A method, apparatus and device for determining a weighing state

Abstract

The application provides a weighing state determination method, device and equipment, which is used for judging whether the weighing state of a to-be-weighed logistics piece is normal from the image level more intuitively and accurately, and can accurately cope with the weighing state judgment result, thereby ensuring the stability and efficiency of automatic sorting operation. The weighing state determination method provided by the application comprises the following steps: obtaining a target image, wherein the target image is an image obtained by a shooting weighing device when weighing a to-be-weighed logistics piece; performing logistics piece identification on the target image to obtain a logistics piece identification result; and determining whether the weighing state of the to-be-weighed logistics piece is normal according to the logistics piece identification result and a preset logistics piece abnormal weighing state condition.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of logistics, in particular to a determination method, device and equipment of a weighing state. BACKGROUND

[0002] In the logistics transportation operation, under the background of optimizing transportation efficiency, the transportation link and the sorting link of the logistics piece are two operation links with great optimization space.

[0003] The newer sorting equipment has the ability of one-to-one code scanning and weighing, so as to check whether the logistics piece itself is consistent with the information of the logistics order attached to the logistics piece.

[0004] However, in the research process of the existing related technology, the inventor found that the existing sorting equipment often has abnormal weighing, which affects the automatic sorting efficiency of the sorting operation. SUMMARY

[0005] The present application provides a determination method, device and equipment of a weighing state, which can more intuitively and accurately judge whether the weighing state of a to-be-weighed logistics piece is normal from the image level, and can accurately handle according to the weighing state judgment result, thereby ensuring the stability and sorting efficiency of the automatic sorting operation.

[0006] In a first aspect, the present application provides a determination method of a weighing state, which comprises:

[0007] obtaining a target image, wherein the target image is an image obtained by photographing a weighing device for weighing a to-be-weighed logistics piece;

[0008] performing logistics piece identification in the target image to obtain a logistics piece identification result;

[0009] determining whether the weighing state of the to-be-weighed logistics piece is normal according to the logistics piece identification result and a preset logistics piece abnormal weighing state condition.

[0010] In combination with the first aspect of the present application, in a first possible implementation manner of the first aspect of the present application, the logistics piece identification in the target image comprises:

[0011] performing logistics piece identification in the target image according to a preset logistics piece image feature to obtain a first identified logistics piece;

[0012] selecting a second logistics piece in the first logistics piece according to the boundary of the weighing area of the weighing device;

[0013] confirming the number of the second logistics piece as the number of the logistics pieces in the logistics piece identification result.

[0014] In a second possible implementation manner of the first aspect of the present application, according to the boundary of the weighing area of the weighing device, the second logistics piece is filtered out from the first logistics piece, comprising:

[0015] extracting the detection frame boundary corresponding to each logistics piece in the first logistics piece;

[0016] extracting the first boundary line and the second boundary line of the boundary of the weighing area, wherein the weighing device is a dynamic weighing device, the weighing area includes a region on the conveying belt, and the first boundary line and the second boundary line are boundary lines arranged at two positions in front of and behind the conveying belt in the conveying direction, and the first boundary line and the second boundary line correspond to the region boundary of the weighing area respectively;

[0017] from the first logistics piece, the logistics piece whose detection frame boundary is within the range between the first boundary line and the second boundary line is determined as the second logistics piece.

[0018] In a third possible implementation manner of the first aspect of the present application, the logistics piece abnormal weighing state condition is specifically:

[0019] if the number of logistics pieces in the logistics piece recognition result is greater than 1, it is determined that the weighing state is an abnormal weighing state;

[0020] if the number of logistics pieces in the logistics piece recognition result is equal to 1, it is determined that the weighing state is a normal weighing state.

[0021] In a fourth possible implementation manner of the first aspect of the present application, in combination with the third possible implementation manner of the first aspect of the present application, the logistics piece abnormal weighing state condition is specifically:

[0022] if the number of logistics pieces in the logistics piece recognition result is greater than 1, and the confidence in the logistics piece recognition result is greater than the confidence threshold, it is determined that the weighing state is an abnormal weighing state.

[0023] In a fifth possible implementation manner of the first aspect of the present application, in combination with the first aspect of the present application, if the weighing state is determined to be an abnormal weighing state, the method further comprises:

[0024] outputting prompt information, wherein the prompt information is used to prompt the user that there is an abnormal weighing state, or the prompt information is used to trigger the sorting device to re-perform the sorting processing on the logistics piece on the weighing device.

[0025] In a second aspect, the present application provides a weighing state determination device, comprising:

[0026] an acquisition unit configured to acquire a target image, wherein the target image is an image obtained by photographing a weighing device weighing a logistics piece to be weighed;

[0027] An identifying unit is configured to perform logistics piece identification on the target image to obtain a logistics piece identification result.

[0028] A determining unit is configured to determine whether the weighing state of the logistics piece to be weighed is normal according to the logistics piece identification result and a preset logistics piece abnormal weighing state condition.

[0029] In a first possible implementation manner of the second aspect of the present application, the identifying unit is specifically configured to:

[0030] perform logistics piece identification on the target image according to a preset logistics piece image feature to obtain a first identified logistics piece;

[0031] filter a second logistics piece in the first logistics piece according to a boundary of a weighing area of the weighing device;

[0032] confirm the number of the second logistics piece as the number of logistics pieces in the logistics piece identification result.

[0033] In a second possible implementation manner of the second aspect of the present application, the identifying unit is specifically configured to:

[0034] extract a detection frame boundary corresponding to each of the logistics pieces in the first logistics piece;

[0035] extract a first boundary line and a second boundary line of the boundary of the weighing area, wherein the weighing device is a dynamic weighing device, the weighing area includes an area located on a conveying belt, and the first boundary line and the second boundary line are boundary lines located at two positions in front of and behind the conveying belt in a conveying direction, and the first boundary line and the second boundary line correspond to area boundaries of the weighing area, respectively;

[0036] determine, from the first logistics piece, a logistics piece whose detection frame boundary is located in a range between the first boundary line and the second boundary line as the second logistics piece.

[0037] In a third possible implementation manner of the second aspect of the present application, the logistics piece abnormal weighing state condition is specifically:

[0038] if the number of logistics pieces in the logistics piece identification result is greater than 1, it is determined that the weighing state is an abnormal weighing state;

[0039] if the number of logistics pieces in the logistics piece identification result is equal to 1, it is determined that the weighing state is a normal weighing state.

[0040] In a fourth possible implementation manner of the second aspect of the present application, the logistics piece abnormal weighing state condition is specifically:

[0041] If the quantity of the logistics pieces in the logistics piece identification result is greater than 1 and the confidence in the logistics piece identification result is greater than the confidence threshold, it is determined that the weighing state is an abnormal weighing state.

[0042] In a fifth possible implementation manner of the second aspect of the application, the apparatus further includes an output unit configured to:

[0043] If the weighing state is determined to be an abnormal weighing state, the output unit is configured to output prompt information, where the prompt information is configured to prompt the user that there is an abnormal weighing state, or the prompt information is configured to trigger the sorting device to re-perform sorting processing on the logistics piece on the weighing device.

[0044] In a third aspect, the application provides a weighing state determination device, including a processor and a memory, the memory storing a computer program, and the processor calling the computer program in the memory to execute the steps in the method provided in the first aspect of the application.

[0045] In a fourth aspect, the application provides a weighing system, including a sorting device and the weighing state determination device provided in the third aspect of the application.

[0046] In a fifth aspect, the application further provides a computer readable storage medium, which stores a plurality of instructions, and the instructions are adapted to be loaded by a processor to execute the steps in the method provided in the first aspect of the application.

[0047] From the above, the application has the following beneficial effects:

[0048] In the logistics operation process, the application introduces an image recognition scheme. When the weighing device weighs the logistics piece to be weighed, the target image is obtained by photographing the weighing device, the logistics piece identification is performed on the target image to obtain a logistics piece identification result, and then the weighing state of the logistics piece to be weighed is determined to be normal or abnormal in combination with the logistics piece identification result and the preset logistics piece abnormal weighing state condition. Compared with the prior art which determines whether the weighing state is normal by comparing whether the weight data scanned by the bar code and the weight data obtained by weighing are consistent, the application can more intuitively and accurately determine whether the weighing state of the logistics piece to be weighed is normal from the image level due to the combination of image recognition. Especially when the upstream link of the weighing device has sorting abnormalities, two or more logistics pieces are transported to the weighing device, the abnormal situation can be detected at the first time, thereby further ensuring the stability and efficiency of the automatic sorting operation. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0050] Figure 1 A flowchart of a method for determining the weighing state according to the present application;

[0051] Figure 2 A flowchart of a method for identifying the logistics piece according to the present application;

[0052] Figure 3 A flowchart of a method for screening the second logistics piece according to the present application;

[0053] Figure 4 Another flowchart of a method for screening the second logistics piece according to the present application;

[0054] Figure 5 A scenario diagram of the present application;

[0055] Figure 6 A network structure diagram of the YOLOv3 model according to the present application;

[0056] Figure 7 An algorithm diagram of the bounding box screening algorithm according to the present application;

[0057] Figure 8 A structural diagram of the weighing state determination device according to the present application;

[0058] Figure 9 A structural diagram of the weighing state determination device according to the present application. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0060] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application can be practiced without these specific details. In other instances, well-known methods, structures and techniques have not been described in detail in order to avoid obscuring the application. In the following description, specific embodiments of the application will be described reference being made to steps and symbolic representations of operations being performed by one or more computers. Although in the interest of clarity, efficient computation, and reduced risks of error and ambiguity, some of the computer operations will be described in a particular, algorithmic order, it is understood that the computer operations can be performed in other orders that are somewhat different depending upon the decision taken in other functions. Moreover, it is recognized that the skilled artisan will be able to conceive of variations to the computer operations described herein, which would be within the scope of the present application. For example, the skilled artisan will recognize that the computer operations described herein can be implemented in hardware, software, firmware, or any combination thereof. Accordingly, the computer operations described herein are intended to include any such variations as would be understood by one of ordinary skill in the art.

[0061] The principles of the application are operable with numerous other general purpose or special purpose computing, communications environments, or configurations. Examples of well-known computing systems, environments, and configurations that can be suitable for use with the application include, but are not limited to, handheld or laptop devices, personal computers, servers, multiprocessor systems, microcomputer-based systems, networked personal computers, mainframe computers, and distributed computing environments that include any of the above systems or devices.

[0062] The terms "first", "second", and "third" and the like, are used to distinguish one element from another, and are not intended to denote a particular order or sequence. Also, the terms "comprises", "comprising", "includes", "including" and the like, are intended to be open-ended and to mean that the listed elements are not the only elements that can be included in the methods and compositions described herein.

[0063] Before introducing the present application, the related content about the application background is introduced first.

[0064] The determination method and device of the weighing state and the computer readable storage medium provided by the present application can be applied to the weighing state determination device, which is used to more intuitively and accurately judge whether the weighing state of the to-be-weighed logistics piece is normal from the image level, so that accurate response processing can be performed according to the weighing state judgment result, and the stability and sorting efficiency of the automatic sorting operation are ensured.

[0065] The determination method of the weighing state mentioned in the present application can be performed by a weighing state determination device, or a server device, a physical host, a user equipment (UE) or other types of weighing state determination devices integrated with the device. The weighing state determination device can be implemented in hardware or software. The UE can be a terminal device such as a smartphone, a tablet computer, a notebook computer, a palm computer, a desktop computer or a personal digital assistant (PDA). The weighing state determination device can also be divided into multiple devices and collectively perform the method provided in the present application.

[0066] In the existing related technology, when the weighing link in the automatic sorting operation detects that a logistics piece passes through the sorting assembly line through an infrared sensing device or other sensing device, the weighing process is triggered, and the logistics single on the logistics piece is scanned by scanning, and the logistics single identifies the weight of the logistics piece. At this time, the weight identified by the scanned logistics single is compared with the weight measured by the weighing device. If they are consistent, it can be determined that the weight identified by the logistics single is normal and effective. If they are inconsistent, it can be determined that the weight identified by the logistics single is abnormal and invalid, and needs to be checked manually or returned to the sorting again.

[0067] However, in the actual automatic sorting operation, other work links are also configured upstream of the weighing link, such as an initial sorting link and a transportation link. If abnormal conditions such as logistics piece accumulation, sorting abnormality and transportation abnormality occur in the upstream link, it is possible that two or more logistics pieces appear in the weighing link at the same detection time. In this case, the weight on the scanned logistics single does not match the weight of two or more logistics pieces.

[0068] Taking the case that A and B logistics pieces appear in the weighing device at the same detection time as an example, the logistics single on the A logistics piece identifies a weight of 5 kg, and the actual weight of the A logistics piece is also 5 kg. The actual weight of the B logistics piece is 3 kg. It can be easily seen that although the 5 kg weight identified by the logistics single on the A logistics piece matches the actual weight (the weight identified by the logistics single on the A logistics piece is normal and effective), the weight of the A and B logistics pieces (8 kg in total) measured by the weighing device does not match. At this time, if an error is reported, manual inspection or re-sorting is performed, which obviously affects the sorting efficiency of the automatic sorting operation.

[0069] Based on the above-mentioned defects of the existing related technology, the present application provides a determination method of a weighing state, which at least partially overcomes the defects of the existing related technology.

[0070] Wherein, in the present application, the logistics piece can be specifically express piece, and the automatic sorting operation is naturally the automatic sorting of the express piece.

[0071] Next, the determination method of the weighing state provided in the present application will be introduced.

[0072] Firstly, referring to Figure 1 , Figure 1 A flowchart of the determination method of the weighing state in the present application is shown, as Figure 1 shown, the determination method of the weighing state provided in the present application can specifically include the following steps:

[0073] Step S101, obtaining a target image, wherein the target image is an image obtained by shooting a weighing device for weighing a to-be-weighed logistics piece;

[0074] Step S102, performing logistics piece recognition in the target image to obtain a logistics piece recognition result;

[0075] Step S103, determining whether the weighing state of the to-be-weighed logistics piece is normal according to the logistics piece recognition result and a preset logistics piece abnormal weighing state condition.

[0076] From the above scheme, it can be concluded that in the logistics operation process, the present application introduces an image recognition scheme, when the weighing device weighs the to-be-weighed logistics piece, after obtaining the target image by shooting the weighing device, the target image is subjected to logistics piece recognition to obtain a logistics piece recognition result, and then the logistics piece recognition result is combined with the preset logistics piece abnormal weighing state condition to determine whether the weighing state of the to-be-weighed logistics piece is normal. Compared with the prior art which determines whether the weighing state is normal by comparing whether the weight data scanned by the bar code and the weight data obtained by weighing are consistent, the present application can more intuitively and accurately judge whether the weighing state of the to-be-weighed logistics piece is normal from the image level due to the combination of image recognition. Especially when the upstream link of the weighing device has sorting abnormalities, two or more logistics pieces are transported to the weighing device, the abnormal situation can be detected at the first time for accurate response and processing, further ensuring the stability and sorting efficiency of the automatic sorting operation.

[0077] Next, the steps of the determination method of the weighing state shown in the above Figure 1 will be specifically introduced.

[0078] In the present application, the weighing device is a device configured by a logistics company in an automatic sorting operation, which is used to weigh the logistics piece on the automatic sorting assembly line to check whether the identification weight and the actual weight of the logistics piece are consistent.

[0079] For example, the weighing device can be a dynamic weighing device, which specifically includes a conveyor belt for transporting the logistics piece, so that the weighing area of the device is located in the area of the conveyor belt, and the logistics piece can be weighed while being transported, that is, the dynamic weighing function can be realized for the logistics piece in the transportation state. For example, the weighing device can be a dynamic weighing system (DWS), which is commonly known as DWS dynamic.

[0080] The weighing device can be configured in an automated sorting pipeline to weigh the logistics piece passing through or placed. During weighing, the logistics piece is placed on the weighing table, weighing surface or weighing area of the weighing device, and the weighing device senses the weight of the logistics piece through the sensor and converts it into data form weight data.

[0081] In this application, the weighing device itself can include a camera, so that the current weighing scene can be photographed while the logistics piece is being weighed; or the weighing device can be configured with a camera, which monitors whether the weighing device is weighing under the trigger of the camera, the weighing device or other devices, and photographs the current weighing scene when the logistics piece is being weighed; or the camera can also monitor the weighing scene of the weighing device in real time through video monitoring under the trigger of the camera, the weighing device or other devices.

[0082] The image obtained by photographing the weighing device for weighing the logistics piece to be weighed can be used as a target image for determining whether the weighing state is normal.

[0083] The images can be sent to the weighing state determination device provided by the application in real time, and the weighing state determination device can trigger the judgment process in real time after receiving the images, or trigger the judgment process according to the trigger of the artificial trigger, the timing trigger and other trigger mechanisms; or the images can be retrieved from the device storing the images and the corresponding judgment process can be performed after the weighing state determination method provided by the application is triggered by the weighing state determination device provided by the application; or the weighing state determination device can also include a camera, such as the above-mentioned weighing device configured with a camera, the processing device configured with a camera, etc. When the images are photographed, the judgment process can be triggered in real time, or the judgment process can be triggered according to the trigger of the artificial trigger, the timing trigger and other trigger mechanisms, which are not limited here.

[0084] It can be understood that after obtaining the target image, the logistics piece can be identified in the target image through image recognition technology.

[0085] The automatic identification of the logistics piece can be performed by artificial intelligence (AI), i.e., by a neural network model. The neural network model can be trained by a large number of images containing logistics pieces. Specifically, a large number of images containing logistics pieces can be collected, such as a large number of images of weighing equipment carrying logistics pieces, and the logistics pieces contained in these images or even the number of logistics pieces are labeled, such as configuring semantic information of "logistics piece 1, and the total number of logistics pieces is 1" for each pixel point of a logistics piece 1 in a certain image.

[0086] The images configured with the labels can be used as a training set, and the images are sequentially input into an initialized neural network model for forward propagation. Then, a loss function is calculated according to the logistics piece recognition result output by the model, and the loss function is used for backward propagation to optimize the parameters of the model. When the training number, training time, recognition accuracy, and other preset training requirements are met, the training of the model is completed. At this time, the model can be used as a logistics piece recognition model to recognize the input target image in the present application.

[0087] After obtaining the logistics piece recognition result recognized in the target image, for example, obtaining the logistics piece recognition result output by the model, the result can be used to determine whether the weighing state of the logistics piece to be weighed in the logistics piece weighing scene corresponding to the target image is normal or not, in combination with the preset logistics piece abnormal weighing state condition.

[0088] For example, the logistics piece abnormal weighing state condition can be set for the logistics piece, the logistics single, or the location of the logistics piece on the weighing equipment, and if the attributes of these logistics pieces are abnormal, it can be determined that the weighing state is abnormal. Specifically, the logistics piece recognition result recognized in the target image and the logistics piece abnormal weighing state condition can be compared to achieve this.

[0089] For example, if the logistics piece recognition result indicates that the logistics piece is damaged, it is more likely that the real quality of the logistics piece currently has a quality drop compared to the real quality before the damage. Although the indicated weight on the logistics single is consistent with the real quality before the damage, the weight obtained at this time will not be consistent with the indicated weight on the logistics single. Therefore, an error can be reported to prompt that the logistics piece is damaged, and the staff can perform operations such as logistics piece recovery and logistics piece compensation.

[0090] For example, if the logistics piece identification result indicates that the logistics order on the logistics piece is damaged, the test is more likely to fail to scan the logistics order and the identification weight on the logistics order from the target image, although the identification weight on the original logistics order is consistent with the mass of the logistics piece. At this time, the damaged logistics piece is also unable to scan the identification weight, and therefore, an error can be reported to prompt that the logistics order on the logistics piece is damaged, so that the staff can perform logistics piece checking, re-pasting, and other operation processing.

[0091] For example, if the logistics piece identification result indicates that the location of the logistics piece on the weighing device is at the boundary of the weighing sensing area, and part of the logistics piece body is outside the weighing sensing area, the weight measured by the weighing device may not be the real weight of the current logistics piece. In other words, whether the identification weight of the logistics order on the logistics piece is consistent with the real weight of the current logistics piece, the weight measured by the weighing device is difficult to meet the identification weight, and therefore, an error can be reported to prompt that the placement position of the logistics piece is abnormal, so that the staff can correct the position of the logistics piece, or check whether the upstream equipment of the weighing device is abnormal, and further cause the abnormal placement position of the current logistics piece reaching the weighing device.

[0092] It should be understood that the above three cases are only examples, and in actual application, corresponding logistics piece abnormal weighing state conditions can be configured as needed, which are not limited herein.

[0093] Further, in actual application, in order to reduce the data processing workload of image recognition and improve the recognition efficiency, the application further provides a judgment mechanism suitable for the logistics piece abnormal weighing state.

[0094] In an exemplary implementation, only the number of logistics pieces in the target image can be determined, and whether the weighing state of the logistics piece in the weighing scene corresponding to the target image is normal can be judged through screening of the number of logistics pieces.

[0095] It can be understood that compared with identifying whether the logistics piece is damaged, whether the logistics order on the logistics piece is damaged, or whether the logistics piece is partially outside the weighing sensing area of the weighing device, and other logistics piece attributes, the data processing amount required for identifying the number of logistics pieces in the target image can be significantly reduced, and the algorithm implementation difficulty is low, and therefore, it is more suitable for the application of the automatic sorting assembly line of the logistics company.

[0096] Correspondingly, in the application, the logistics piece identification result can specifically include the number of logistics pieces, and the judgment rule for whether the weighing state is abnormal in the above-mentioned preset logistics piece abnormal weighing state condition can include:

[0097] If the number of logistics pieces in the logistics piece identification result is greater than 1, it is determined that the weighing state is an abnormal weighing state.

[0098] If the number of logistics pieces in the logistics piece identification result is equal to 1, it is determined that the weighing state is a normal weighing state.

[0099] It can be understood that in a normal weighing scenario, only one logistics piece arrives at the weighing device for weighing within a unit detection time, so if there is more than one logistics piece in the target image, it is obvious that there is an abnormal problem of the number of logistics pieces, which may be caused by abnormal situations such as logistics piece accumulation, sorting abnormality, transportation abnormality, etc. in the upstream link, resulting in the presence of more than two logistics pieces at the weighing device within the same detection time. Therefore, whether the number of identified logistics pieces is greater than 1 can directly filter the abnormal weighing state of more than two logistics pieces appearing at the weighing device.

[0100] It is easy to understand that for a neural network model, if it is only used to identify the number of logistics pieces in the target image, obviously, compared with focusing on the local image features of the logistics pieces, the required data processing amount can be greatly reduced. In the weighing scenario, there is a relatively obvious image feature difference between the logistics pieces and the weighing device and other background objects, and the model can vaguely identify the logistics pieces and their number, so the requirement for the identification accuracy of the model is relatively low. Therefore, it is more suitable for real-time application in the automatic sorting pipeline site, and the weighing state at the current weighing device can be directly determined in a very short time. If it is abnormal, an error prompt can be given, and the staff can check at the first time, or the automatic sorting pipeline can perform logistics piece backflow, re-sorting and other processing at the first time.

[0101] Further, in the process of identifying logistics pieces in the target image, including the process of identifying logistics pieces in the target image by the neural network model, considering that the logistics pieces may be in a motion state, or there may be logistics pieces waiting to be weighed in the target image, part of the logistics pieces may also be captured in the shooting field of view and appear in the target image with the current logistics piece being weighed. Filtering can be performed to exclude interference.

[0102] Specifically, referring to Figure 2 a flowchart of identifying logistics pieces according to the present application is shown, and the process of identifying the logistics pieces to be weighed in the target image can specifically include:

[0103] Step S201, according to the pre-set logistics piece image features, identifying logistics pieces in the target image to obtain the first identified logistics piece;

[0104] It can be understood that when identifying logistics pieces in the target image through image recognition, the logistics piece image features can be pre-configured. The presence of these logistics piece image features can confirm the presence of logistics pieces in the target image, and the number of logistics pieces in the target image can be confirmed according to the number of connected images where the logistics piece image features are located.

[0105] Taking the neural network model as an example, the training process of the model is the process of training the model to perceive the preset image features of the logistics piece.

[0106] At this time, the initial logistics piece identified is the first logistics piece, which not only includes the logistics piece currently weighed, but also may include a misidentified or misintroduced logistics piece. At this time, the filtration of the logistics piece can be performed through subsequent data processing.

[0107] In step S202, a second logistics piece within the boundary of the weighing area of the weighing device is screened from the first logistics piece according to the boundary of the weighing area of the weighing device.

[0108] In the present application, the boundary of the weighing area of the weighing device can be configured. The boundary is used to identify the weighing area of the weighing device in the image.

[0109] Specifically, the image features corresponding to the weighing area of the weighing device can be identified, for example, in actual application, the weighing area can be a smooth and silver table surface, and the image area with a similar silver color in the image can be identified as the weighing area. The boundary of the silver image area is the boundary of the weighing area of the weighing device.

[0110] Considering that in actual application, the camera device configured in the automated sorting assembly line is often fixed, therefore, a fixed boundary of the weighing area of the weighing device can be configured by the staff directly according to the shooting environmental conditions such as the deployment position and shooting angle of the camera device, which is convenient for practical use and avoids the data processing amount of real-time identification of the weighing area and its boundary of the weighing device in the target image through image recognition technology.

[0111] After obtaining the boundary of the weighing area of the weighing device, the logistics piece within the boundary can be screened from the initial logistics piece identified in front of the boundary. At this time, the logistics piece screened can be used as the effective logistics piece identified, that is, the second logistics piece.

[0112] In step S203, the number of the second logistics piece is confirmed as the logistics piece number of the logistics piece to be weighed.

[0113] Then, the number of the second logistics piece screened can be used as the number of the effective logistics piece identified for subsequent judgment processing of whether the weighing state is normal based on the logistics piece number.

[0114] Further, in actual application, the logistics piece identified from the target image through image recognition technology can be identified in the image through a detection frame. The detection frame can be understood as a rectangular contour selected by a plurality of coordinate points in the image. The picture information in the rectangular contour contains the image information of the identified logistics piece.

[0115] In this context, refer to Figure 3 A flowchart for screening the second logistics piece from the first logistics piece is shown, and the second logistics piece can be screened from the first logistics piece, which can specifically include:

[0116] Step S301, extracting the detection frame boundary of each logistics piece in the first logistics piece;

[0117] First, the detection frame boundary of each logistics piece in the initial logistics piece, i.e. the first logistics piece, can be extracted. For example, if two initial logistics pieces are identified in the current image, there are two detection frame boundaries.

[0118] Step S302, determining the logistics piece in the first logistics piece whose detection frame boundary is within the boundary of the weighing area as the second logistics piece.

[0119] After obtaining the detection frame boundary of each identified logistics piece, it can be compared with the boundary of the weighing area of the weighing device in turn. If the detection frame boundary is within the boundary of the weighing area of the weighing device, it can be determined as a recognized valid logistics piece, and these recognized valid logistics pieces can be used as the second logistics piece.

[0120] On the other hand, in the present application, considering that the transportation direction of the logistics piece on the automated sorting assembly line is generally fixed or within a certain range, for example, if the weighing device is a dynamic weighing device, obviously, the weighing device configures the transportation direction and the corresponding transportation channel for the logistics piece.

[0121] Therefore, in this case, the boundary of the weighing area of the weighing device can also be simplified, for example, refer to Figure 4 Another flowchart for screening the second logistics piece from the first logistics piece is shown, and the second logistics piece can also be screened from the first logistics piece, which can include:

[0122] Step S401, extracting the first boundary line and the second boundary line, wherein the weighing device is a dynamic weighing device, the weighing area includes the area on the conveying belt, the first boundary line and the second boundary line are boundary lines arranged at the front and back positions of the conveying belt in the conveying direction, and the first boundary line and the second boundary line correspond to the area boundary of the weighing area;

[0123] It can be understood that whether it is a pipeline link other than the weighing device in the automated sorting assembly line or the weighing device, a conveying belt can be configured to transport the logistics piece. When the logistics piece is transported by the conveying belt to the weighing area of the logistics piece, the weighing can be performed. For example, the dynamic weighing device itself can be configured with a conveying belt, and the weighing of the logistics piece can be performed while the logistics piece is transported by the conveying belt.

[0124] In the present application, the weighing area of the dynamic weighing device can be specifically arranged at the conveying belt, so that when the second logistics piece within the boundary of the weighing area of the weighing device is screened out from the first logistics piece according to image recognition, the area range of the weighing area of the device can be identified on the conveying belt.

[0125] Specifically, two boundary lines can be extracted based on the area boundary of the weighing area, the first boundary line and the second boundary line being arranged perpendicular to the conveying direction of the conveying belt. When the logistics piece is conveyed by the conveying belt to pass through the dynamic weighing device for weighing, it will inevitably pass through the first boundary line and the second boundary line in turn, so that the area range of the weighing area can be confirmed in combination with the first boundary line and the second boundary line.

[0126] In step S402, the logistics piece within the range between the first boundary line and the second boundary line in the first logistics piece is determined as the second logistics piece.

[0127] After the two boundary lines configured for the conveying belt are extracted, it can be judged whether the image of the logistics piece is in the image range within the two boundary lines. If so, it can be determined as a valid logistics piece, i.e., a second logistics piece.

[0128] In addition, it should be noted that from the above two implementation manners of screening the second logistics piece, it can also be seen that the two screening manners can also be applied together, for example, the two boundary lines corresponding to the boundary of the weighing area of the weighing device and the detection frame boundary of the logistics piece in the target image are extracted respectively. If the detection frame boundary is within the two boundary lines, it is obvious that the current logistics piece is a valid recognized second logistics piece.

[0129] Specifically, in the case shown in the scenario diagram of the present application, Figure 5 For example, the scenario diagram of the present application shown in the scenario diagram of the present application, Figure 5 The target image itself can be in the Figure 5 In the present application, the real weighing area of the weighing device is a quadrilateral area surrounded by A-B-C-D, A-B is the first boundary line of the boundary configured for the weighing area of the weighing device, C-D is the second boundary line of the boundary configured for the weighing area of the weighing device, and a-b-c-d is a quadrilateral detection frame of the recognized logistics piece. It can be seen that the quadrilateral a-b-c-d is within the range between the two boundary lines A-B and C-D, so it can be determined that the logistics piece is a valid recognized second logistics piece.

[0130] It should be understood that the boundary configured for the weighing area of the weighing device in the present application is not necessarily the boundary of the real weighing area of the weighing device, but can be a boundary adjusted in combination with actual application for the convenience of image processing, for example, Figure 5The two boundary lines A-B and C-D overlap the real weighing area of the weighing device, and in actual application, the two boundary lines A-B and C-D can be located within the range of the real weighing area of the weighing device or outside the range of the real weighing area of the weighing device.

[0131] Further, in actual application, for the convenience of judgment, the judgment can also be performed only on one side of the detection frame boundary of the logistics piece along the conveying direction, so that Figure 5 Taking the side c-d of the detection frame boundary a-b-c-d of the logistics piece as an example, the rules for judging that the quadrangle surrounded by a-b-c-d is within the range between the two boundary lines A-B and C-D include two conditions.

[0132] 1. The judgment standard for the logistics piece entering the weighing area is that the side c-d of the detection frame boundary of the logistics piece crosses into the side C-D along the conveying direction of the conveying belt (corresponding to the logistics piece entering the weighing area of the weighing device).

[0133] 2. The judgment standard for the logistics piece not leaving the weighing area is that the side c-d of the detection frame boundary of the logistics piece does not cross the side A`-B` along the conveying direction of the conveying belt (corresponding to the logistics piece not leaving the weighing area of the weighing device).

[0134] The side A`-B` is parallel to the two boundary lines A-B and C-D and is located in the real weighing area of the weighing device.

[0135] In this way, in the specific judgment process, it is only necessary to judge whether the side c-d of the detection frame boundary of the logistics piece is within the range between the side C-D and the side A`-B`, so as to determine whether the logistics piece is within the boundary of the weighing area of the weighing device, thereby avoiding the situation that the logistics piece is actually within the boundary of the weighing area of the weighing device in the shooting angle, the image of the logistics piece exceeds the boundary of the weighing area of the weighing device, and the logistics piece is mistakenly judged as not being within the boundary of the weighing area of the weighing device, and further improving the accuracy of identification.

[0136] Further, in another exemplary implementation, when the logistics piece is identified from the target image by the image recognition technology, the identification result of the logistics piece obtained further includes the confidence of the number of the logistics piece. It can be understood that the confidence is used to indicate the credibility of the identification result, or in other words, to indicate the probability that the identification result of the logistics piece is consistent with the true result in this identification process. If the confidence is high, it means that the credibility of the identification result is high, and if the confidence is low, it means that the credibility of the identification result is low. In this way, in the process of judging whether the weighing state is normal in combination with the number of the logistics piece, the following can be included:

[0137] If the number of logistics pieces is greater than 1 and the confidence is greater than the confidence threshold, it is determined that the weighing state is an abnormal weighing state.

[0138] Through further screening of the confidence, the judgment of whether the weighing state is normal has higher accuracy.

[0139] The above-mentioned content will be introduced in the following model involved in actual application.

[0140] In the present application, the neural network model can specifically adopt different types of models such as YOLOv3 model, ResNet model, R-CNN model, Fast R-CNN model, Faster R-CNN model, Mask R-CNN model, SSD model, etc. Taking the YOLOv3 model as an example, reference can be made to Figure 6 A network structure diagram of the YOLOv3 model of the present application is shown, the YOLOv3 model scales the input target picture to 416*416*3 size, and after feature extraction by the Darknet53 network, P3, P4 and P5 are taken as feature layer outputs. Among them, P3, P4 and P5 are 1 / 8, 1 / 16 and 1 / 32 of the size of the input image respectively.

[0141] P4 and P5 are upsampled respectively using bilinear interpolation, and then the original feature outputs P3, P4 are fused (concatenation), that is, the output graph after feature fusion is:

[0142] O1=P3+upsampled P4,

[0143] O2=P4+upsampled P5,

[0144] O3=P5.

[0145] The output graphs O1, O2 and O3 after feature fusion are respectively subjected to convolution operation to generate output results Y1, Y2 and Y3, and the sizes thereof are 13*13, 26*26 and 52*52 respectively, which are consistent with the sizes of P5, P4 and P3. The channel number of the output result is A*5, wherein A represents the number of prediction boxes responsible for each point in the graph, and A=3 is adopted in practice; each prediction box is described by (x, y, w, h, c), i.e. the center point position (x, y), width and height (w, h) and confidence, which are five values. Among them, the target detection object can only contain logistics pieces on the conveying belt, or only the confidence can represent the probability that the logistics pieces are contained in the prediction box without class prediction.

[0146] After the model output, firstly, all the output prediction boxes are arranged in descending order according to the confidence, and then the prediction boxes with the confidence greater than T are taken as candidate boxes, and T = 0.05 is adopted in actual application. The output candidate boxes are screened by Non-Maximum Suppression (NMS) or its variants (such as Soft-NMS, Adaptive-NMS, etc.), and the candidate boxes with larger overlapping regions are removed, and the screened boxes are taken as the final detection result output. In actual application, NMS is used as the prediction box screening algorithm, and for details, refer to Figure 7 An algorithm schematic diagram of the prediction box screening algorithm of the present application is shown.

[0147] After determining whether the weighing state of the weighing device is normal, corresponding processing can be performed according to the determination result of the weighing state.

[0148] In actual application, it can be understood that if the weighing state is normal, i.e., the determination result is a normal weighing state, the determination device of the weighing state generally does not need to be processed, and the sorting device of the sorting line can continue to perform the remaining normal sorting processing on the logistics piece, such as transporting to the corresponding sorting port, facilitating the distribution to the corresponding logistics vehicle; or the determination device of the weighing state can also actively trigger the sorting device of the sorting line to perform the remaining normal sorting processing on the logistics piece, such as transporting to the corresponding sorting port, facilitating the distribution to the corresponding logistics vehicle.

[0149] If the weighing state is abnormal, i.e., the determination result is an abnormal weighing state, the determination device of the weighing state can output a prompt information, and the prompt information is used to prompt the existence of the abnormal weighing state.

[0150] On the one hand, the determination device of the weighing state can output the prompt information to the user through the output device such as a loudspeaker, a warning light, a display screen, and a vibration motor, for example, a window can be popped up on the display screen, and the window displays the text "there is an abnormal weighing state, which needs to be checked / returned / sorted again", and for another example, the corresponding abnormal weighing state can be prompted by the preset red warning light, and the user can manually check the logistics piece on the weighing device according to the prompt information output by the determination device of the weighing state, or arrange the logistics piece on the weighing device to return and sort again.

[0151] On the other hand, the return and sorting processing of the logistics piece can also be automatically performed, for example, the determination device of the weighing state can trigger the sorting device on the sorting line to re-perform the sorting processing on the logistics piece on the weighing device through the output prompt information.

[0152] Specifically, for example, the logistics piece can be grabbed by a mechanical arm to a return flow channel, which can transport the logistics piece back to the upstream of the sorting assembly line through its conveying belt, and after the logistics piece is sorted again, it can be determined again when it reaches the weighing device. The weighing state determination process; for another example, the logistics piece can also be directly grabbed by a mechanical arm to the upstream of the sorting assembly line; for another example, the logistics piece can also be made to slide or fall to the return flow channel through the movable baffle to be sorted again.

[0153] It can be understood that the triggering mode of the weighing state determination device to trigger the sorting device and the return flow mode of the sorting device can be adjusted according to the actual situation of the sorting device, which is not limited here.

[0154] In order to better implement the weighing state determination method provided in the present application, the present application also provides a weighing state determination device.

[0155] Referring to Figure 8 , Figure 8 A structural schematic diagram of the weighing state determination device of the present application, in the present application, the weighing state determination device 800 can specifically include the following structure:

[0156] The acquisition unit 801 is configured to acquire a target image, wherein the target image is an image obtained by photographing a weighing device that weighs a logistics piece to be weighed;

[0157] The identification unit 802 is configured to identify the logistics piece in the target image to obtain a logistics piece identification result;

[0158] The determination unit 803 is configured to determine whether the weighing state of the logistics piece to be weighed is normal according to the logistics piece identification result and a preset logistics piece abnormal weighing state condition.

[0159] In an exemplary implementation, the identification unit 802 is specifically configured to:

[0160] Identify the logistics piece in the target image according to a preset logistics piece image feature to obtain a first identified logistics piece;

[0161] According to the boundary of the weighing area of the weighing device, the second logistics piece in the first logistics piece is screened out;

[0162] The number of the second logistics piece is confirmed as the number of the logistics piece in the logistics piece identification result.

[0163] In another exemplary implementation, the identification unit 802 is specifically configured to:

[0164] Extract the detection frame boundary corresponding to each of the logistics pieces in the first logistics piece;

[0165] Extract the first boundary line and the second boundary line of the weighing area. The weighing device is a dynamic weighing device. The weighing area includes the area located on the conveyor belt. The first boundary line and the second boundary line are boundary lines set at two positions before and after the conveyor belt in the conveying direction. The first boundary line and the second boundary line correspond to the area boundary of the weighing area, respectively.

[0166] From the first logistics component, the logistics component whose detection frame boundary is located within the range between the first boundary line and the second boundary line is identified as the second logistics component.

[0167] In yet another exemplary implementation, the abnormal weighing condition for a logistics shipment is specifically as follows:

[0168] If the number of logistics items in the logistics item identification result is greater than 1, the weighing status is determined to be an abnormal weighing status.

[0169] If the number of logistics items in the logistics item identification result is equal to 1, then the weighing status is determined to be normal weighing status.

[0170] In yet another exemplary implementation, the abnormal weighing condition for a logistics shipment is specifically as follows:

[0171] If the number of logistics items in the logistics item identification result is greater than 1, and the confidence level in the logistics item identification result is greater than the confidence level threshold, then the weighing status is determined to be an abnormal weighing status.

[0172] In yet another exemplary implementation, the apparatus further includes an output unit 804 for:

[0173] If the weighing status is determined to be abnormal, a prompt message will be output. The prompt message is used to inform the user that there is an abnormal weighing status, or it is used to trigger the sorting equipment to re-sort the logistics items on the weighing equipment.

[0174] This application also provides equipment for determining the weighing condition, see [link / reference]. Figure 9 , Figure 9 This diagram illustrates a structural schematic of a weighing state determination device according to this application. Specifically, the weighing state determination device includes a processor 901, a memory 902, and an input / output device 903. The processor 901 executes the computer program stored in the memory 902 to implement, for example... Figures 1 to 7 Corresponding to each step of the method for determining the weighing state in any embodiment, the memory 902 is used to store the steps executed by the processor 901. Figures 1 to 7 The computer program required for determining the weighing state in any embodiment.

[0175] For example, the computer program can be divided into one or more modules / units, one or more modules / units are stored in the memory 902 and executed by the processor 901 to complete the present application. One or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the computer device.

[0176] The determination device of the weighing state can include, but is not limited to, the processor 901, the memory 902, the input and output device 903. Those skilled in the art can understand that the schematic is only an example of the determination device of the weighing state, and does not constitute a limitation on the determination device of the weighing state, and can include more or less components than the schematic, or combine certain components, or different components, for example, the device can also include a network access device, a bus, etc. The processor 901, the memory 902, the input and output device 903 and the network access device are connected through the bus.

[0177] The processor 901 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The processor is the control center of the determination device of the weighing state, and connects various parts of the whole device through various interfaces and lines.

[0178] The memory 902 can be used to store computer programs and / or modules, and the processor 901 realizes various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 902, and calling data stored in the memory 902. The memory 902 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as an image playing function, etc.), etc.; and the data storage area can store data (such as image data, etc.) created according to the determination of the use of the weighing state, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0179] The processor 901 is used to execute the computer programs stored in the memory 902, and can specifically realize the following functions:

[0180] Obtaining a target image, wherein the target image is an image obtained by photographing a weighing device for weighing a to-be-weighed logistics piece;

[0181] Performing logistics piece identification in the target image to obtain a logistics piece identification result;

[0182] Determining whether the weighing state of the to-be-weighed logistics piece is normal according to the logistics piece identification result and a preset logistics piece abnormal weighing state condition.

[0183] The application also provides a sorting system, which includes a weighing device, a sorting device, and a weighing state determination device.

[0184] The descriptions of the weighing device, the sorting device, and the weighing state determination device can be referred to the foregoing content, and are not limited here.

[0185] In addition, the weighing state determination device in the application can also be integrated into the weighing device or the sorting device in actual application, so as to directly improve the functions of the weighing device or the sorting device, and also can reduce the cost of the hardware device.

[0186] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the weighing state determination device, the device and the corresponding units described above can be referred to the descriptions of the weighing state determination device, the device and the corresponding units in the embodiments of the application. Figures 1 to 7 The descriptions of the weighing state determination method in any embodiment are not repeated here.

[0187] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by related hardware controlled by the instructions, which can be stored in a computer readable storage medium and loaded and executed by a processor.

[0188] To this end, the present application provides a computer readable storage medium, which stores a plurality of instructions capable of being loaded by a processor to execute the method of the present application as Figures 1 to 7 Corresponding to the steps in the determination method of the weighing state in any embodiment, the specific operation can be referred to as Figures 1 to 7 Corresponding to the description of the determination method of the weighing state in any embodiment, it will not be repeated here.

[0189] The computer readable storage medium can include a read only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0190] Due to the instructions stored in the computer readable storage medium, the method of the present application as Figures 1 to 7 Corresponding to the steps in the determination method of the weighing state in any embodiment, the specific operation can be referred to as Figures 1 to 7 Corresponding to the beneficial effects that can be achieved by the determination method of the weighing state in any embodiment, the details are described above, and will not be repeated here.

[0191] The determination method, device, equipment and computer readable storage medium of the weighing state provided by the present application are described in detail above, and the principle and implementation mode of the present application are described by applying specific examples; the above embodiment is only used to help understand the method and core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed; in view of the above, the content of the specification should not be understood as the limitation of the present application.

Claims

1. A method of determining a weighing state, characterized by, The method comprises: acquiring a target image, wherein the target image is an image obtained by photographing a weighing device for weighing a to-be-weighed logistics piece; performing logistics piece identification in the target image to obtain a logistics piece identification result; determining whether a weighing state of the to-be-weighed logistics piece is normal according to the logistics piece identification result and a preset logistics piece abnormal weighing state condition; the logistics piece abnormal weighing state condition is specifically: if the number of logistics pieces in the logistics piece identification result is greater than 1 and the confidence in the logistics piece identification result is greater than a confidence threshold, it is determined that the weighing state is an abnormal weighing state; or, if the number of logistics pieces in the logistics piece identification result is greater than 1, it is determined that the weighing state is an abnormal weighing state; performing logistics piece identification in the target image to obtain a logistics piece identification result comprises: performing logistics piece identification in the target image according to a preset logistics piece image feature to obtain a first identified logistics piece; screening a second logistics piece in the first logistics piece according to a boundary of a weighing area of the weighing device; confirming the number of the second logistics piece as the number of logistics pieces in the logistics piece identification result.

2. The method of claim 1, wherein, The screening of the second logistics piece in the first logistics piece according to the boundary of the weighing area of the weighing device comprises: extracting a detection frame boundary corresponding to each logistics piece in the first logistics piece; extracting a first boundary line and a second boundary line of the boundary of the weighing area, wherein the weighing device is a dynamic weighing device, the weighing area includes an area on a conveying belt, the first boundary line and the second boundary line are boundary lines arranged at two positions in front of and behind the conveying belt in a conveying direction, and the first boundary line and the second boundary line correspond to area boundaries of the weighing area, respectively; from the first logistics piece, determining a logistics piece whose detection frame boundary is within a range between the first boundary line and the second boundary line as the second logistics piece.

3. The method of claim 1, wherein, The logistics piece abnormal weighing state condition is specifically: if the number of logistics pieces in the logistics piece identification result is equal to 1, it is determined that the weighing state is a normal weighing state.

4. The method of claim 1, wherein, if the weighing state is determined to be an abnormal weighing state, the method further comprises: outputting prompt information, wherein the prompt information is used to prompt a user that there is an abnormal weighing state, or the prompt information is used to trigger a sorting device to re-perform sorting processing on a logistics piece on the weighing device.

5. A device for determining a state of a weighing, characterized in that The device comprises: an acquisition unit configured to acquire a target image, wherein the target image is an image obtained by photographing a weighing device for weighing a to-be-weighed logistics piece; an identification unit configured to perform logistics piece identification in the target image to obtain a logistics piece identification result; The determining unit is configured to determine whether the weighing state of the to-be-weighed logistics piece is normal according to the logistics piece identification result and a preset logistics piece abnormal weighing state condition. The logistics piece abnormal weighing state condition is specifically: if the number of logistics pieces in the logistics piece identification result is greater than 1 and the confidence in the logistics piece identification result is greater than a confidence threshold, it is determined that the weighing state is an abnormal weighing state; or, if the number of logistics pieces in the logistics piece identification result is greater than 1, it is determined that the weighing state is an abnormal weighing state. The identifying unit is configured to perform logistics piece identification in the target image to obtain a logistics piece identification result, which includes: performing logistics piece identification in the target image according to a preset logistics piece image feature to obtain a first identified logistics piece; filtering a second logistics piece in the first identified logistics piece according to a boundary of a weighing area of the weighing device; confirming the number of the second logistics piece as the number of logistics pieces in the logistics piece identification result.

6. A device for determining the weighing state, characterized in that, The processor and the memory are included, and the memory stores a computer program. When the processor invokes the computer program in the memory, the method in any one of claims 1 to 4 is executed.

7. A weighing system characterized in that, The weighing system includes a weighing device, a sorting device, and a weighing state determining device as claimed in claim 6.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a plurality of instructions, which are suitable for being loaded by the processor to execute the method in any one of claims 1 to 4. The computer readable storage medium stores a plurality of instructions, which are suitable for being loaded by the processor to execute the method in any one of claims 1 to 4.

Images