Packaging material cancel-after-verification method, device, equipment, medium and computer program product

Abstract

The invention relates to a packaging material cancel-after-verification method and device, computer equipment, a storage medium and a computer program product, and relates to the technical field of image processing and logistics. The method comprises the following steps: acquiring image information and waybill identifiers of express items in a plurality of sorting links; performing package identification processing on each piece of image information to obtain a package identification result; aggregating the package identification result of the image information according to the waybill identifier associated with the image information to obtain an aggregation identification result corresponding to each waybill identifier; the aggregation identification result comprises a packaging material type and a packaging material source corresponding to the waybill identifier; and according to an aggregation identification result corresponding to the plurality of waybill identifiers obtained in the target time period, determining the consumption of the packaging material of each packaging material type in the target time period of the preset mechanism. According to the invention, various types of packaging materials of the logistics institution can be efficiently and accurately cancelled after verification.

Description

Technical Field

[0001] The present application relates to the technical fields of image processing and logistics, and in particular, to a method, device, computer device, storage medium, and computer program product for verifying and writing off packaging materials. Background Art

[0002] With the development of the express logistics industry, the number of express deliveries that logistics agencies need to process is increasing day by day, and the demand for packaging materials also increases accordingly. In order to achieve reasonable allocation of materials, logistics agencies usually need to count the packaging materials used for express deliveries and determine the consumption of different types of packaging materials.

[0003] In traditional packaging material statistics, it usually relies on manual entry to record the sources and types of packaging materials used for each express delivery, and then counts the usage of various types of packaging materials provided by the logistics agency itself. However, the express deliveries that logistics agencies need to process usually mix different sources and types of packaging materials. The manual entry method is inefficient and prone to errors and omissions, and it is difficult to meet the needs of logistics agencies for counting and verifying the packaging materials of a large number of express deliveries. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer device, storage medium, and computer program product for verifying and writing off packaging materials in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for verifying and writing off packaging materials. The method includes:

[0006] Obtaining image information and waybill identifiers of express deliveries at multiple sorting links;

[0007] Performing packaging recognition processing on each piece of the image information to obtain a packaging recognition result;

[0008] Aggregating the packaging recognition results of the image information according to the waybill identifiers associated with the image information to obtain an aggregated recognition result corresponding to each waybill identifier; the aggregated recognition result includes the types and sources of packaging materials corresponding to the waybill identifier;

[0009] Determining the consumption of packaging materials of each packaging material type of a preset institution during the target period according to the aggregated recognition results corresponding to multiple waybill identifiers obtained during the target period.

[0010] In one embodiment, the process of performing packaging recognition processing on each piece of the image information to obtain a packaging recognition result includes: performing anomaly detection on the image information to obtain an anomaly detection result; if the anomaly detection result indicates that the image information belongs to non-anomalous image information, then performing material type classification processing on the image information to obtain a material classification result; if the material classification result indicates that the packaging material belongs to a known type of packaging material, then performing material source identification on the image information to obtain a material source identification result; and obtaining the packaging recognition result of the image information based on the material classification result and the material source identification result.

[0011] In one embodiment, the process of performing material source identification on the image information to obtain a material source identification result includes: determining whether the image information contains visual recognition elements of a preset institution based on the detection of institutional elements in the image information; if it contains such elements, then obtaining the material source identification result that the packaging material is from the preset institution; if it does not contain such elements, then determining whether the image information contains visual recognition elements of other known institutions based on the identification of institutional elements in the image information; if so, then obtaining the material source identification result that the packaging material is from the other known institution.

[0012] In one embodiment, the process of performing anomaly detection on the image information to obtain an anomaly detection result includes: performing imaging anomaly detection on the image information according to the image acquisition method of the image information to obtain an imaging anomaly detection result; if the imaging anomaly detection result indicates that the imaging of the image information is normal, then obtaining a quantity detection result based on the detection of the number of express items in the image information; if the quantity detection result indicates that the number of express items corresponding to the image information meets the preset conditions, then obtaining the anomaly detection result that the image information belongs to non-anomalous image information; if the imaging anomaly detection result indicates that the imaging of the image information is anomalous, or the quantity detection result indicates that the number of express items corresponding to the image information does not meet the preset conditions, then obtaining the anomaly detection result that the image information belongs to anomalous image information.

[0013] In one embodiment, the method further includes: if the anomaly detection result indicates that the image information belongs to anomalous image information, or the material classification result indicates that the packaging material belongs to an unknown type of packaging material, or the material source identification result is an unknown source, then determining the packaging recognition result of the image information as a preset result.

[0014] In one embodiment, determining the consumption amount of packaging materials of each packaging material type of a preset institution in the target period according to the aggregated recognition results corresponding to multiple waybill identifiers obtained within the target period includes: obtaining a target result set with the source of the packaging materials being the preset institution according to the aggregated recognition results corresponding to multiple waybill identifiers obtained within the target period; determining the target result quantity corresponding to each packaging material type according to the target result set; and determining the consumption amount of packaging materials of each packaging material type of the preset institution in the target period according to the target result quantity corresponding to each packaging material type.

[0015] In a second aspect, the present application further provides a packaging material verification device. The device includes:

[0016] An information acquisition module, configured to acquire image information and waybill identifiers of express items in multiple sorting links;

[0017] A packaging recognition module, configured to perform packaging recognition processing on each piece of the image information to obtain a packaging recognition result;

[0018] A result aggregation module, configured to aggregate the packaging recognition results of the image information according to the waybill identifiers associated with the image information to obtain an aggregated recognition result corresponding to each waybill identifier; the aggregated recognition result includes the packaging material type and the source of the packaging materials corresponding to the waybill identifier;

[0019] A consumption amount determination module, configured to determine the consumption amount of packaging materials of each packaging material type of a preset institution in the target period according to the aggregated recognition results corresponding to multiple waybill identifiers obtained within the target period.

[0020] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0021] Acquire image information and waybill identifiers of express items in multiple sorting links; perform packaging recognition processing on each piece of the image information to obtain a packaging recognition result; aggregate the packaging recognition results of the image information according to the waybill identifiers associated with the image information to obtain an aggregated recognition result corresponding to each waybill identifier; the aggregated recognition result includes the packaging material type and the source of the packaging materials corresponding to the waybill identifier; determine the consumption amount of packaging materials of each packaging material type of a preset institution in the target period according to the aggregated recognition results corresponding to multiple waybill identifiers obtained within the target period.

[0022] Fourthly, the present application also provides a computer-readable storage medium. On the computer-readable storage medium, a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0023] Obtain the image information and waybill identifier of the express item in multiple sorting links; perform packaging recognition processing on each of the image information to obtain a packaging recognition result; aggregate the packaging recognition results of the image information according to the waybill identifier associated with the image information to obtain an aggregated recognition result corresponding to each waybill identifier; the aggregated recognition result includes the packaging material type and packaging material source corresponding to the waybill identifier; determine the consumption amount of the packaging materials of each packaging material type of a preset institution in the target period according to the aggregated recognition results corresponding to multiple waybill identifiers obtained in the target period.

[0024] Fifthly, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0025] Obtain the image information and waybill identifier of the express item in multiple sorting links; perform packaging recognition processing on each of the image information to obtain a packaging recognition result; aggregate the packaging recognition results of the image information according to the waybill identifier associated with the image information to obtain an aggregated recognition result corresponding to each waybill identifier; the aggregated recognition result includes the packaging material type and packaging material source corresponding to the waybill identifier; determine the consumption amount of the packaging materials of each packaging material type of a preset institution in the target period according to the aggregated recognition results corresponding to multiple waybill identifiers obtained in the target period.

[0026] The above packaging material verification method, device, computer equipment, storage medium, and computer program product obtain the image information and waybill identifier of express parcels in multiple sorting links, perform packaging recognition processing on each piece of image information to obtain a packaging recognition result, and then aggregate the packaging recognition results of the image information according to the waybill identifier associated with the image information to obtain an aggregated recognition result corresponding to each waybill identifier. The aggregated recognition result includes the packaging material type and the source of the packaging material corresponding to the waybill identifier. Then, based on the aggregated recognition results corresponding to multiple waybill identifiers obtained within the target time period, determine the consumption quantity of the packaging materials of each packaging material type by the preset institution during the target time period. This solution combines the characteristic that the express parcel processing process of the logistics institution usually includes multiple sorting links, obtains the image information and waybill identifier of express parcels in multiple sorting links, and performs packaging recognition on each piece of image information. Without manual entry, it can efficiently obtain the packaging recognition results of all express parcels that have experienced the sorting link, effectively improve the acquisition efficiency of express parcel packaging information and avoid omissions while reducing labor costs. Then, aggregating the packaging recognition results in the image dimension according to the waybill identifier associated with the image information can combine the packaging recognition results of the same express parcel in different sorting links, comprehensively judge the packaging material type and the source of the packaging material of the express parcel to obtain an aggregated recognition result, and can avoid the impact of incorrect recognition results in a single link on the final result, effectively improving the accuracy of the packaging material recognition of express parcels. Furthermore, based on the aggregated recognition results corresponding to each waybill identifier within the target time period, it is possible to count the consumption of different types of packaging materials by the logistics institution during the target time period and obtain a statistical verification result with higher accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic flowchart of the packaging material verification method in an embodiment;

[0028] Figure 2 It is a schematic flowchart of the step of performing packaging recognition processing on image information in an embodiment;

[0029] Figure 3 It is a schematic flowchart of the step of performing anomaly detection on image information in an embodiment;

[0030] Figure 4 It is a schematic flowchart of the step of performing source recognition of materials on image information in an embodiment;

[0031] Figure 5 It is a schematic flowchart of the step of determining the consumption quantity of packaging materials in an embodiment;

[0032] Figure 6 It is a schematic flowchart of the packaging material verification method in another embodiment;

[0033] Figure 7 It is a structural block diagram of a packaging material verification device in an embodiment;

[0034] Figure 8 It is an internal structure diagram of a computer device in an embodiment. Specific embodiments

[0035] In order to make the purpose, technical solutions and advantages of the present application clearer, the following further details the present application in combination 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.

[0036] In one embodiment, as Figure 1 shown, a packaging material verification method is provided. In this embodiment, an example is given where this method is applied to a server. It can be understood that this method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0037] Step S101, obtain the image information and waybill identifier of the express package at multiple sorting links.

[0038] Specifically, after the express package is picked up by a logistics agency, it can pass through multiple transfer stations, and each transfer station can sort the express package through one or more automated sorting devices. Among them, each automated sorting device that the express package experiences can correspond to a sorting link.

[0039] Exemplarily, in this step, the image of the express package on the device can be collected through an image acquisition device set on the automated sorting device, and the waybill identifier of the express package can be obtained through an identifier acquisition device set on the automated sorting device. Among them, the image acquisition device can include an area array camera, a line scan camera, etc. The identifier acquisition device can be a device such as a code scanning camera that can directly identify the graphic code of the express package and obtain the waybill identifier, or a device that can perform image recognition on the image information obtained by the image acquisition device to obtain the waybill identifier contained therein.

[0040] In this step, after obtaining the image information and waybill identifier of the express package in the sorting link, the image information and waybill identifier of the express package can be bound to each other.

[0041] Step S102, perform packaging recognition processing on each image information to obtain a packaging recognition result.

[0042] In this step, the acquired image information can be processed for package recognition. Among them, the package recognition processing can determine the package material type and the source of the package material of the express package included in the image information by means of image recognition or the like. According to the recognized package material type and the source of the package material, the package recognition result corresponding to the image information can be obtained.

[0043] Exemplarily, the package material types can include cartons, waterproof bags, document envelopes, unknown types, etc., and the sources of the package materials can include preset institutions, other known institutions, unknown sources, etc. The package recognition results can include categories such as preset institution cartons, preset institution waterproof bags, preset institution document envelopes, other known institution cartons, other known institution waterproof bags, other known institution document envelopes, preset results, etc. In addition, the package recognition result can also include the result confidence level. Among them, the preset institution can be this logistics institution, and the preset result can be that the package material type is an unknown type, or the source of the package material is an unknown source, etc.

[0044] Step S103: Aggregate the package recognition results of the image information according to the waybill identifier associated with the image information to obtain an aggregated recognition result corresponding to each waybill identifier; the aggregated recognition result includes the package material type and the source of the package material corresponding to the waybill identifier.

[0045] In this step, the package recognition results corresponding to the image information obtained from multiple sorting links can be summarized, and then the package recognition results are aggregated according to the waybill identifier bound to the image information.

[0046] Among them, the package recognition result of the image information can include the package material type, the source of the package material, and the result confidence level. The aggregation of the package recognition results can be for multiple package recognition results corresponding to the same waybill identifier. First, the part belonging to the preset result category is excluded, and then the result confidence levels of the remaining package recognition results are summed according to the categories of the package material type and the source of the package material. According to the categories of the package material type and the source of the package material with the largest sum of the result confidence levels, the aggregated recognition result corresponding to the waybill identifier is obtained.

[0047] Among them, the aggregation of the package recognition results can also be to count the categories of the package material type and the source of the package material in multiple package recognition results corresponding to the same waybill identifier, and according to the categories of the package material type and the source of the package material with the largest statistical quantity, the aggregated recognition result corresponding to the waybill identifier is obtained.

[0048] Step S104: Determine the consumption quantity of the package materials of each package material type of the preset institution during the target time period according to the aggregated recognition results corresponding to multiple waybill identifiers obtained during the target time period.

[0049] In this step, the aggregated recognition results corresponding to multiple waybill identifiers obtained in the target period can be summarized according to different packaging material types and packaging material sources. According to the number of waybill identifiers corresponding to each packaging material type with the packaging material source being the preset institution in the summary result, the consumption quantity of the packaging materials of each packaging material type of the preset institution in the target period can be determined.

[0050] Exemplarily, the above steps S101 and S102 can be executed at the edge side and the packaging recognition result of the image information can be transmitted to the cloud server. Then, the cloud server can store the obtained packaging recognition result in the data warehouse and regularly execute steps S103 and S104 through the data engine to obtain the consumption quantity of the packaging materials of each packaging material type of the preset institution in the target period.

[0051] For the above packaging material verification method, the image information and waybill identifiers of the express parcels are obtained in multiple sorting links, each image information is subjected to packaging recognition processing to obtain a packaging recognition result, and then the packaging recognition results of the image information are aggregated according to the waybill identifiers associated with the image information to obtain an aggregated recognition result corresponding to each waybill identifier, where the aggregated recognition result includes the packaging material type and packaging material source corresponding to the waybill identifier. Then, according to the aggregated recognition results corresponding to multiple waybill identifiers obtained within the target period, the consumption quantity of the packaging materials of each packaging material type of the preset institution in the target period is determined. This solution combines the characteristic that the express parcel processing process of the logistics institution usually includes multiple sorting links, obtains the image information and waybill identifiers of the express parcels in multiple sorting links, and performs packaging recognition on each image information, and can efficiently obtain the packaging recognition results of all express parcels that have experienced the sorting links without manual entry, which can effectively improve the acquisition efficiency of the express parcel packaging information and avoid omission while reducing the labor cost. Then, aggregating the packaging recognition results in the image dimension according to the waybill identifiers associated with the image information can combine the packaging recognition results of the same express parcel in different sorting links, comprehensively judge the packaging material type and packaging material source of the express parcel to obtain an aggregated recognition result, which can avoid the influence of incorrect recognition results in a single link on the final result and effectively improve the accuracy of the packaging material recognition of the express parcel. Furthermore, based on the aggregated recognition results corresponding to each waybill identifier within the target period, the consumption of different types of packaging materials of the logistics institution in the target period can be counted to obtain a statistical verification result with higher accuracy.

[0052] In one embodiment, as Figure 2 shown, step S102, performing packaging recognition processing on each image information to obtain a packaging recognition result, includes:

[0053] Step S201, performing anomaly detection on the image information to obtain an anomaly detection result.

[0054] Specifically, affected by the acquisition environment and acquisition timing, the image information collected in the sorting process may have abnormal imaging, failure to capture express items, and other abnormal situations that are likely to affect package recognition. Based on this, in this step, the image information can be first subjected to anomaly detection.

[0055] In one embodiment, as Figure 3 shown, performing anomaly detection on the image information to obtain an anomaly detection result may include:

[0056] Step S301, performing imaging anomaly detection on the image information according to the image acquisition method of the image information to obtain an imaging anomaly detection result.

[0057] In this step, for the image information obtained by using different image acquisition methods, corresponding methods can be adopted to perform imaging anomaly detection.

[0058] Among them, when the image information is collected by a area array camera, since the area array camera usually performs image acquisition with the assistance of a fill light, when the acquisition timing of the area array camera does not match the lighting timing of the fill light, it is easy to cause the collected image information to be overexposed.

[0059] Based on this, in this step, the image information collected by the area array camera can be input into the first classification network model to obtain an exposure classification result output by the model. Among them, the first classification network model can classify the exposure category of the image information according to the brightness of the input image information and output a classification result of "overexposure" or "normal exposure". Among them, when the exposure category of the image information is "overexposure", it can be determined that the imaging anomaly detection result of the image is the imaging anomaly of the image information, and when the exposure category of the image information is "normal exposure", it can be determined that the imaging anomaly detection result of the image is the imaging normal of the image information.

[0060] Among them, when the image information is collected by a line array camera, since the line array camera obtains complete image information by scanning the object row by row and then splicing the multiple scanned images, the image information collected by the line array camera is not easily overexposed, but is prone to being too dark, or having an abnormal image aspect ratio, etc.

[0061] Based on this, in this step, for the image information collected by the linear array camera, the aspect ratio abnormality and whether it is too dark can be judged respectively. Among them, for the aspect ratio abnormality, the width and height of the image information can be obtained, and then the ratio of the width to the height can be calculated. When the ratio is within the preset range, it can be determined that the aspect ratio of the image information is normal; otherwise, it can be determined that the aspect ratio of the image information is abnormal. Exemplarily, the preset range can be from 0.1 to 10. When the ratio is less than 0.1 or greater than 10, it can be determined that the aspect ratio of the image information is abnormal. Among them, for whether it is too dark, the image information can be converted into a grayscale image, and then a grayscale histogram corresponding to the image information can be generated. According to the grayscale histogram, the proportion of the overly dark pixels in the image information can be counted. When this proportion is greater than the set threshold, it is determined that the image information is too dark; otherwise, it is determined that the image information is not too dark. Among them, when the aspect ratio of the image information is abnormal or the image information is too dark, it can be determined that the imaging abnormality detection result of the image is the imaging abnormality of the image information. When the aspect ratio of the image information is normal and the image information is not too dark, it can be determined that the imaging abnormality detection result of the image is the imaging normality of the image information.

[0062] Step S302, if the imaging abnormality detection result is the imaging normality of the image information, then based on the detection of the number of express parcels in the image information, the number detection result is obtained.

[0063] Specifically, when the imaging abnormality detection result obtained in the above step is the imaging normality of the image information, in this step, the number of express parcels included in the image information can be further detected to determine whether the number of express parcels in the image information meets the preset conditions. Among them, the preset conditions can be determined according to the number of waybill identifiers bound to the image information. For example, when the image information is bound to one waybill identifier, the preset condition can be that the number of express parcels included in the image information is 1. In addition, since it is difficult to identify the packaging materials of the obscured express parcels when there are overlapping express parcels in the image information, in this step, it can also be detected whether there are overlapping parcels in the image information. When it is detected that there are overlapping parcels, it can be considered that the number of express parcels corresponding to the image information does not meet the preset conditions.

[0064] Exemplarily, in this step, the image information can be input into the first detection network model to obtain the detection result output by the model. Among them, the first detection network model can be a trained target recognition model, and the target recognition model can be SSD (Single Shot Multibox Detector, a single-stage multi-layer object detection model), YOLO (You Only Look Once, a second type of object recognition technology designed for speed and real-time use), RCNN (Region-based Convolutional Neural Networks, region-based convolutional neural network), etc. It can perform object detection on the express items and overlapping items in the input image information and output the detected object classification and the bounding box of the object in the image information. Among them, when the object classification output by the first detection network model includes overlapping items, it can be determined that the quantity detection result of the image information is that the quantity of express items corresponding to the image information does not meet the preset conditions. When the object classification output by the first detection network model does not include overlapping items, it can be further determined whether the quantity of express items corresponding to the image information meets the preset conditions according to the number of bounding boxes of the express items that are the object classification output by the model. Exemplarily, when the preset condition is that the number of express items included in the image information is 1, when the number of bounding boxes of the express items that are the object classification output by the model is 0 or greater than 1, it can be determined that the quantity detection result is that the quantity of express items corresponding to the image information does not meet the preset conditions.

[0065] Step S303, if the quantity detection result is that the quantity of express items corresponding to the image information meets the preset conditions, then the abnormal detection result is obtained that the image information belongs to non-abnormal image information.

[0066] In this step, for the image information whose quantity detection result is that the quantity of express items corresponding to the image information meets the preset conditions, it can be determined that the imaging of the image information is normal and contains the normal quantity of express items. Therefore, it can be determined that the image information belongs to non-abnormal image information, and the abnormal detection result of the image information is obtained.

[0067] Step S304, if the imaging abnormal detection result is that the imaging of the image information is abnormal, or the quantity detection result is that the quantity of express items corresponding to the image information does not meet the preset conditions, then the abnormal detection result is obtained that the image information belongs to abnormal image information.

[0068] In this step, for the image information whose imaging abnormal detection result is that the imaging of the image information is abnormal, or the quantity detection result is that the quantity of express items corresponding to the image information does not meet the preset conditions, it can be determined that it is difficult to obtain the correct material classification result and material source identification result for this image information in subsequent processing. Therefore, it can be considered that the image information belongs to abnormal image information, and the abnormal detection result of the image information is obtained.

[0069] The above process can use targeted anomaly detection means for different image acquisition methods of image information. Moreover, when the detection shows normal imaging, it also detects the number of express items in the image information, covering multiple abnormal scenarios of the image information and obtaining comprehensive and accurate anomaly detection results.

[0070] Step S202: If the anomaly detection result indicates that the image information belongs to non-abnormal image information, perform material classification processing on the image information to obtain a material classification result.

[0071] After the above anomaly detection, when the anomaly detection result is that the image information belongs to non-abnormal image information, in this step, the image information can be further subjected to material classification processing to determine the type of packaging material used for the express item corresponding to the image information.

[0072] Exemplarily, in this step, the first image information corresponding to the express parcel area can be selected from the image information, and the first image information is input into the second classification model to obtain the classification result output by the model. Among them, the second classification model can be a classification network model trained using pictures of packaging materials of common materials, which can classify the input image information according to the packaging material and output a material classification result. Exemplarily, the classification results that the second classification model can output include document envelopes, waterproof bags, cardboard boxes, foam boxes, gunny bags / small packages, and other materials. Among them, the material classification result of other materials can be obtained after the second classification model determines that the packaging material corresponding to the first image information does not belong to other classification results.

[0073] Furthermore, by comparing the type of the packaging material with the types of packaging materials used by the preset institution and capable of setting identifiers, it can be determined whether the packaging material corresponding to the image information belongs to a known type. Exemplarily, when the packaging materials used by the preset institution and set with identifiers include document envelopes, waterproof bags, and cardboard boxes, according to the material classification result corresponding to the document envelope, it can be determined that the packaging material in the image information belongs to a known type of packaging material, while according to the material classification result corresponding to the foam box, it can be determined that the packaging material in the image information belongs to an unknown type of packaging material.

[0074] Step S203: If the material classification result indicates that the packaging material belongs to a known type of packaging material, perform material source identification on the image information to obtain a material source identification result.

[0075] Specifically, when the material classification result of the image information indicates that the packaging material belongs to a known type of packaging material, in this step, the image information can be further subjected to material source identification, and according to the material source identification result, the source of the packaging material in the image information can be determined.

[0076] In one embodiment, as Figure 4 shown, perform material source identification on the image information to obtain a material source identification result, including:

[0077] Step S401: Determine whether the image information contains visual recognition elements of a preset institution based on the detection of institutional elements in the image information.

[0078] Specifically, in this step, it can first be determined whether the packaging material corresponding to the image information is a packaging material sourced from a preset institution by detecting whether the image information contains visual recognition elements of the preset institution. Among them, the visual recognition elements of the preset institution can include the logo of the preset institution, combinations of colors and shapes, etc.

[0079] Exemplarily, in this step, the image information can be input into a second detection network model to obtain the detection result output by the model. Among them, the second detection network model can be a detection model trained using images containing visual recognition elements of a preset institution, which can detect whether the output image information contains visual recognition elements of the preset institution and output a detection result. Among them, the detection result can be "contained" or "not contained".

[0080] Step S402: If it is contained, obtain the material source identification result that the packaging material is sourced from a preset institution.

[0081] When the detection of institutional elements in the image information determines that the image information contains visual recognition elements of a preset institution, in this step, it can be determined that the material source identification result of the image information is that the packaging material is sourced from a preset institution.

[0082] Step S403: If it is not contained, determine whether the image information contains visual recognition elements of other known institutions based on the identification of institutional elements in the image information.

[0083] Since when the detection of institutional elements in the image information determines that the image information does not contain visual recognition elements of a preset institution, it cannot be directly determined that the packaging material corresponding to the image information is not sourced from a preset institution. In this step, the image information can be further identified for institutional elements to determine whether it contains visual recognition elements of other known institutions.

[0084] Exemplarily, in this step, the image information can be input into the third classification network model to obtain the classification result output by the model. Among them, the third classification network model can be a classification model trained using an image containing visual recognition elements of one or more other known institutions. It can classify the image information based on whether the input image information contains visual recognition elements of other known institutions and output a classification result of "contains" or "does not contain". Among them, when the classification result output by the third classification network model is "contains", it can be determined that the image information contains visual recognition elements of other known institutions; otherwise, it can be determined that the image information does not contain visual recognition elements of other known institutions.

[0085] Step S404, if so, the material source recognition result is obtained that the packaging material comes from other known institutions.

[0086] When the recognition of the institutional elements of the image information determines that the image information contains visual recognition elements of other known institutions, in this step, it can be determined that the material source recognition result of the image information is that the packaging material comes from other known institutions.

[0087] Regarding the material source of the image information in the above process, first judge whether it contains visual recognition elements of a preset institution. If it does not contain, then judge whether it contains visual recognition elements of other known institutions. It can quickly determine the material recognition result from the preset institution without wasting too much computing resources. Then, through the detection of visual recognition elements of other known institutions, a result that is not from the preset institution can be obtained, which is conducive to quick exclusion in subsequent processing. Furthermore, the efficiency of verifying the packaging materials of the preset institution can be effectively improved.

[0088] Step S204, according to the material classification result and the material source recognition result, obtain the packaging recognition result of the image information.

[0089] Based on the material classification result obtained after the material texture classification process of the image information and the material source recognition result obtained after the material source recognition of the image information, in this step, the two can be combined to obtain the packaging recognition result of the image information.

[0090] In some other embodiments, the packaging recognition result can also include the result confidence level, which can be obtained by combining the confidence level of the material classification result obtained in the material texture classification process and the confidence level of the material source recognition result obtained in the material source recognition.

[0091] Through the above process of performing anomaly detection, material material classification processing, and material source identification on the image information in sequence, it is possible to screen the image information with abnormal image information, unknown material types, and unknown material sources layer by layer, and then efficiently process the image information with relatively high reference value, and avoid processing the image information with relatively low reference value, which can effectively save computing resources.

[0092] In one embodiment, the method of the present application may further include: if the anomaly detection result is that the image information belongs to abnormal image information, or the material classification result is that the packaging material belongs to an unknown type of packaging material, or the material source identification result is an unknown source, then determine the packaging identification result of the image information as a preset result.

[0093] Specifically, in this embodiment, for the image information with abnormal results or unknown results obtained in the above multiple detections, such as the anomaly detection result is that the image information belongs to abnormal image information, or the material classification result is that the packaging material belongs to an unknown type of packaging material, or the material source identification result is an unknown source, etc., the packaging identification result of the image information is uniformly determined as a preset result, so that these image information can be conveniently distinguished from other types of image information in subsequent statistics.

[0094] In this embodiment, for the image information with relatively low reference value determined in the anomaly detection, material material classification processing, and material source identification, the packaging identification result is uniformly determined as a preset result, which can facilitate the distinction from the packaging identification results obtained by normal identification in subsequent aggregation, and can improve the aggregation efficiency of the packaging identification results and the overall efficiency of verifying the packaging materials.

[0095] In one embodiment, as Figure 5 shown, step S104, according to the aggregated recognition results corresponding to multiple waybill identifiers obtained within the target time period, determine the consumption quantity of the packaging materials of each packaging material type of the preset institution within the target time period, including:

[0096] Step S501, according to the aggregated recognition results corresponding to multiple waybill identifiers obtained within the target time period, obtain a target result set with the packaging material source being the preset institution.

[0097] Step S502, according to the target result set, determine the target result quantity corresponding to each packaging material type.

[0098] Step S503, according to the target result quantity corresponding to each packaging material type, determine the consumption quantity of the packaging materials of each packaging material type of the preset institution within the target time period.

[0099] In this embodiment, for the aggregated recognition results corresponding to multiple waybill identifiers obtained within the target time period, different aggregated recognition results can first be classified according to the source of the packaging materials in step S501, and multiple target results with the source of the packaging materials being a preset institution can be selected therefrom to form a target result set. Then, in step S502, the types of packaging materials corresponding to each target result in the target result set can be counted to obtain the number of target results corresponding to each type of packaging material. Since the aggregated recognition result corresponds to the waybill identifier one by one, the number of express parcels using the packaging materials of this type can be determined according to the number of target results corresponding to each type of packaging material. Therefore, in step S503, the quantity of the packaging materials of each type consumed by the preset institution during the target time period can be determined according to the number of target results corresponding to each type of packaging material.

[0100] In this embodiment, for the aggregated recognition results obtained within the target time period, first, a target result set with the source of the packaging materials being a preset institution is screened and determined, and then the number of results corresponding to each type of packaging material is respectively counted. By utilizing the characteristic that the aggregated recognition result corresponds to the express parcel one by one, the quantity of various types of packaging materials actually used by the preset institution during the target time period can be quickly and accurately determined.

[0101] In one embodiment, as Figure 6 shown, a method for verifying and writing off packaging materials is provided, which can be executed in cooperation by the edge side and the cloud side.

[0102] Among them, at the edge side, image preprocessing can be performed first. For the pictures generated when the express items pass through the machine, the edge side (edge computing server) can adopt different processing strategies according to the picture sources (area array camera and line scan camera). Among them, when the express item passes through the automated sorting equipment, the fill light will turn on. During this process, the automated equipment can select a moment to trigger the area array camera to take pictures. When the triggering timing is incorrect, it may cause overexposure of the picture. For this, the first classification network (classification network 1) can be used to filter out overexposed pictures. When the category output by the first classification network is overexposed, the picture dimension recognition result of this picture can be recorded as "not detected". When the express item passes through the machine, the line scan camera can also perform imaging at the same time. The line scan camera can scan the object row by row, and then splice the images scanned in each row together to form the final image, and there is basically no overexposure situation, but there may be pictures with underexposure and abnormal aspect ratio. For this, the image quality determination module can be used to determine the image quality. Among them, the image quality determination module can be implemented by an image processing algorithm, and the image processing algorithm performs the following steps: 1. Calculate the aspect ratio of the image a = W (width) / H (height). When the aspect ratio a is greater than the first value (for example, 10) or the aspect ratio a is less than the second value (for example, 0.1), the image processing algorithm can output information about abnormal aspect ratio; 2. Convert the image into a grayscale image, and by calculating the histogram, count the proportion of underexposed pixels. When this proportion is greater than the threshold, information about underexposure abnormality can be output. Among them, when the image quality determination module outputs any abnormal information, the picture dimension recognition result of this picture can be recorded as "not detected".

[0103] At the edge side, express delivery item detection and processing can also be performed. This express delivery item detection and processing can correspond to the first detection network (detection network 1). The first detection network can use an object detection network (including but not limited to SSD, YOLO, RCNN, etc.), and the detection categories can include express delivery packages, stacked items, etc. Among them, when only the bounding box of one express delivery package is detected in the image that appears in the picture, the result can be recorded as "single item"; when there is no detection bounding box, the picture dimension recognition result of this picture can be recorded as "not detected"; when the number of detected stacked item bounding boxes is greater than or equal to the first preset quantity (for example, 1), or the number of detected express delivery package bounding boxes is greater than the second preset quantity (for example, 1), the picture dimension recognition result of this picture can be recorded as "multiple items". The edge side can also use the second classification network (classification network 2, which can be used for material classification). Among them, for the picture with the result of "single item" in the previous link, the image of the area of the express delivery package can be cropped. This new image can be recorded as Ia, and the new image Ia can be sent to the second classification network for material judgment. The second classification network can output multiple categories (for example, 6 categories: document envelope, cardboard box, waterproof bag, foam box, other materials, gunny bag / small package). For example, when the material does not belong to any of the document envelope, cardboard box, and waterproof bag categories, the picture dimension recognition result of this picture can be recorded as "other", otherwise it can enter the next link. The edge side can also use the second detection network (detection network 2). Among them, the new image Ia can be sent to the second detection network, and the second detection network can be used to detect whether there are visual recognition elements of this logistics agency (such as the LOGO and sign of the logistics agency) on the outer packaging of the express delivery item. If there are, the picture dimension recognition result of this picture can be obtained by combining the result of material classification. For example, if the material classification is recognized as a cardboard box and the visual recognition elements of this logistics agency are detected, then the final picture dimension recognition result can be recorded as "cardboard box of this logistics agency". For the express delivery items without detected visual recognition elements of the logistics agency, it is usually impossible to confirm that they are not materials of this logistics agency, and the judgment of the subsequent links can be carried out.

[0104] The edge side can also use a third classification network (Classification Network 3), which can be used to identify materials with visual recognition elements of non-this logistics organization. For the training of this third classification network, it can be defined that materials with visual recognition elements (obvious textures, colors, logos, etc.) of other logistics organizations can be regarded as materials of non-this logistics organization, while for cartons, waterproof bags, document envelopes, etc. that do not contain visual recognition elements (obvious textures, colors, logos, etc.) of other logistics organizations, they can be regarded as materials for which the logistics organization cannot be confirmed. Thus, the third classification network can classify the new image Ia into, for example, cartons of non-this logistics organization, waterproof bags of non-this logistics organization, document envelopes of non-this logistics organization, cartons for which the logistics organization cannot be confirmed, waterproof bags for which the logistics organization cannot be confirmed, document envelopes for which the logistics organization cannot be confirmed, etc. Among them, various categories (such as 3) for which the logistics organization cannot be confirmed can be mapped to the picture dimension recognition result "other".

[0105] The edge side can also integrate the above results to obtain the single-image algorithm result and push (report) it to the cloud. Among them, the possible picture dimension recognition results at the edge side include cartons of this logistics organization, waterproof bags of this logistics organization, document envelopes of this logistics organization, cartons of non-this logistics organization, waterproof bags of non-this logistics organization, document envelopes of non-this logistics organization, other, multiple items, not detected, etc. At the same time, it can also include the confidence level corresponding to each picture dimension recognition result.

[0106] For the cloud, since a single express consignment usually passes through multiple transfer stations and multiple automated sorting devices, multiple picture dimension recognition results will be generated. These results can be cross-checked and result-fused according to the waybill, so as to effectively improve the accuracy of material identification and verification for this waybill. Among them, after receiving the picture dimension recognition results from the edge side, the cloud can store them in the Hive (a data warehouse tool based on Hadoop) library of big data, and the big data engine can run the result fusion of the picture dimension regularly every day. For the result fusion, the picture dimension recognition results can be aggregated according to the waybill first. For all picture recognition results of the same waybill, the records with the picture recognition results of multiple items and not detected are excluded, and then based on the excluded results, the confidence levels are summed according to the picture dimension recognition results, and the category with the maximum confidence sum is used as the final classification result of this waybill. Then, the material consumption situation of the day can be obtained by verifying the materials with the final classification result.

[0107] This embodiment belongs to an edge-cloud integrated solution. Through edge-cloud collaboration, the acquisition of single-image recognition results can be achieved at the edge, and the aggregation of results can be achieved in the cloud. The image recognition results of each passing of the machine can be calculated at the edge and uploaded to the cloud big data Hive library. The Hive library can perform big data operations regularly every day, aggregate the multiple passing-of-the-machine recognition results of the waybill to obtain the fused recognition result at the waybill dimension, and finally calculate the consumption of various outer packaging materials. Thus, after the express delivery passes through the transfer station, the materials used for this ticket can be automatically recognized without manual intervention, saving labor costs, improving the efficiency and accuracy of material recognition / categorization, having good real-time / timeliness, and being able to fully consider various special situations actually encountered, with strong robustness. Through the cooperation of the edge and the cloud big data platform, a relatively high accuracy can be achieved for material verification, which is very convenient for logistics institutions to better master the material usage situation and achieve the optimal allocation of resources.

[0108] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the indication of the arrows, these steps do not necessarily need to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily need to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily need to be sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0109] Based on the same inventive concept, the embodiments of the present application also provide a packaging material verification device for implementing the above-mentioned packaging material verification method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the following packaging material verification device can refer to the limitations on the packaging material verification method in the above text, and will not be repeated here.

[0110] In one embodiment, as Figure 7 shown, a packaging material verification device 700 is provided, including:

[0111] An information acquisition module 701, configured to acquire the image information and waybill identifier of the express delivery at multiple sorting links;

[0112] A packaging recognition module 702, configured to perform packaging recognition processing on each of the image information to obtain a packaging recognition result;

[0113] A result aggregation module 703 is configured to aggregate the package recognition results of the image information according to the waybill identifiers associated with the image information, so as to obtain an aggregated recognition result corresponding to each waybill identifier; the aggregated recognition result includes the package material type and the package material source corresponding to the waybill identifier.

[0114] A consumption amount determination module 704 is configured to determine the consumption amount of the package materials of each package material type of a preset organization during the target time period according to the aggregated recognition results corresponding to multiple waybill identifiers obtained during the target time period.

[0115] In one embodiment, the package recognition module 702 is further configured to: perform anomaly detection on the image information to obtain an anomaly detection result; if the anomaly detection result indicates that the image information is non-anomalous image information, perform material texture classification processing on the image information to obtain a material classification result; if the material classification result indicates that the package material is a known type of package material, perform package material source recognition on the image information to obtain a package material source recognition result; and obtain the package recognition result of the image information according to the material classification result and the package material source recognition result.

[0116] In one embodiment, the package recognition module 702 is further configured to: determine whether the image information contains a visual recognition element of a preset organization based on organization element detection of the image information; if it contains, obtain that the package material source recognition result is that the package material comes from the preset organization; if it does not contain, determine whether the image information contains a visual recognition element of other known organizations based on organization element recognition of the image information; if so, obtain that the package material source recognition result is that the package material comes from the other known organization.

[0117] In one embodiment, the package recognition module 702 is further configured to: perform imaging anomaly detection on the image information according to the image acquisition method of the image information to obtain an imaging anomaly detection result; if the imaging anomaly detection result indicates that the imaging of the image information is normal, obtain a quantity detection result based on the express delivery quantity detection of the image information; if the quantity detection result indicates that the express delivery quantity corresponding to the image information meets a preset condition, obtain that the anomaly detection result is that the image information is non-anomalous image information; if the imaging anomaly detection result indicates that the imaging of the image information is anomalous, or the quantity detection result indicates that the express delivery quantity corresponding to the image information does not meet the preset condition, obtain that the anomaly detection result is that the image information is anomalous image information.

[0118] In one embodiment, the packaging identification module 702 is further configured to: if the abnormal detection result indicates that the image information belongs to abnormal image information, or the material classification result indicates that the packaging material belongs to an unknown type of packaging material, or the material source identification result is unknown, determine the packaging identification result of the image information as a preset result.

[0119] In one embodiment, the consumption amount determination module 704 is further configured to: obtain a target result set with the source of the packaging material being a preset institution according to the aggregated identification results corresponding to a plurality of waybill identifiers obtained within a target time period; determine the target result quantity corresponding to each packaging material type according to the target result set; and determine the consumption amount of the packaging materials of each packaging material type of the preset institution during the target time period according to the target result quantity corresponding to each packaging material type.

[0120] Each module in the above packaging material verification and cancellation device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the computer device in the form of hardware or be independent of the processor, or can be stored in the memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above respective modules.

[0121] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 8 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. 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 image information, waybill identifiers, aggregated identification results, and consumption amounts of packaging materials. The input / output interface of the computer device is used for the processor to exchange information with external devices. The communication 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, it implements a packaging material verification and cancellation method.

[0122] Those skilled in the art can understand that Figure 8The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0123] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0124] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0125] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0126] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. And the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0127] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include Read-Only Memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0128] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope recorded in this specification.

[0129] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for verifying and writing off packaging materials, characterized in that, The method includes: Obtaining the image information and waybill identification of express parcels in multiple sorting links; Performing packaging recognition processing on each piece of the image information to obtain a packaging recognition result; Aggregating the packaging recognition results of the image information according to the waybill identification associated with the image information to obtain an aggregated recognition result corresponding to each waybill identification; the aggregated recognition result includes the packaging material type and packaging material source corresponding to the waybill identification; Determining the consumption amount of packaging materials of each packaging material type of a preset institution during the target period according to the aggregated recognition results corresponding to multiple waybill identifications obtained during the target period.

2. The method according to claim 1, characterized in that, The performing packaging recognition processing on each piece of the image information to obtain a packaging recognition result includes: Performing anomaly detection on the image information to obtain an anomaly detection result; If the anomaly detection result indicates that the image information belongs to non-abnormal image information, then performing material texture classification processing on the image information to obtain a material classification result; If the material classification result indicates that the packaging material belongs to a known type of packaging material, then performing material source identification on the image information to obtain a material source identification result; Obtaining the packaging recognition result of the image information according to the material classification result and the material source identification result.

3. The method according to claim 2, characterized in that, The performing material source identification on the image information to obtain a material source identification result includes: Determining whether the image information contains a visual recognition element of a preset institution based on the detection of institution elements in the image information; If it contains, then obtaining the material source identification result that the packaging material comes from the preset institution; If it does not contain, then determining whether the image information contains a visual recognition element of other known institutions based on the recognition of institution elements in the image information; If so, then obtaining the material source identification result that the packaging material comes from the other known institution.

4. The method according to claim 2, characterized in that, The performing anomaly detection on the image information to obtain an anomaly detection result includes: Performing imaging anomaly detection on the image information according to the image acquisition method of the image information to obtain an imaging anomaly detection result; If the imaging anomaly detection result indicates that the imaging of the image information is normal, then obtaining a quantity detection result based on the detection of the number of express parcels in the image information; If the quantity detection result indicates that the number of express parcels corresponding to the image information meets the preset conditions, then obtaining the anomaly detection result that the image information belongs to non-abnormal image information; If the imaging anomaly detection result indicates that the imaging of the image information is abnormal, or the quantity detection result indicates that the number of express parcels corresponding to the image information does not meet the preset conditions, then obtaining the anomaly detection result that the image information belongs to abnormal image information.

5. The method according to claim 2, wherein The method further includes: If the anomaly detection result indicates that the image information belongs to abnormal image information, or the material classification result indicates that the packaging material belongs to an unknown type of packaging material, or the material source identification result is an unknown source, then determining the packaging recognition result of the image information as a preset result.

6. The method according to any one of claims 1 to 5, characterized in that, Determining the consumption amount of packaging materials of each packaging material type of a preset institution in the target time period according to the aggregated recognition results corresponding to a plurality of waybill identifiers obtained within the target time period includes: Obtaining a target result set with the packaging material source being the preset institution according to the aggregated recognition results corresponding to a plurality of waybill identifiers obtained within the target time period; Determining the target result quantity corresponding to each packaging material type according to the target result set; Determining the consumption amount of packaging materials of each packaging material type of the preset institution in the target time period according to the target result quantity corresponding to each packaging material type.

7. A packaging material verification and cancellation device, characterized in that, The device includes: An information acquisition module, configured to acquire image information and waybill identifiers of express items in a plurality of sorting links; A packaging recognition module, configured to perform packaging recognition processing on each piece of the image information to obtain a packaging recognition result; A result aggregation module, configured to aggregate the packaging recognition results of the image information according to the waybill identifiers associated with the image information to obtain an aggregated recognition result corresponding to each waybill identifier; the aggregated recognition result includes the packaging material type and the packaging material source corresponding to the waybill identifier; A consumption amount determination module, configured to determine the consumption amount of packaging materials of each packaging material type of a preset institution in the target time period according to the aggregated recognition results corresponding to a plurality of waybill identifiers obtained within the target time period.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images