Logistics information detection method, system and device and storage medium

Abstract

The invention provides a logistics information detection method, system and device and a storage medium, and the method comprises the steps: receiving at least one group of transfer information of a target package, and enabling any transfer information to comprise a perspective image, weighing data and order information of the target package at a corresponding transfer node; based on at least one of weighing data and order information in the at least one group of transfer information and a perspective image, determining a target transfer node corresponding to the target package entering a preset loss state; and outputting the order information and the information of the target transfer node. According to the embodiment of the invention, most of the transfer data can be filtered in an automatic manner, and the detection efficiency can be improved to a great extent.

Description

Technical Field

[0001] This application relates to the field of logistics technology, and particularly to a logistics information detection method, system, device and storage medium. Background Art

[0002] Logistics is a process of moving goods from the supply place to the receiving place, including a series of activities such as transportation, storage, packaging, distribution, loading and unloading, storage, and logistics information management of goods. During the process of goods flow, the situation of lost goods occurs from time to time. At present, manual inspection is used to detect lost goods packages. However, for thousands of goods packages and multiple transportation links, not only is the labor cost high, but the detection efficiency is also low. Summary of the Invention

[0003] This application proposes a logistics information detection method, system, device and storage medium, which can automatically screen out suspected lost packages from a large number of packages, not only saving labor costs but also improving detection efficiency.

[0004] In a first aspect, an embodiment of this application proposes a logistics information detection method, which is applied to a detection system and includes: receiving at least one set of transfer information of a target package, where any set of transfer information includes a perspective image, weighing data, and order information of the target package at a corresponding transfer node; determining a target transfer node corresponding to the target package entering a preset lost state based on at least one of the weighing data and order information in the at least one set of transfer information and the perspective image; and outputting the order information and the information of the target transfer node.

[0005] In one implementation manner of the first aspect, determining a target transfer node corresponding to the target package entering a preset lost state based on at least one of the weighing data and order information in the at least one set of transfer information and the perspective image includes: for any set of transfer information, in response to receiving the transfer information, detecting whether the transfer information represents that the target package is in a preset lost state based on the order information and the perspective image in the transfer information; if the transfer information represents that the target package is in a preset lost state, determining the transfer node corresponding to the transfer information as the target transfer node.

[0006] In one implementation manner of the first aspect, determining a target transfer node corresponding to the target package entering a preset lost state based on at least one of the weighing data and order information in the at least one set of transfer information and the perspective image includes: when the at least one set of transfer information is at least two sets of transfer information, detecting whether the target package changes to a preset lost state based on the weighing data and the perspective image in the at least two sets of transfer information; if the target package changes to a preset lost state, determining the transfer node corresponding to the transfer information after the target package changes its state as the target transfer node.

[0007] In an implementation of the first aspect, based on the order information and the perspective image in the transfer information, detecting whether the transfer information indicates that the target package is in a preset lost state includes: determining the item state of the target package according to the perspective image in the transfer information; if it is determined that there is no item in the target package, determining whether the item type indicated by the perspective image order information in the transfer information is a preset type; if the item type indicated by the order information is a preset type, determining that the transfer information indicates that the target package is in a preset lost state.

[0008] In an implementation of the first aspect, if the item type indicated by the order information is not a preset type, starting from the transfer information, sequentially comparing the weighing data in every two adjacent transfer information in the earlier transfer information; if the first weighing data is less than the second weighing data, determining that the transfer information corresponding to the first weighing data indicates that the target package has changed to a preset lost state; the transfer information corresponding to the first weighing data is the transfer information obtained later among any two adjacent transfer information, and the transfer information corresponding to the second weighing data is the transfer information obtained earlier among any two adjacent transfer information.

[0009] In an implementation of the first aspect, based on the weighing data and the perspective image in at least two sets of transfer information, detecting whether the target package has changed to a preset lost state includes: in response to receiving the i-th set of transfer information, comparing the i-th weighing data with the (i - 1)-th weighing data, where the i-th weighing data refers to the weighing data in the i-th set of transfer information, and the (i - 1)-th weighing data refers to the weighing data in the (i - 1)-th set of transfer information; i is an integer greater than or equal to 2; if the i-th weighing data is less than the (i - 1)-th weighing data, detecting whether the i-th perspective image is the same as the (i - 1)-th perspective image; the i-th perspective image refers to the perspective image in the i-th set of transfer information, and the (i - 1)-th perspective image refers to the perspective image in the (i - 1)-th set of transfer information; if the i-th perspective image is different from the (i - 1)-th perspective image, determining that the target package has changed to a preset lost state at the transfer node corresponding to the i-th set of transfer information.

[0010] In an implementation of the first aspect, determining the item state of the target package according to the perspective image in the transfer information includes: extracting the color features of the perspective image, where the color features include the brightness feature value of the perspective image; if the brightness feature value is greater than the preset brightness threshold, determining that there is no item in the target package.

[0011] In an implementation of the first aspect, detecting whether the i-th perspective image is the same as the (i - 1)-th perspective image includes: respectively extracting the semantic features of the i-th perspective image and the semantic features of the (i - 1)-th perspective image to obtain a first semantic feature and a second semantic feature; calculating a similarity parameter between the first semantic feature and the second semantic feature; if the similarity represented by the similarity parameter does not meet a preset similarity condition, determining that the i-th perspective image is different from the (i - 1)-th perspective image.

[0012] In an implementation of the first aspect, the detection system includes a first detection device and a second detection device, and receives at least one set of transfer information of the target package, including: the first detection device receives at least one set of perspective images and order information of the target package; if the first detection device receives at least two sets of transfer information of the target package, the second detection device receives at least two sets of perspective images, weighing data and order information of the target package.

[0013] In an implementation of the first aspect, based on at least one of the weighing data and the order information in at least one set of transfer information and the perspective image, determining a target transfer node corresponding to the target package entering a preset lost state includes: the first detection device, in response to receiving the transfer information, based on the order information and the perspective image in the transfer information, detects whether the transfer information indicates that the target package is in the preset lost state; the second detection device, based on the weighing data and the perspective image in at least two sets of transfer information, detects whether the target package has changed to the preset lost state.

[0014] In a second aspect, an embodiment of the present application provides a logistics information detection system, including:

[0015] A receiving module, configured to receive at least one set of transfer information of the target package, and any transfer information includes a perspective image, weighing data and order information of the target package at a corresponding transfer node;

[0016] A determining module, configured to determine a target transfer node corresponding to the target package entering a preset lost state based on at least one of the weighing data and the order information in at least one set of transfer information and the perspective image;

[0017] An output module, configured to output the order information and the information of the target transfer node.

[0018] An embodiment of the third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor runs the computer program to implement the method of the first aspect described above.

[0019] An embodiment of the fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and the program is executed by the processor to implement the method of the first aspect described above.

[0020] In the embodiments of the present application, by receiving transfer information such as perspective images, weighing data, and order information of a target package at each transfer node, based on the processing of at least one set of transfer information, it is possible to detect whether the target package is suspected of being lost and the transfer link where the loss is suspected, and output relevant detection results for further confirmation of the loss situation. In this way, not only can most of the transfer data be filtered out in an automated manner, greatly improving the detection efficiency, but also it is beneficial to timely solve the problem of item loss before the user perceives it, thereby improving the user experience.

[0021] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 FIG. shows a schematic architecture diagram of a logistics system provided by an embodiment of the present application;

[0024] Figure 2 FIG. shows a schematic flowchart of a logistics information detection method provided by an embodiment of the present application;

[0025] Figure 3 FIG. shows a schematic architecture diagram of a logistics information detection system provided by an embodiment of the present application;

[0026] Figure 4 FIG. shows a schematic composition diagram of a logistics information detection system provided by an embodiment of the present application;

[0027] Figure 5 FIG. shows a schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The following will describe the exemplary embodiments of the present application in more detail with reference to the drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0029] It should be understood that the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of this application, "a plurality of" means two or more, unless otherwise specifically defined.

[0030] It should be noted that unless otherwise specified, the technical terms or scientific terms used in this application should have the ordinary meanings understood by those skilled in the art to which this application pertains.

[0031] First, the technical scenario involved in the embodiments of this application will be described.

[0032] In the logistics field, items are usually packaged into parcels for flow. During the flow of parcels, there will be at least one transfer. In actual implementation scenarios, usually a large number of parcels go through multiple transfers respectively. In the scenario where a large number of parcels go through multiple transfers respectively, situations such as the loss or replacement of items inside the parcels often occur, thus resulting in a poor user experience.

[0033] The existing methods for detecting item loss usually are, after receiving the information of item loss feedback from users, manually tracing the flow line of the item parcel, the number of transfers, relevant data at each transfer, etc., to lock the transfer node where the item is suspected to be lost. After that, further detect, verify and give conclusions and solutions. Since the parcels to be detected may go through multiple transfers, and each transfer may be processed together with a large number of other parcels. It can be seen that through the manual detection method, not only the labor cost is high, but also the amount of data to be processed is large, resulting in low detection efficiency, thus further reducing the user experience.

[0034] In view of this, the embodiments of this application provide a logistics information detection system. This logistics information detection system can identify the parcels suspected to be lost and the transportation links where the parcels are suspected to be lost by detecting the parcel information (also called transfer information) obtained at each transfer node. After that, output the relevant identification results for further confirmation of the loss situation. In this way, not only can most of the data be filtered out through an automated method, greatly improving the detection efficiency, but also it is beneficial to solve the problem of item loss in time before the user perceives it, thereby improving the user experience.

[0035] As Figure 1 shown, the logistics system involved in the embodiments of this application may include: at least one transfer node 10 and a detection system 20. Among them, the relevant devices of at least one transfer node 10 are all communicatively connected to the detection system 20.

[0036] It should be understood, Figure 1The technical scenario shown is only one technical scenario of the solution of this application and does not constitute a limitation on the technical scenario of the solution of this application. Figure 1 The transfer nodes and detection systems shown can be regarded as functionally equivalent components. In some embodiments, in the technical scenario of the solution of this application, each transfer node may include multiple package detection devices, and the detection system may also include multiple detection devices (such as Figure 3 shown). There is no limitation here.

[0037] Any transfer node 10 may correspond to a logistics transfer yard in the actual logistics scenario. Correspondingly, any transfer node 10 may include a six-sided scanning device, a weighing device, and a security inspection device, so as to perform six-sided scanning on the packages passing through the transfer node using the six-sided scanning device to obtain the order information of the package; perform weighing using the weighing device to obtain the weighing data of the package at the transfer node; use the security inspection device to scan the package to obtain the perspective image of the package. The package information obtained by the three devices of the transfer node can be used as the transfer information of the transfer node. After that, the three devices of the transfer node can respectively transmit the obtained package information to the detection system 20, so that the detection system 20 can detect the transfer information of the package at the transfer node to determine whether the status of the package at the transfer node is the preset lost status.

[0038] In some embodiments, the six-sided scanning device, weighing device, and security inspection device of any transfer node 10 can be arranged in sequence. For example, after the package enters the transfer node, it first passes through the six-sided scanning device, then passes through the weighing device, and finally passes through the security inspection device. The three devices of any transfer node 10 can transmit the obtained package information to the detection system 20 immediately after obtaining the package information of a package.

[0039] It should be noted that different packages may pass through different numbers of transfer nodes according to the logistics address and path. For example, some packages have relatively short logistics paths (such as adjacent cities) and can pass through one transfer node; for another example, some packages have relatively long logistics paths (such as spanning multiple cities) and can pass through multiple transfer nodes. If an item in a package is lost during transportation, then at least one of the perspective image and weighing data of the package will change. Based on this, after each transfer node 10 obtains the package information and transmits it to the detection system 20, it helps the detection system 20 to screen out the packages suspected of having lost items by detecting the transfer information of each transfer node 10.

[0040] After receiving a set of transfer information from any transfer node 10, the detection system 20 can establish a corresponding relationship among the perspective image, weighing data, and order information in the transfer information, and detect the perspective image, weighing data, and order information according to a preset detection rule. Among them, the detection of the perspective image by the detection system 20 can be implemented as recognizing the state of the corresponding perspective image based on the image features of the perspective image, or detecting the similarity of the image features of the same package at two transfer nodes to recognize the state of the items in the corresponding package, etc. In the embodiments of the present application, the image features of the perspective image can be implemented as different features in different implementation manners. The detection of the weighing data by the detection system 20 can be implemented as: comparing the consistency of the weighing data of the same package at two adjacent transfer connection points to assist in identifying whether the items in the package are lost. The detection of the order information by the detection system 20 can include determining the item information, package attribute information, etc. in the package through the order information.

[0041] Correspondingly, function modules such as an image recognition algorithm or network model, a data comparison module, and an information recognition module can be pre-deployed in the detection system 20. Among them, there can be multiple image recognition algorithms or network models according to the implementation scenario, for example, including a lightweight convolutional neural network (mobile net) and a Siamese Network.

[0042] The detection system 20 can be implemented as any electronic device that supports the above detection functions. The electronic device can be an independent server, or a server network, server cluster, blockchain system, etc. composed of servers. The electronic devices described in the embodiments of the present application can include, but are not limited to, computers, network hosts, single network servers, multiple sets of network servers, cloud servers composed of multiple servers, or a combination form of edge servers and cloud servers. Among them, the cloud server is composed of a large number of computers or network servers based on cloud computing (Cloud Computing).

[0043] In some embodiments, if the detection system 20 includes a first detection device and a second detection device, different function modules can be deployed in different detection devices according to the computing power of the first detection device and the second detection device, so that the first detection device and the second detection device execute different steps in the detection method (such as Figure 3 the illustrated embodiment).

[0044] The following describes the logistics information detection method, system, device, and storage medium of the embodiments of the present application with reference to examples.

[0045] Figure 2 Shows a logistics information detection method provided by the embodiments of the present application, Figure 2The schematic logistics information detection method can be applied to Figure 1 the detection system shown in

[0046] In step S201, at least one set of transfer information of the target package is received.

[0047] Among them, the target package can be any package being transferred.

[0048] It should be understood that although a package may pass through multiple transfer nodes and a transfer node processes multiple packages, the detection process of the transfer information of any package at each transfer node can be considered the same. Based on this, in the embodiments of the present application, any transferred package is used as the target package to illustrate the embodiments of the logistics information detection method of the present application.

[0049] Combined with the above technical scenario, any transfer information includes a perspective image, weighing data, and order information of the target package at the corresponding transfer node.

[0050] In some embodiments, the order information can be implemented in the form of a barcode or a QR code, and the barcode or QR code can be obtained by converting the order number, item name, note information (for example, the number of items, whether it is fragile, whether it is insured) of the target package, etc.

[0051] Combined with Figure 1 the illustrated embodiments, the perspective image, weighing data, and order information in any transfer information of the target package are respectively obtained by three devices at the corresponding transfer node. Correspondingly, the detection system can receive the corresponding information from the three devices at the corresponding transfer node respectively. To facilitate the management and detection of the package information of each transfer node, after receiving the perspective image, weighing data, and order information of the target package, the detection system can, for example, establish the corresponding relationship of these three items of information with the order information as the index.

[0052] In some embodiments, if the detection system includes a first detection device and a second detection device, both the first detection device and the second detection device can receive at least one set of transfer information of the target package. If the computing powers of the first detection device and the second detection device are different, for example, the computing power of the first detection device is less than that of the second detection device, the first detection device can receive at least one set of perspective images and order information of the target package, while the second detection device can receive at least two sets of perspective images, weighing data, and order information of the target package and establish the corresponding relationship of the three items of package information for each set of transfer information when the target package corresponds to at least two sets of transfer information.

[0053] Exemplarily, if the computing power of the first detection device is less than that of the second detection device, the first detection device may first receive at least one set of perspective images and order information of the target package. If it is determined that the target package corresponds to at least two sets of transfer information, the first detection device may send commands to each connected transfer node, so that each transfer node sends all the transfer information of the target package to the second detection device.

[0054] In step S202, based on at least one of the weighing data and the order information in at least one set of transfer information and the perspective image, determine the target transfer node corresponding to the target package entering the preset lost state.

[0055] Among them, if the transfer information meets the preset conditions, it can be determined that the corresponding transfer information indicates that the target package is in the preset lost state.

[0056] It should be noted that there can be various scenarios of item loss in the target package. For example, all items in the target package are lost; for another example, a part of the items in the target package are lost; and for another example, the items in the target package are swapped. For different loss scenarios, the changed package information items are also different. For example, if all items in the target package are lost, then the perspective image of the target package shows that there are no items in the target package, and the weighing data of the target package will become smaller; for another example, if a part of the items in the target package are lost, the perspective image of the target package still shows that there are items in the target package, but the weighing data of the target package will still become smaller; for another example, if the items in the target package are swapped, the perspective image of the target package still shows that there are items in the target package, and the weighing data of the target package may change, but the content of the perspective images of different transfer information of the target package will change.

[0057] It should be understood that the above are only exemplary item loss scenarios listed, and the changes in package information caused by different loss scenarios do not limit the scenarios involved in the embodiments of the present application. In the actual implementation scenarios, the scenarios of item loss may be more than those listed above, and the changes in the corresponding package information under different loss scenarios may be more complex and changeable. They are not listed one by one here.

[0058] Referring to the changes in package information caused by the above different loss scenarios, the conditions for the transfer information to indicate that the target package is in the preset lost state may include, for example: there are no items in the target package, there are no items in the target package and the weighing data of two adjacent sets of transfer information of the target package are different, the weighing data and the content of the perspective images of two adjacent sets of transfer information of the target package are different, and so on. Further, the embodiments of the present application can, according to different loss scenarios, based on at least one of the weighing data and the order information and the perspective image, detect from different angles whether the target package is in the preset lost state at the relevant transfer node.

[0059] In some embodiments for detecting whether a target package is in a preset lost state at a relevant transfer node, for any transfer information, in response to receiving the transfer information, the detection system may detect whether the transfer information indicates that the target package is in the preset lost state based on the order information and the perspective image in the transfer information. If the transfer information indicates that the target package is in the preset lost state, the detection system may determine the transfer node corresponding to the transfer information as the target transfer node.

[0060] Exemplarily, the detection system may determine the item state of the target package according to the perspective image in the transfer information. If it is determined that there are no items in the target package, that is, the target package is an empty package, the detection system may determine whether the item type indicated by the perspective image order information in the transfer information is a preset type. If the item type indicated by the order information is a preset type, it is determined that the transfer information indicates that the target package is in the preset lost state.

[0061] Among them, the perspective image may represent the items in the target package through color, brightness of the color, etc. For example, for items that cannot be penetrated by the light of the security inspection machine, the perspective image of the corresponding items may be an image that is blue and has a certain contour, while for items that can be penetrated by the light of the security inspection machine, the perspective image of the corresponding items may be an orange image with relatively low brightness. Based on this, the detection system may extract the color features of the perspective image, and the color features include the brightness feature value of the perspective image. For example, if the brightness feature value is greater than the preset brightness threshold, it is determined that there are no items in the target package.

[0062] Exemplarily, the brightness feature value can be flexibly set according to requirements. For example, the brightness feature value can be set to 128.

[0063] The detection system may, for example, call the pre-trained mobile net to extract the color features of the perspective image. The color features may include the features of each of the three primary colors (red, green, blue, RGB) of the perspective image, as well as the brightness features and transparency features of each color. Furthermore, the mobile net may determine the type of the item state in the package matched by the perspective image based on the extracted color features. The types of the item state in the package may include no items (i.e., an empty package), there are items but the package is not full, and the package is full.

[0064] It should be noted that in the actual implementation scenario, the color features of some item perspective images may be similar to those of an empty package, such as clothes, paper, etc. Based on this, even if it is determined that there are no items in the target package through the color features of the perspective image, it may not be accurate to determine the target package as a lost state. To improve the accuracy of the detection result, after determining that there are no items in the target package according to the color features of the perspective image, the state of the target package may be further detected based on at least one of the order information and the weighing data of the target package.

[0065] In an actual implementation scenario, some types of items can be preset according to empirical values with a relatively high loss rate as a basis for further determining whether an empty package is a lost package. Furthermore, after determining that there are no items in the target package, it is possible to determine whether the items in the target package are of the preset type according to the order information of the target package. If the items in the target package are of the preset type, it can be determined that the target package is a lost package. The preset type can include, for example, the type of item whose name indicates an electronic product and the type selected by the user for insured value.

[0066] In addition, if it is determined that there are no items in the target package and the items in the target package are not of the preset type, in the case where the target package corresponds to at least two sets of transfer information, it is possible to determine whether the weight of the target package has changed during the transfer process by comparing the weighing data in every two adjacent sets of transfer information. If the weight of the target package has changed during the transfer process, it can be determined that the target package has changed to the preset lost state.

[0067] Exemplarily, if the type of item indicated by the order information is not the preset type, the detection system can start from the transfer information and sequentially compare the weighing data in every two adjacent sets of transfer information in the earlier transfer information. Take the weighing data of the later obtained transfer information in any two adjacent sets of transfer information as the first weighing data, and take the weighing data of the earlier obtained transfer information in these two adjacent sets of transfer information as the second weighing data. If the first weighing data is less than the second weighing data, it can be determined that the items in the target package are lost during the transportation between the transfer nodes corresponding to these two adjacent sets of transfer information. Correspondingly, it can be determined that the transfer information corresponding to the first weighing data represents that the target package has changed to the preset lost state.

[0068] The above implementation method is for the detection of the scenario where all items in the target package are lost. For the scenario where some items in the target package are lost or replaced, the embodiments of the present application can detect by comparing the perspective images and weighing data in two adjacent sets of transfer information.

[0069] In other embodiments for detecting whether the target package is in the preset lost state at relevant transfer nodes, in the case where at least one set of transfer information is at least two sets of transfer information, the detection system can detect whether the target package has changed to the preset lost state based on the weighing data and perspective images in at least two sets of transfer information. If the target package has changed to the preset lost state, determine the transfer node corresponding to the transfer information after the target package changes its state as the target transfer node.

[0070] Exemplarily, in response to receiving the i-th group of transfer information, the detection system may compare the i-th weighing data with the (i - 1)-th weighing data. The i-th weighing data refers to the weighing data in the i-th group of transfer information, and the (i - 1)-th weighing data refers to the weighing data in the (i - 1)-th group of transfer information. Here, i is an integer greater than or equal to 2. That is, the (i - 1)-th group of transfer information and the i-th group of transfer information are the transfer information of any two adjacent transfer nodes. If the i-th weighing data is less than the (i - 1)-th weighing data, it is necessary to detect whether the i-th perspective image is the same as the (i - 1)-th perspective image. Here, the i-th perspective image refers to the perspective image in the i-th group of transfer information, and the (i - 1)-th perspective image refers to the perspective image in the (i - 1)-th group of transfer information. If the i-th perspective image is different from the (i - 1)-th perspective image, it indicates that both the importance and content of the items in these two groups of transfer information of the target package are different. Then, it can be determined that part of the items in the target package are lost during the transportation between these adjacent transfer nodes, and it can be determined that the target package changes to a preset lost state at the transfer node corresponding to the i-th group of transfer information.

[0071] It should be noted that in this example, detecting whether the i-th perspective image is the same as the (i - 1)-th perspective image means detecting whether the image content in the i-th perspective image is the same as the image content in the (i - 1)-th perspective image. Based on this, in this example, the detection system can respectively extract the semantic features of the i-th perspective image and the (i - 1)-th perspective image to obtain the first semantic feature and the second semantic feature. Then, the similarity parameter between the first semantic feature and the second semantic feature is calculated. If the similarity characterized by the similarity parameter does not meet the preset similarity condition, it is determined that the i-th perspective image is different from the (i - 1)-th perspective image.

[0072] For example, the detection system can call the pre-deployed Siamese Network to extract the first semantic feature and the second semantic feature. The similarity parameter between the first semantic feature and the second semantic feature can be implemented as a parameter for characterizing feature similarity such as Euclidean distance or cosine distance.

[0073] It should be understood that the above is only an illustrative implementation method of item loss detection and does not limit the technical solutions of the embodiments of the present application. In the actual implementation scenario, the above neural networks for extracting color features and semantic features can also be other algorithm networks that support related functions, which are not limited here.

[0074] In addition, in a scenario where the detection system includes a first detection device and a second detection device, MobileNet is, for example, pre-set in the first detection device, and Siamese Network is, for example, pre-set in the second detection device. The first detection device can, for example, perform empty package detection and detection of whether the type of the item is a preset type, while the second detection device can, for example, perform detection of whether the weighing data and the content of the perspective image are consistent in the transfer information of any two adjacent transfer nodes.

[0075] In some embodiments, if it is determined that the item in the target package is not an item of the preset type, the first detection device can obtain the weighing data in the transfer information of the target package from the second detection device to detect whether there is a change in the weighing data in every two adjacent transfer information. In other embodiments, if it is determined that the item in the target package is not an item of the preset type, the first detection device can send the order information of the target package to the second detection device so that the second detection device can detect whether there is a change in the weighing data in every two adjacent transfer information of the target package, and further determine whether the target package is in a state of item loss.

[0076] In step S203, the order information and the information of the target transfer node are output.

[0077] Among them, after determining that the item in the target package is suspected of being lost and the target transfer node corresponding to the suspected loss, the detection system can output the order information of the target package and the information of the target transfer node corresponding to the suspected loss to trigger relevant personnel to further verify the status of the target package. The information of the target transfer node can be, for example, the number of the transfer yard corresponding to the target transfer node.

[0078] Exemplarily, the detection system can output the order information and the information of the target transfer node through any device with an information output function or a display function in the first detection device and the second detection device. For example, if the first detection device is implemented as an edge server and the second detection device is implemented as a cloud server, the cloud server can output the order information and the information of the target transfer node.

[0079] In the embodiments of the present application, by receiving transfer information such as perspective images, weighing data, and order information of the target package at each transfer node, based on the processing of at least one set of transfer information, it can be detected whether the target package is suspected of being lost and the transfer link corresponding to the suspected loss, and the relevant detection results are output to facilitate further confirmation of the loss situation. In this way, not only can most of the transfer data be filtered out in an automated manner, which can greatly improve the detection efficiency, but also it is beneficial to solve the problem of item loss in time before the user perceives it, thereby improving the user experience.

[0080] In some embodiments, taking the first detection device implemented as an edge server and the second detection device implemented as a cloud server as an example, the structure of the detection system can be as Figure 3 shown. Figure 3 In this case, an edge server can be configured for each transit node, and the edge servers of each transit node can be communicatively connected to the cloud server.

[0081] Among them, for the functions of the edge server and the cloud server, reference can be made to the descriptions of the corresponding embodiments above, and details are not described herein again.

[0082] It can be seen that by adopting this implementation method, a logistics information detection system is provided. The logistics information detection system can detect the package information (also called transit information) obtained by each transit node, identify the suspected lost packages and the transportation links where the packages are suspected of being lost, and then output the relevant identification results for further confirmation of the lost situation. In this way, not only can most of the data be filtered out in an automated manner, greatly improving the detection efficiency, but also it is beneficial to timely solve the problem of item loss before the user perceives it, thereby improving the user experience.

[0083] Corresponding to the implementation method of the above logistics information detection method, an embodiment of the present application further provides a logistics information detection system, which can be used as Figure 1 the detection system shown in, and is used to execute the logistics information detection method of any of the above embodiments. As Figure 4 shown, the logistics information detection system includes: a receiving module 41, a determining module 42, and an output module 43.

[0084] Among them, the receiving module 41 is used to receive at least one set of transit information of a target package, and any transit information includes a perspective image, weighing data, and order information of the target package at a corresponding transit node; the determining module 42 is used to determine a target transit node corresponding to the target package entering a preset lost state based on at least one of the weighing data and the order information in at least one set of transit information and the perspective image; the output module 43 is used to output the order information and the information of the target transit node.

[0085] Optionally, the determining module 42 is further used to: for any transit information, in response to receiving the transit information, based on the order information and the perspective image in the transit information, detect whether the transit information represents that the target package is in a preset lost state; if the transit information represents that the target package is in a preset lost state, determine the transit node corresponding to the transit information as the target transit node.

[0086] Optionally, the determining module 42 is further configured to: when at least one set of transfer information is at least two sets of transfer information, detect whether the target package has changed to a preset lost state based on the weighing data and the perspective image in the at least two sets of transfer information; if the target package has changed to the preset lost state, determine the transfer node corresponding to the transfer information after the target package changes its state as the target transfer node.

[0087] Optionally, the determining module 42 is further configured to: determine the item state of the target package according to the perspective image in the transfer information; if it is determined that there is no item in the target package, determine whether the item type indicated by the perspective image order information in the transfer information is a preset type; if the item type indicated by the order information is the preset type, determine that the transfer information represents that the target package is in the preset lost state.

[0088] Optionally, the determining module 42 is further configured to: if the item type indicated by the order information is not the preset type, starting from the transfer information, sequentially check the weighing data in every two adjacent transfer information in the earlier transfer information; if the first weighing data is less than the second weighing data, determine that the transfer information corresponding to the first weighing data represents that the target package has changed to the preset lost state; the transfer information corresponding to the first weighing data is the later obtained transfer information among any two adjacent transfer information, and the transfer information corresponding to the second weighing data is the earlier obtained transfer information among any two adjacent transfer information.

[0089] Optionally, the determining module 42 is further configured to: in response to receiving the i-th set of transfer information, compare the i-th weighing data with the (i - 1)-th weighing data, where the i-th weighing data refers to the weighing data in the i-th set of transfer information, and the (i - 1)-th weighing data refers to the weighing data in the (i - 1)-th set of transfer information; i is an integer greater than or equal to 2; if the i-th weighing data is less than the (i - 1)-th weighing data, detect whether the i-th perspective image is the same as the (i - 1)-th perspective image; the i-th perspective image refers to the perspective image in the i-th set of transfer information, and the (i - 1)-th perspective image refers to the perspective image in the (i - 1)-th set of transfer information; if the i-th perspective image is different from the (i - 1)-th perspective image, determine that the target package has changed to the preset lost state at the transfer node corresponding to the i-th set of transfer information.

[0090] Optionally, the determining module 42 is further configured to: extract the color features of the perspective image, where the color features include the brightness feature value of the perspective image; if the brightness feature value is greater than the preset brightness threshold, determine that there is no item in the target package.

[0091] Optionally, the determining module 42 is further configured to: extract the semantic features of the i-th perspective image and the semantic features of the (i-1)-th perspective image respectively to obtain a first semantic feature and a second semantic feature; calculate a similarity parameter between the first semantic feature and the second semantic feature; and if the similarity represented by the similarity parameter does not meet a preset similarity condition, determine that the i-th perspective image is different from the (i-1)-th perspective image.

[0092] It should be noted that Figure 4 each module illustrated in Figure 3 can be understood as a software module that performs different logical functions in the process of executing the logistics information detection method. It does not conflict with

[0093] The logistics information detection system provided in the above embodiments of the present application and the logistics information detection method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0094] Figure 4 It is a software module obtained by dividing from the perspective of logical functions. In implementation, the functions of this software module can be integrated into a hardware entity for implementation. For example, the functions of the receiving module and the output module can be integrated into the communication interface for implementation; the function of the determining module can be integrated into the processor for implementation, etc.

[0095] Based on this, an embodiment of the present application further provides an electronic device, which can be used as Figure 1 the detection system 20 illustrated in Figure 5 to execute the above logistics information detection method. Please refer to Figure 5 which shows a schematic diagram of an electronic device provided in some embodiments of the present application. As Figure 5 shown, the electronic device 5 includes: a processor 500, a memory 501, a bus 502, and a communication interface 503. The processor 500, the communication interface 503, and the memory 501 are connected through the bus 502; a computer program that can run on the processor 500 is stored in the memory 501, and when the processor 500 runs the computer program, it executes the logistics information detection method provided in any of the foregoing embodiments of the present application.

[0096] Among them, the memory 501 may include a high-speed random access memory (Random Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 503 (which can be wired or wireless), a communication connection between this system network element and at least one other network element is realized, and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0097] The bus 502 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 501 is used to store programs. After receiving an execution instruction, the processor 500 executes the program. The foregoing Figure 2 The logistics information detection method disclosed in any of the foregoing embodiments can be applied to or implemented by the processor 500.

[0098] The processor 500 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 500 or by instructions in software form. The above-mentioned processor 500 can be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 501, and the processor 500 reads the information in the memory 501 and combines its hardware to complete the steps of the above method.

[0099] The electronic device provided in the embodiments of the present application and the logistics information detection method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run, or implemented by it.

[0100] Corresponding to the logistics information detection method provided in the foregoing embodiments, the embodiments of the present application also provide a computer-readable storage medium, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the logistics information detection method provided in any of the foregoing embodiments.

[0101] It should be noted that examples of the computer-readable storage medium may further include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other optical and magnetic storage media, which will not be elaborated here one by one.

[0102] The computer-readable storage medium provided by the above embodiments of the present application and the logistics information detection method provided by the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run, or implemented by the application programs stored therein.

[0103] It should be noted that:

[0104] In the specification provided here, a large number of specific details are described. However, it can be understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail so as not to obscure the understanding of this specification.

[0105] Similarly, it should be understood that, in order to streamline the present application and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be construed as reflecting the following schematic: that the claimed present application requires more features than those expressly recited in each claim. Rather, as reflected by the following claims, the inventive aspect lies in less than all the features of the single embodiments disclosed above. Therefore, the claims following the detailed description are hereby expressly incorporated into the detailed description, where each claim itself serves as a separate embodiment of the present application.

[0106] In addition, those skilled in the art can understand that, although some of the embodiments described herein include certain features included in other embodiments but not other features, the combination of the features of different embodiments means that it is within the scope of the present application and forms different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination.

[0107] As described above, the above are only the preferred specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A logistics information detection method, characterized in that, Applied to a detection system, including: Receiving at least one set of transfer information of a target package, where any transfer information includes a perspective image, weighing data, and order information of the target package at a corresponding transfer node; Based on at least one of the weighing data and order information in the at least one set of transfer information and the perspective image, determining a target transfer node corresponding to the target package entering a preset lost state; Outputting the order information and information of the target transfer node.

2. The method according to claim 1, characterized in that, The determining the target transfer node corresponding to the target package entering the preset lost state based on at least one of the weighing data and order information in the at least one set of transfer information and the perspective image includes: For any transfer information, in response to receiving the transfer information, based on the order information and the perspective image in the transfer information, detecting whether the transfer information indicates that the target package is in the preset lost state; If the transfer information indicates that the target package is in the preset lost state, determining the transfer node corresponding to the transfer information as the target transfer node.

3. The method according to claim 1, characterized in that The determining the target transfer node corresponding to the target package entering the preset lost state based on at least one of the weighing data and order information in the at least one set of transfer information and the perspective image includes: When the at least one set of transfer information is at least two sets of transfer information, based on the weighing data and the perspective image in the at least two sets of transfer information, detecting whether the target package has changed to the preset lost state; If the target package has changed to the preset lost state, determining the transfer node corresponding to the transfer information after the target package changes its state as the target transfer node.

4. The method according to claim 2, characterized in that, The detecting whether the transfer information indicates that the target package is in the preset lost state based on the order information and the perspective image in the transfer information includes: Determining the item state of the target package according to the perspective image in the transfer information; If it is determined that there is no item in the target package, determining whether the item type indicated by the perspective image order information in the transfer information is a preset type; If the item type indicated by the order information is the preset type, determining that the transfer information indicates that the target package is in the preset lost state.

5. The method according to claim 3 or 4, characterized in that, It further includes: If the item type indicated by the order information is not the preset type, starting from the transfer information, sequentially for the weighing data in every two adjacent transfer information in the earlier transfer information; If the first weighing data is less than the second weighing data, determining that the transfer information corresponding to the first weighing data indicates that the target package has changed to the preset lost state; The transfer information corresponding to the first weighing data is the transfer information obtained later among any two adjacent transfer information, and the transfer information corresponding to the second weighing data is the transfer information obtained earlier among the any two adjacent transfer information.

6. The method according to claim 3, wherein The detecting whether the target package has changed to the preset lost state based on the weighing data and the perspective image in the at least two sets of transfer information includes: In response to receiving the i-th group of transfer information, compare the i-th weighing data with the (i - 1)-th weighing data, where the i-th weighing data refers to the weighing data in the i-th group of transfer information, and the (i - 1)-th weighing data refers to the weighing data in the (i - 1)-th group of transfer information; i is an integer greater than or equal to 2. If the i-th weighing data is less than the (i - 1)-th weighing data, detect whether the i-th perspective image is the same as the (i - 1)-th perspective image; the i-th perspective image refers to the perspective image in the i-th group of transfer information, and the (i - 1)-th perspective image refers to the perspective image in the (i - 1)-th group of transfer information. If the i-th perspective image is different from the (i - 1)-th perspective image, determine that the target package changes to the preset lost state at the transfer node corresponding to the i-th group of transfer information.

7. The method according to claim 4, wherein Determining the item state of the target package according to the perspective image in the transfer information includes: Extract the color features of the perspective image, where the color features include the brightness feature value of the perspective image. If the brightness feature value is greater than the preset brightness threshold, determine that there is no item in the target package.

8. The method according to claim 6, wherein Detecting whether the i-th perspective image is the same as the (i - 1)-th perspective image includes: Extract the semantic features of the i-th perspective image and the semantic features of the (i - 1)-th perspective image respectively to obtain the first semantic feature and the second semantic feature. Calculate the similarity parameter between the first semantic feature and the second semantic feature. If the similarity characterized by the similarity parameter does not meet the preset similarity condition, determine that the i-th perspective image is different from the (i - 1)-th perspective image.

9. The method according to claim 1, wherein The detection system includes a first detection device and a second detection device. Receiving at least one group of transfer information of the target package includes: The first detection device receives at least one group of perspective images and order information of the target package. If the first detection device receives at least two groups of transfer information of the target package, the second detection device receives at least two groups of perspective images, weighing data and order information of the target package.

10. The method according to any one of claims 1-3, 9, characterized in that, Determining the target transfer node corresponding to the target package entering the preset lost state based on at least one of the weighing data and order information and the perspective image in the at least one group of transfer information includes: In response to receiving the transfer information, the first detection device detects whether the transfer information indicates that the target package is in the preset lost state based on the order information and the perspective image in the transfer information. The second detection device detects whether the target package changes to the preset lost state based on the weighing data and the perspective image in the at least two groups of transfer information.

11. A logistics information detection system, characterized in that, The system includes: A receiving module, configured to receive at least one group of transfer information of the target package, and any transfer information includes the perspective image, weighing data and order information of the target package at the corresponding transfer node. A determining module, configured to determine the target transfer node corresponding to the target package entering the preset lost state based on at least one of the weighing data and order information and the perspective image in the at least one group of transfer information. An output module, configured to output the order information and the information of the target transfer node.

12. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor runs the computer program to implement the method according to any one of claims 1-10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the method according to any one of claims 1-10.

Images