier.

[0072] In one embodiment of the present invention, the process of generating an abnormal data record can be as follows: Figure 2 As shown, steps S201 to S205 may be included:

[0073] Step S201: Push metadata from the MySQL database to the Hive database regularly.

[0074] You can set a daily schedule to push metadata to the hive database. The metadata includes: waybill ID, waybill image URL address, source end ID, and exception code.

[0075] Step S202: Generate offline tasks regularly and query waybill information according to the waybill ID.

[0076] In the hive database, query the detailed tracking information of the waybill according to the waybill ID.

[0077] Step S203: Determine the delivery type.

[0078] Determine the corresponding delivery type based on the originating station type corresponding to the waybill identification. The delivery type can include warehouse delivery and sales department collection.

[0079] Step S204: In the case of warehouse delivery type, obtain packaging information from the warehouse data source to determine the operator information; in the case of sales department collection type, obtain collection information from the collection data source to determine the operator information.

[0080] Step S205: Complete the metadata and generate an abnormal data record.

[0081] While obtaining the operator information, the originating logistics site identifier can be obtained, and the identifier corresponding to the operator information and the originating logistics site identifier can be added to the metadata to generate an abnormal data record.

[0082] Step S104: Correct the abnormal package information according to the abnormal data record.

[0083] In a specific implementation, the following method may be adopted: correcting the abnormal package information according to the abnormal data record and the abnormal type of the abnormal package information.

[0084] For example, if the delivery note is not pasted evenly, resulting in the recipient being unable to confirm the acceptance, the recipient information can be obtained according to the delivery note identifier in the abnormal data record, and the delivery person can manually print the delivery note and paste it again after confirming the abnormal type; the parcels corresponding to the abnormal parcel information can also be centrally stored according to the abnormal type during sorting, so as to correct and handle according to different abnormal types; for example, the severity of the abnormal type can be evaluated, and the delivery note can be reprinted and re-pasted for the parcels corresponding to the abnormal parcel information with more serious abnormal types, so as to avoid further impact on subsequent logistics links and improve logistics efficiency; the cause of the abnormal type in the logistics site can also be checked according to the logistics site identifier in the abnormal data record, so as to improve and correct the corresponding packaging operation process of the logistics site, so as to avoid the occurrence of parcels with irregular delivery notes pasted again; in addition, the abnormal data records in the hive database can also be processed into reports and displayed using the display terminal. For example, according to the logistics site identifier, a report can be generated for the abnormal data record corresponding to the site, and then pushed to the display terminal corresponding to the logistics site, so that the personnel of the logistics site can perform statistics and analysis of the abnormal type according to the display result, so as to check the possible irregular delivery note pasting in the process, so as to correct and handle it.

[0085] After the abnormal package information is corrected, resource allocation may be performed on the operator and source end in the abnormal data record, and the following method provided by the embodiment of the present invention may be adopted: according to the abnormal data record, a negative feedback record corresponding to the operator information and / or a positive feedback record corresponding to the source end of the package information is generated; according to the negative feedback record and / or the positive feedback record, resources are allocated to users corresponding to the operator information and / or the source end respectively.

[0086] Among them, the negative feedback record can be a record of punishing the user corresponding to the operator information; the positive feedback record can be a record of rewarding the user corresponding to the source end.

[0087] In one embodiment of the present invention, after the abnormal data record is generated, the abnormal data record can be periodically extracted from the hive database to the database for resource allocation processing.

[0088] The metadata pushed from the MySQL database is completed through the hive database, and then extracted to the database for resource allocation processing. Therefore, the hive database can be used to process big data according to the business needs of different databases, thereby effectively isolating the interactive operations between different business databases and improving the efficiency of big data processing.

[0089] Taking the generation of reward points and penalty points for the source of abnormal package information and the operator who affixes the label to the abnormal package as an example, the process of generating positive and negative feedback records provided by the embodiment of the present invention is described in detail. Specifically, it can be as follows: Figure 3 As shown, steps S301 to S305 are included:

[0090] Step S301: Obtain abnormal data records from the reward and punishment database.

[0091] The reward and punishment database may be a relational database, such as a SQL, MySQL database, etc. The data in the reward and punishment database may be extracted from the hive database according to a fixed period. The extracted data is the abnormal data record in the hive database.

[0092] Step S302: Generate reward and punishment scores based on abnormal data records.

[0093] According to each abnormal data record, two scores with the status of pending confirmation can be created: one is the penalty score of the person responsible for the abnormal package (the user corresponding to the operator information), and the other is the reward score of the person who reported the abnormal package information (the user corresponding to the source end). Among them, the status of the reward score is linked to the status of the penalty score, that is, the change of the penalty score status will trigger the change of the reward score status.

[0094] Step S303: Push the penalty score to the responsible person's terminal for confirmation or appeal.

[0095] The person responsible can view the corresponding waybill image and information based on the abnormal data records associated with the penalty points, and confirm whether he is responsible on the terminal.

[0096] Step S304: monitor the status of penalty scoring.

[0097] By monitoring the status of penalty points through the message middleware, the confirmation or appeal operation of the responsible person on the terminal can trigger the status change of the penalty points.

[0098] Step S305: Determine whether the status is confirmed; if yes, that is, the person responsible accepts the responsibility, then both the reward points and the penalty points are in the confirmed status; if no, that is, the person responsible does not accept the responsibility after appeal, then both the reward points and the penalty points are in the invalid status.

[0099] In one embodiment of the present invention, when the status of the reward score changes to confirmed, the reward score can be pushed to the terminal of the reporter for display.

[0100] In addition, a confirmation deadline can be set. If the responsible person fails to confirm within the confirmation deadline, the reward, penalty and penalty points can be automatically set to the confirmed status.

[0101] Through the reward and punishment database and reward and punishment process, the responsible person will be punished accordingly, and the reporter will be rewarded accordingly, so as to achieve the purpose of supervising the face-to-face pasting operation.

[0102] Combine the following Figure 4 , further describes a method for processing a shipping label provided by an embodiment of the present invention. Figure 4 , specifically, it may include steps S401 to S411:

[0103] Step S401: Take a picture of the waybill manually or using an all-in-one machine and obtain the waybill logo.

[0104] Step S402: Store the package information in the MySQL database.

[0105] Among them, the package information includes the waybill logo and waybill picture; the MySQL database is also the first database.

[0106] Step S403: Input the face order image into the convolutional model for recognition.

[0107] Step S404: Determine whether the label image is abnormal; if so, trigger step S405; if not, do nothing and follow the normal process.

[0108] Step S405: Input the abnormal face order image into the image processing model for re-recognition to determine the abnormal type and corresponding abnormal package information.

[0109] The image processing model may be other commonly used image processing models different from the convolution model, such as an image processing model based on algorithms such as a support vector machine and a decision tree.

[0110] Determine the abnormal package information corresponding to the abnormal waybill image, update the abnormal type and source identifier to the abnormal package information, and generate metadata.

[0111] Step S406: The metadata corresponding to the abnormal package information is regularly pushed from the MySQL database to the hive database, and an offline task is generated.

[0112] Among them, the hive database is also the second database.

[0113] Step S407: Use offline tasks to complete data and generate abnormal data records.

[0114] When implementing it specifically, Figure 2 The process is shown in the figure.

[0115] Step S408: Perform correction processing according to the abnormal data record and the abnormal type.

[0116] Step S409: extract abnormal data records into the reward and punishment database.

[0117] In the embodiment of the present invention, step S408 and step S409 are performed in no particular order, that is, step S408 may be performed first and then step S409; step S409 may be performed first and then step S408; or step S408 and step S409 may be performed simultaneously.

[0118] Step S410: Generate reward and punishment scores, and reward or punish the reporter and the person responsible.

[0119] When implementing it specifically, Figure 3 The process is shown in the figure.

[0120] Step S411: display at a display terminal.

[0121] The reward and punishment scores and abnormal data can be recorded and displayed on the display terminal, where the display terminal can be each display terminal for displaying big data reports, or it can be a display terminal corresponding to a logistics site.

[0122] According to an embodiment of the present invention, a method for processing a delivery bill is provided, which can identify the delivery bill image on the package to determine abnormal package information, generate corresponding abnormal data records using offline tasks, and then correct the abnormal package information according to the abnormal data records. In this way, the package information with abnormal delivery bill pasting can be screened out and corrected in time, reducing the impact of the abnormal delivery bill pasting on other subsequent links and improving transportation efficiency and accuracy.

[0123] In addition, by generating positive and negative feedback records and punishing or rewarding the operators and source users corresponding to the abnormal package information, the purpose of supervising the pasting behavior of the waybill can be achieved and the standardization of the pasting of the waybill can be further improved.

[0124] like Figure 5 As shown, the embodiment of the present invention provides a bill processing device 500, comprising: an acquisition module 501, an identification module 502 and a processing module 503; wherein,

[0125] The acquisition module 501 is used to acquire one or more pieces of package information; the package information includes a label image and label logo on the package;

[0126] The identification module 502 is used to identify the label image and determine abnormal package information from the one or more package information;

[0127] The processing module 503 is used to generate an offline task according to the abnormal package information, so as to generate an abnormal data record corresponding to the abnormal package information by using the offline task; and perform correction processing on the abnormal package information according to the abnormal data record.

[0128] In one embodiment of the present invention, the identification module 502 is used to store the multiple package information through the first database when there are multiple package information; input the stored multiple package information into the convolution model, and use the convolution model to determine the abnormal package information and the abnormal type of the abnormal package information from the multiple package information.

[0129] In one embodiment of the present invention, the identification module 502 is used to input the waybill image into at least two image processing models respectively, and obtain the abnormal type of the waybill image output by the at least two image processing models respectively; determine whether the abnormal types output by the at least two image processing models are consistent; if so, determine that the package information corresponding to the waybill image is abnormal package information, and use the abnormal type as the abnormal type of the abnormal package information.

[0130] In one embodiment of the present invention, the processing module 503 is used to perform correction processing on the abnormal package information according to the abnormal data record and the abnormal type of the abnormal package information.

[0131] In one embodiment of the present invention, the processing module 503 is used to determine that the abnormal data record also includes: the source end of the package information and the operator information of the package; based on the abnormal data record, generate a negative feedback record corresponding to the operator information and / or a positive feedback record corresponding to the source end of the package information; based on the negative feedback record and / or the positive feedback record, allocate resources to users corresponding to the operator information and / or the source end respectively.

[0132] In one embodiment of the present invention, the processing module 503 is used to push the metadata corresponding to the abnormal package information in the first database to the second database according to a preset period; the metadata includes: the source of the package information, the waybill image and the waybill logo; and generate the offline task according to the metadata in the second database.

[0133] In one embodiment of the present invention, the processing module 503 is used to determine the delivery type of the package; when the delivery type is the delivery type, obtain the operator information of the package from the warehouse data source; when the delivery type is the collection type, obtain the operator information of the package from the collection site data source; use the offline task to supplement the metadata according to the operator information to generate the abnormal data record.

[0134] According to an embodiment of the present invention, a delivery bill processing device is provided, which can identify the delivery bill image on the package to determine the abnormal package information, and use the offline task to generate the corresponding abnormal data record, and then correct the abnormal package information according to the abnormal data record. In this way, the packages with abnormal delivery bill pasting can be screened out and corrected in time, which reduces the impact of the abnormal delivery bill pasting on other subsequent links and improves the transportation efficiency and accuracy.

[0135] In addition, by generating positive and negative feedback records and punishing or rewarding the operators and source users corresponding to the abnormal package information, the purpose of supervising the pasting behavior of the waybill can be achieved and the standardization of the pasting of the waybill can be further improved.

[0136] Figure 6 An exemplary system architecture 600 is shown to which the method or device for processing a shipping bill according to an embodiment of the present invention can be applied.

[0137] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0138] Users can use terminal devices 601, 602, 603 to interact with server 605 through network 604 to receive or send messages, etc.

[0139] The terminal devices 601 , 602 , and 603 may be various electronic devices having a display screen and supporting information browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0140] Server 605 may be a server that provides information processing services, such as a backend server that manages package information sent by users using terminal devices 601, 602, and 603. The backend server may recognize the received label image, analyze and process data such as abnormal package information, and feed back the processing results to the terminal device.

[0141] It should be noted that the waybill processing method provided in the embodiment of the present invention is generally executed by the server 605, and accordingly, the waybill processing device is generally set in the server 605.

[0142] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0143] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of a terminal device suitable for implementing an embodiment of the present invention. Figure 7 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0144] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0145] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0146] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present invention are executed.

[0147] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0148] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0149] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, they may be described as: a processor includes an acquisition module, an identification module, and a processing module. The names of these modules do not, in some cases, limit the modules themselves. For example, the acquisition module may also be described as a "module for acquiring package information."

[0150] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: obtaining one or more package information; the package information includes a label image and a label mark on the package; identifying the label image, and determining abnormal package information from the one or more package information; generating an offline task according to the abnormal package information, so as to generate an abnormal data record corresponding to the abnormal package information by using the offline task; and correcting the abnormal package information according to the abnormal data record.

[0151] According to the technical solution of the embodiment of the present invention, it is possible to identify the package image on the package to determine the abnormal package information, and use the offline task to generate the corresponding abnormal data record, and then correct the abnormal package information according to the abnormal data record. In this way, packages with abnormal label pasting can be screened out and corrected in time, reducing the impact of abnormal label pasting on other subsequent links and improving transportation efficiency and accuracy. In addition, by generating positive and negative feedback records, punishing or rewarding the operators and source-end users corresponding to the abnormal package information, the purpose of supervising the label pasting behavior can be achieved, and the standardization of label pasting can be further improved.

[0152] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for processing a shipping order. It is characterized in that include: Obtain one or more package information; the package information includes a label image and a label logo on the package; Identify the label image and determine abnormal package information from the one or more package information; Generate an offline task according to the abnormal package information, so as to generate an abnormal data record corresponding to the abnormal package information by using the offline task; The abnormal data record also includes: the source of the package information and the operator information of the package; According to the abnormal data record, correct the abnormal package information; Generate a negative feedback record corresponding to the operator information and / or a positive feedback record corresponding to the source of the package information according to the abnormal data record; According to the negative feedback record and / or the positive feedback record, resources are allocated to the user corresponding to the operator information and / or the source end respectively.

2. The method according to claim 1, It is characterized in that In the case where there are multiple pieces of package information, Storing the plurality of package information in a first database; The stored multiple package information is input into a convolution model, and the convolution model is used to determine the abnormal package information and the abnormal type of the abnormal package information from the multiple package information.

3. The method according to claim 1, It is characterized in that The identifying the waybill image and determining abnormal package information from the one or more package information includes: Inputting the waybill image into at least two image processing models respectively, and obtaining the abnormality type of the waybill image outputted by the at least two image processing models respectively; Determining whether the abnormality types respectively output by the at least two image processing models are consistent; If yes, determine that the package information corresponding to the waybill image is abnormal package information, and use the abnormal type as the abnormal type of the abnormal package information.

4. The method according to claim 2 or 3, It is characterized in that Correction processing is performed on the abnormal package information according to the abnormal data record and the abnormal type of the abnormal package information.

5. The method according to claim 2, It is characterized in that Generate an offline task according to the abnormal package information, including: According to a preset period, the metadata corresponding to the abnormal package information in the first database is pushed to the second database; the metadata includes: the source end of the package information, the waybill image and the waybill logo; The offline task is generated according to the metadata in the second database.

6. The method according to claim 5, It is characterized in that The generating the abnormal data record corresponding to the abnormal package information by using the offline task includes: Determining a shipping type for the package; When the distribution type is a delivery type, obtaining operator information of the package from a warehouse data source; When the delivery type is a pick-up type, obtaining operator information of the package from a pick-up site data source; The metadata is supplemented according to the operator information by using the offline task to generate the abnormal data record.

7. A bill processing device, It is characterized in that include: Acquisition module, identification module and processing module; wherein, The acquisition module is used to acquire one or more pieces of package information; the package information includes a label image and a label logo on the package; The recognition module is used to recognize the label image and determine abnormal package information from the one or more package information; The processing module is used to generate an offline task according to the abnormal package information, so as to use the offline task to generate an abnormal data record corresponding to the abnormal package information; the abnormal data record also includes: the source end of the package information and the operator information of the package; according to the abnormal data record, the abnormal package information is corrected; according to the abnormal data record, a negative feedback record corresponding to the operator information and / or a positive feedback record corresponding to the source end of the package information is generated; according to the negative feedback record and / or the positive feedback record, resources are allocated to users corresponding to the operator information and / or the source end respectively.

8. An electronic device, It is characterized in that include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images