Method and apparatus for sampling packages in a logistics sorting center

Abstract

The present disclosure provides a package sampling method and device for a logistics sorting center; it relates to the technical field of logistics. The method comprises: receiving package information and loading information uploaded by a pickup site in real time; constructing a vehicle data pool for each vehicle, storing the package information in the corresponding vehicle data pool until the overflow condition is reached, and obtaining first package data; obtaining second pickup information, removing the package information corresponding to the second pickup information in the first package data, and obtaining second package data; respectively counting the total package information in the first package data and the risk package information in the second package data, determining a target sampling vehicle, and sampling the package of the target sampling vehicle. The present disclosure can solve the problems of low abnormal package detection rate, poor sampling effect and low sampling efficiency caused by the fact that the sampling personnel enter the station in advance to wait in the related art by random sampling.

Description

Technical Field

[0001] This disclosure relates to the field of logistics technology, and more specifically, to a method for random inspection of parcels in a logistics sorting center, a device for random inspection of parcels in a logistics sorting center, a computer-readable storage medium, and an electronic device. Background Technology

[0002] With the rapid development of the logistics industry, logistics and transportation have become an indispensable part of people's lives. Currently, the logistics industry uses weight or volume as the basis for billing the transportation and delivery of goods. However, the weight and volume of goods are determined by re-weighing and rely on manual recording. This leads to abnormal packages such as zero weight, zero volume, or overweight / oversized packages during actual logistics transportation or delivery, affecting the accuracy of logistics company data statistics and customer experience.

[0003] In related technologies, abnormal packages are detected by randomly sampling logistics vehicles and their contents at sorting centers. However, this results in a low detection rate and poor sampling effectiveness. Furthermore, it requires sampling personnel to be stationed at the sorting center in advance, leading to low sampling efficiency.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this disclosure is to provide a method for random sampling of packages in a logistics sorting center, a device for random sampling of packages in a logistics sorting center, a computer-readable storage medium, and an electronic device, thereby solving to some extent the problems in related technologies such as low detection rate of abnormal packages, poor sampling effect, and low sampling efficiency caused by sampling personnel entering the station in advance to wait.

[0006] According to a first aspect of this disclosure, a method for random inspection of parcels in a logistics sorting center is provided, comprising:

[0007] The system receives real-time package and loading information uploaded by pickup stations located before the logistics sorting center along the route. The package information includes first pickup information.

[0008] Based on the loading information, a vehicle data pool is constructed for each vehicle, and the package information is stored in the corresponding vehicle data pool until the vehicle data pool reaches the overflow condition, at which point the first package data is obtained.

[0009] Obtain the second pickup information, and based on the second pickup information and the first pickup information in the vehicle data pool, remove the package information in the first package data that corresponds to the second pickup information to obtain the second package data.

[0010] The total parcel information in the first parcel data and the risk parcel information in the second parcel data are respectively counted; based on the risk parcel information and the total parcel information, the target inspection vehicle is determined, and the target inspection vehicle is assigned to the inspection personnel so that the inspection personnel can carry out parcel inspection on the target inspection vehicle.

[0011] In one exemplary embodiment of this disclosure, based on the foregoing scheme, the package information includes waybill attributes, and before obtaining the second package data, the method further includes:

[0012] Based on the waybill attributes, package information corresponding to the target waybill attributes in the first package data is removed; the target waybill attributes include document-type waybills.

[0013] In one exemplary embodiment of this disclosure, based on the foregoing scheme, obtaining the second pickup information includes:

[0014] The second collection information is determined based on historical parcel collection information through an offline platform; the second collection information sent by the offline platform is received.

[0015] In one exemplary embodiment of this disclosure, based on the foregoing scheme, the method further includes:

[0016] For each pickup station in the vehicle data pool, a station data pool is constructed, and the waybill information of each pickup station is stored in the corresponding station data pool.

[0017] The system collects waybill information from each of the station data pools in the vehicle data pool and sends the waybill information from each collection station to the offline platform, so that the offline platform can determine risk station information based on the waybill information from each collection station.

[0018] In one exemplary embodiment of this disclosure, based on the foregoing scheme, the method further includes:

[0019] Receive the risk site information sent by the offline platform;

[0020] Based on the risk site information, the sampling site information is determined;

[0021] Based on the information from the sampling sites, packages at the logistics sorting center are sampled and inspected.

[0022] In one exemplary embodiment of this disclosure, based on the foregoing scheme, the step of randomly inspecting packages at the logistics sorting center based on the inspection site information includes:

[0023] Based on the sampling site information, vehicles containing the sampling site information are selected as target sampling vehicles, and packages inside the target sampling vehicles are sampled and inspected.

[0024] or,

[0025] Based on the sampling site information, packages inside the target sampling vehicle that correspond to the sampling site information are sampled and inspected.

[0026] In one exemplary embodiment of this disclosure, based on the aforementioned scheme, the risk site information is determined based on the collection waybill information, sampled waybill information, and over-standard waybill information of each collection site within the target period.

[0027] In one exemplary embodiment of this disclosure, based on the foregoing scheme, the vehicle loading information includes the vehicle's license plate information, and the method further includes:

[0028] The vehicle data pool corresponding to vehicles with empty license plate information is filtered out.

[0029] In an exemplary embodiment of this disclosure, based on the foregoing scheme, the risk package information includes the number of risk packages, the total package information includes the total number of packages, and the step of determining the target sampling vehicle based on the risk package information and the total package information includes:

[0030] Based on the comparison result of the proportion of the number of risky packages in the total number of packages and a first threshold, it is determined whether the corresponding vehicle meets the first sampling inspection condition;

[0031] In response to the comparison result between the number of risky packages and the second threshold, it is determined whether the corresponding vehicle meets the second sampling inspection condition;

[0032] When a vehicle meets both the first and second sampling conditions, the current vehicle is determined as the target sampling vehicle.

[0033] In one exemplary embodiment of this disclosure, based on the foregoing solution, the step of distributing the target inspection vehicle to the inspection personnel so that the inspection personnel can conduct package inspections on the target inspection vehicle includes:

[0034] The license plate information and departure time information of the target inspection vehicle are determined; the license plate information and departure time information of the target inspection vehicle are sent to the sorting center so that the inspection personnel can conduct random package inspections on the vehicles corresponding to the license plate information and departure time information of the target inspection vehicle.

[0035] According to a second aspect of this disclosure, a parcel sampling device for a logistics sorting center is provided, comprising:

[0036] The first receiving module is used to receive package information and loading information uploaded by the pickup station located before the sorting center in the routing line, wherein the package information includes the first pickup information;

[0037] The construction module is used to build a vehicle data pool for each vehicle based on the loading information, and store the package information in the corresponding vehicle data pool until the vehicle data pool reaches the overflow condition to obtain the first package data.

[0038] The first rejection module is used to obtain the second pickup information and, based on the second pickup information and the first pickup information in the vehicle data pool, reject the package information in the vehicle data pool that corresponds to the second pickup information, so as to obtain the risk package information in the vehicle data pool.

[0039] The sampling inspection module is used to collect risk package information and total package information in the vehicle data pool, determine target sampling vehicles based on the risk package information and total package information, and perform package sampling inspection on the target sampling vehicles.

[0040] According to a third aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the preceding claims.

[0041] According to a fourth aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method described in any of the preceding methods by executing the executable instructions.

[0042] The exemplary embodiments disclosed herein may have some or all of the following beneficial effects:

[0043] In the parcel sampling method for a logistics sorting center provided in the publicly available example implementation, on the one hand, parcel information and loading information uploaded by pickup stations located before the sorting center along the routing route can be received. Based on the loading information, a vehicle data pool is constructed for each vehicle. The vehicle data pool is used to store the parcel information and loading information corresponding to a vehicle. This isolates the parcel data within each vehicle, stores and statistically analyzes the parcel information by vehicle, and improves data processing efficiency. On the other hand, based on the second pickup information, the information on parcels exempt from inspection in each vehicle data pool can be removed to obtain the second parcel data and statistically analyze the risk parcels. Based on the risk parcel information and total parcel information of each vehicle, the target sampling vehicle is determined. On a vehicle-by-vehicle basis, based on the parcel information on the vehicle, the vehicle with higher risk is identified and used as the sampling vehicle. Compared with random sampling, this greatly improves the detection rate and sampling effect of abnormal parcels. In addition, the target sampling vehicle can be sent to the sampling personnel in real time, avoiding long waiting times for sampling personnel to arrive in advance and improving sampling efficiency.

[0044] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0046] Figure 1 A schematic diagram of an exemplary system architecture for a parcel sampling method and apparatus for a logistics sorting center, to which embodiments of the present disclosure can be applied, is shown.

[0047] Figure 2 A flowchart illustrating a parcel sampling method in a logistics sorting center according to an embodiment of the present disclosure is shown schematically.

[0048] Figure 3 The illustration shows a schematic diagram of a site isolation data processing procedure according to an embodiment of the present disclosure.

[0049] Figure 4 A flowchart illustrating a risk site determination process according to one embodiment of the present disclosure is shown.

[0050] Figure 5 The schematic diagram illustrates a process flow chart of a package sampling inspection method in a logistics sorting center according to an embodiment of the present disclosure.

[0051] Figure 6 The diagram illustrates a structural block diagram of a package sampling device in a logistics sorting center according to an embodiment of the present disclosure.

[0052] Figure 7 A schematic diagram of the structure of a computer system suitable for implementing the embodiments of the present disclosure is shown. Detailed Implementation

[0053] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of these specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0054] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0055] Figure 1 A schematic diagram of a system architecture 100 for an exemplary application environment in which a parcel sampling method and apparatus for a logistics sorting center, according to embodiments of this disclosure, can be applied. (See diagram below.) Figure 1 As shown, the system architecture 100 may include an information collection device 101, a processing server 102, and a terminal device 103. The information collection device 101 and the processing server 102, as well as the processing server 102 and the terminal device 103, are connected via network communication. The network includes, but is not limited to, a wide area network (WAN), a metropolitan area network (MAN), or a local area network (LAN). The information collection device 101 includes, but is not limited to, a barcode scanner with wireless communication capabilities, handheld terminal devices used in the logistics industry, various models of integrated weighing and barcode scanning machines, computer equipment connected to a barcode scanner, or other physical devices capable of collecting package information. The terminal device 103 includes, but is not limited to, various mobile terminal devices (e.g., mobile phones, tablets, etc.), intelligent handheld terminal devices used in the logistics industry, and various forms of computer equipment. The processing server 102 can be any form of server with data processing capabilities. In this example, the number of information collection devices 101, processing servers 102, and terminal devices 103 can be one or more; this example does not limit this. The information collection device 101 can be a package information collector at a collection station before the first sorting center.

[0056] Figure 1 In this process, after the vehicle loads packages at collection point 1, it transmits the package information from that point to processing server 102. Then, the vehicle travels along the route to collection point 2, loads packages at that point, uploads information, and then travels to collection point 3. After loading packages and uploading information at collection point 3, the vehicle travels to the first sorting center on the route. After the vehicle is sealed at the last collection point on the route, processing server 102 begins the method disclosed herein.

[0057] The package sampling inspection method for logistics sorting centers provided in this embodiment can be executed in the processing server 102. Accordingly, the package sampling inspection device for logistics sorting centers is generally set in the processing server 102.

[0058] The technical solutions of the embodiments of this disclosure are described in detail below:

[0059] refer to Figure 2 As shown, a parcel sampling inspection method for a logistics sorting center according to an example embodiment of this disclosure may include the following steps:

[0060] Step S210: Receive package information and loading information uploaded by the pickup station located before the sorting center in the routing line, wherein the package information includes the first pickup information.

[0061] In this example implementation, the sorting center can be the first sorting center located after the pickup station on the route. Package information may include package number, package attributes (such as clothing, documents, fruit, etc.), package quantity, package weight, and first pickup information, which may include package pickup time, package pickup station, package pickup merchant, package destination station, package receiving time, package receiving courier, etc. Loading information may include vehicle sealing operation, sealing time, sealing location, vehicle information (such as license plate number, vehicle model, vehicle load capacity, departure time, destination station arrival time, etc.), vehicle unsealing operation, unsealing time, unsealing location, etc.

[0062] In this example implementation, the parcel information and loading information of each collection station are obtained through barcode scanners, various handheld devices, or the data management center of each collection station.

[0063] Step S220: Based on the loading information, a vehicle data pool is constructed for each vehicle, and the package information is stored in the corresponding vehicle data pool until the vehicle data pool reaches the overflow condition to obtain the first package data.

[0064] In this example implementation, a vehicle data pool can be built for each vehicle to store the package and loading information corresponding to that vehicle. For example, the Flink architecture can be used to process package data streams in real time, building a data storage pool for each vehicle. When a vehicle is sealed, the corresponding data storage pool reaches its overflow condition and no longer stores data in it. The data stored in the vehicle data pool constitutes the first package data. The state of package receiving, sealing, pickup, and unsealing operations can also be stored in the state. Flink is an open-source stream processing framework developed by the Apache Software Foundation. Its core is a distributed stream data stream engine written in Java and Scala. State is a state mechanism in Flink that can be used to store process data.

[0065] For example, each package number can be hashed, and the data associated with the hash value can be stored in the corresponding vehicle data pool, using the Flink architecture to achieve package isolation between vehicles.

[0066] Step S230: Obtain the second pickup information, and based on the second pickup information and the first pickup information in the vehicle data pool, remove the package information in the first package data that corresponds to the second pickup information to obtain the second package data.

[0067] In this example implementation, the second pickup information is used to indicate the inspection-free pickup information in the logistics database. The inspection-free pickup information may include one or more of the following: trusted pickup merchant information, trusted pickup station information, and trusted pickup courier information. It may also include other forms of trusted pickup entity information, which is not limited in this example. In this example, the trusted pickup merchant / station information may include the name, logo, address, etc., of the trusted pickup merchant / station, which is not limited in this example. The second pickup information can be obtained through an offline platform. The offline platform can comprehensively evaluate each pickup entity based on its historical package pickup data (number or proportion of abnormal packages), credit rating, and location. In this example, relevant information (such as package information) corresponding to packages picked up by trusted pickup entities can be removed from each vehicle data pool, and the remaining package information can be used as the second package data.

[0068] Step S240: Collect the total parcel information in the first parcel data and the risk parcel information in the second parcel data respectively; based on the risk parcel information and the total parcel information, determine the target inspection vehicle and issue the target inspection vehicle to the inspection personnel so that the inspection personnel can carry out parcel inspection on the target inspection vehicle.

[0069] In this example implementation, the risk package information may include the number of risk packages, their weight, or volume. The total package information may include the total number of packages and the total weight or volume of packages in the vehicle data pool. For example, one or more of the following conditions may be used to determine the target vehicle for random inspection: the ratio of the number of risk packages to the total number of packages exceeding a preset upper limit, or the ratio of the weight (volume) of risk packages to the total weight (volume) of packages exceeding a preset upper limit.

[0070] In this example implementation, the sampling inspection personnel may conduct a package inspection of the target vehicle by verifying the weight (volume) of all packages of the target vehicle, or by verifying the weight (volume) of only some packages of the target vehicle. This example does not limit this.

[0071] In the parcel sampling method for a logistics sorting center provided in this example implementation, on the one hand, parcel information and loading information uploaded by pickup stations located before the sorting center along the routing route can be received. Based on the loading information, a vehicle data pool is constructed for each vehicle. The vehicle data pool is used to store the parcel information and loading information corresponding to a vehicle. This isolates the parcel data within each vehicle, stores and statistically analyzes the parcel information by vehicle, and improves data processing efficiency. On the other hand, based on the second pickup information, the information on parcels exempt from inspection in each vehicle data pool is removed to obtain the second parcel data and count the risk parcels. Based on the risk parcel information and total parcel information of each vehicle, the target sampling vehicle is determined. On a vehicle-by-vehicle basis, based on the parcel information on the vehicle, the vehicle with higher risk is identified and used as the sampling vehicle. Compared with random sampling, this greatly improves the detection rate and sampling effect of abnormal parcels. In addition, the target sampling vehicle can be sent to the sampling personnel in real time, avoiding the long waiting time for the sampling personnel to arrive in advance and improving the sampling efficiency.

[0072] In some embodiments, prior to obtaining the second package data, the method further includes:

[0073] Based on the waybill attributes, package information corresponding to the target waybill attributes in the first package data is removed; the target waybill attributes include document-type waybills.

[0074] In this example implementation, the waybill attribute can be the waybill type, such as document waybill, clothing waybill, fruit waybill, etc. Considering that document waybills are unlikely to have overweight or oversized abnormal packages, package information with the waybill attribute of "document" can be removed from the first package data first.

[0075] In some embodiments, obtaining the second pickup information includes:

[0076] First, the second collection information is determined through an offline platform based on historical parcel collection information.

[0077] In this example implementation, the second pickup information is used to indicate the inspection-free pickup information in the logistics database. The inspection-free pickup information may include one or more of the following: trusted pickup merchant information, trusted pickup station information, and trusted pickup courier information. It may also include other forms of trusted pickup entity information, which is not limited in this example. In this example, the trusted pickup merchant / station information may include the name, identifier, address, etc., of the trusted pickup merchant / station, which is not limited in this example. Historical package pickup information may be package information picked up by a pickup merchant within a certain period of time. For example, a pickup entity with zero abnormal packages picked up within the past month can be considered a trusted pickup entity. The offline platform can update and distribute the trusted pickup entities in the second pickup information in real time based on the pickup entity's real-time package pickup data.

[0078] Then, the second pickup information sent by the offline platform is received.

[0079] In this example implementation, the online sampling inspection platform determines the target vehicle for sampling inspection based on the received second pickup information.

[0080] In some embodiments, reference Figure 3 The method further includes:

[0081] Step S310: Construct a site data pool for each pickup station in the vehicle data pool, and store the waybill information of each pickup station in the corresponding site data pool.

[0082] In this example implementation, secondary data isolation is performed on the vehicle data pool, that is, the data in the vehicle data pool is stored separately according to the pickup station, and the parcel data of the same pickup station is stored in the same station data pool, which facilitates the subsequent statistical processing of station data and the traceability process of abnormal parcels or abnormal waybills.

[0083] Step S320: Collect the waybill information in each of the station data pools in the vehicle data pool, and send the waybill information of each collection station to the offline platform so that the offline platform can determine the risk station information based on the waybill information of each collection station.

[0084] In this example implementation, the waybill information may include waybill number, waybill attributes, waybill pickup merchant, and other waybill-related information. It can also collect statistics on the number of waybills, waybill weight, waybill volume, and waybill pickup merchants in each site's data pool. This statistical information is sent to the offline platform, enabling the offline platform to dynamically determine risk site information based on the waybill statistics for each site.

[0085] In some embodiments, reference Figure 4 The risk site information is determined based on the collection order information, sampled order information, and out-of-standard order information for each collection site within the target period. Specifically, it is obtained through an offline platform following these steps:

[0086] Step S410: Collect the inspection waybill information, collection waybill information, and oversized waybill information for each collection station within the target period.

[0087] In this example implementation, the target period can be a period of time prior to the current moment (such as ten days, a month, or a quarter). The sampled waybill information may include the number of sampled waybills and their weight (volume). The collected waybill information may include the number of collected waybills and their weight (volume). The out-of-limit waybill information may include the number of abnormal waybills sampled within the target period and their weight (volume). Abnormal waybills can be waybills whose actual weight (volume) differs from the weight (volume) stated on the waybill by a specified threshold.

[0088] Step S420: Based on the sampled waybill information and the out-of-standard waybill information, determine the waybill discrepancy rate of the corresponding collection station.

[0089] In this example implementation, the ratio of excess waybill information to sampled waybill information can be used as the waybill discrepancy rate. For example, the ratio of the number of excess waybills to the number of sampled waybills can be used as the waybill discrepancy rate.

[0090] Step S430: Based on the waybill discrepancy rate and the collection waybill information, determine the risk level of the corresponding collection station.

[0091] In this example implementation, different waybill discrepancy rates can be set to correspond to different risk scores. For example, a higher waybill discrepancy rate can result in a higher risk score. The ratio of historical excess waybill information to historical collected waybill information can also be used as a risk weighting factor, as can the information of the collecting courier (e.g., quantity) as another risk weighting factor. The risk score of the collection station can be determined based on one or more of these risk factors, and then the risk level can be classified according to the risk score. For example, a risk score can be set as follows: 20 points for a waybill discrepancy rate ≥ 0.15; 15 points for the number of waybills whose actual weight equals the total weight / total number of waybills collected ≥ 0.4; otherwise, 15 points + the number of couriers collecting the same weight from the same merchant. The number of couriers collecting the same weight from the same merchant can be the number of couriers whose daily average waybill collection volume exceeds a waybill volume threshold (e.g., 100 waybills) and whose actual weight equals the total weight exceeds a preset proportion (e.g., 40%).

[0092] Step S440: Determine risk site information based on the risk level of the collection site.

[0093] In this example implementation, collection stations with a risk level of a certain level or higher can be designated as risk stations. Risk station information may include the risk station name, risk station identifier, and the region where the risk station is located.

[0094] In some embodiments, the method further includes:

[0095] First, receive the risk site information sent by the offline platform.

[0096] In this example implementation, the online sampling platform receives risk site information sent by the offline platform.

[0097] Secondly, based on the risk site information, the sampling site information is determined.

[0098] In this example implementation, all risk sites can be used as sampling sites. Alternatively, all risk sites can be sorted by risk score, and the top 100 risk sites can be used as sampling sites. Sampling site information may include the sampling site name, sampling site identifier, and the region where the sampling site is located.

[0099] Finally, based on the information from the sampling sites, packages at the logistics sorting center were sampled and inspected.

[0100] In this example implementation, the objects to be sampled (parcels or waybills) can be determined from two dimensions: the target sampling vehicle and the sampling station. For example, the weight of parcels belonging to the sampling station in the target sampling vehicle can be verified.

[0101] In some embodiments, the method further includes:

[0102] The vehicle data pool corresponding to vehicles with empty license plate information is filtered out.

[0103] In this example implementation, the loading information may include the vehicle's license plate information. When the license plate information is empty, the vehicle data pool corresponding to that vehicle can be directly filtered out. For the first package data or the second package data, when it is found that the pickup station information corresponding to a certain package number is empty, the data associated with that package number can be filtered out.

[0104] In some embodiments, determining the target vehicle for random inspection based on the risk package information and the total package information includes:

[0105] Based on the comparison result of the proportion of the number of risky packages in the total number of packages and a first threshold, it is determined whether the corresponding vehicle meets the first sampling inspection condition.

[0106] In this example implementation, it can be set that when the proportion of risky packages in the total number of packages is greater than a preset first threshold, the corresponding vehicle is determined to meet the first sampling inspection condition.

[0107] Based on the comparison result between the number of risky packages and the second threshold, it is determined whether the corresponding vehicle meets the second sampling inspection condition.

[0108] In this example implementation, it can be set that when the number of risky packages exceeds a preset second threshold, the corresponding vehicle is determined to meet the second sampling inspection condition.

[0109] When a vehicle meets both the first and second sampling conditions, the current vehicle is determined as the target sampling vehicle.

[0110] In some embodiments, the step of distributing the target inspection vehicle to the inspection personnel so that the inspection personnel can conduct package inspections on the target inspection vehicle includes:

[0111] First, determine the license plate information and departure time information of the target vehicles to be sampled.

[0112] In this example implementation, license plate information and departure time information can be uploaded through the pickup station. A vehicle can be uniquely identified within the routing network using the license plate information and departure time information.

[0113] Then, the license plate information and departure time information of the target inspection vehicle are sent to the inspection personnel so that they can conduct package inspections on the vehicles corresponding to the license plate information and departure time information of the target inspection vehicle.

[0114] In this example implementation, the license plate information and departure time of the target inspection vehicle can be sent to the inspection personnel. This allows the inspection personnel to schedule their time reasonably, arrive at the inspection station on time, and proceed to the next inspection station immediately after the inspection, thus improving the work efficiency of the inspection personnel. In this example, the inspection personnel can verify the weight (volume) of all or part of the packages of the target inspection vehicle according to their work tasks and actual conditions.

[0115] In this example implementation, after each collection station collects the goods, it generates cargo routing information. After the package is loaded onto the vehicle at the collection station, the package information and loading information can be sent through a barcode scanner, handheld device, or the data management device of each collection station.

[0116] The following is a specific example illustrating the parcel sampling inspection method of the logistics sorting center disclosed in this disclosure. (Refer to...) Figure 5 As shown, the parcel sampling inspection method provided in this example for a logistics sorting center includes:

[0117] Step S501: The collection station collects real-time information on the parcels loaded onto the vehicle and the loading information.

[0118] In this example, the package information may include the first pickup information, which may include the package pickup time, package pickup station, package pickup merchant, package destination station, package receiving time, package receiving courier, and so on.

[0119] In step S502, the pickup station uploads the package information and loading information to the online data processing center in real time.

[0120] In this example, each logistics vehicle collects and uploads information about the packages being loaded at the pickup station in real time. Package and loading information can include details related to the package and vehicle, as well as status information such as receipt, vehicle sealing, pickup status, and planned destination.

[0121] In step S503, the online data processing center constructs a vehicle data pool for each vehicle based on the loading information, stores the package information in the corresponding vehicle data pool, and obtains the first package data when the vehicle data pool reaches the overflow condition.

[0122] In this example, based on the real-time uploaded package information and loading information, the relevant package information in each vehicle is stored in the corresponding vehicle data pool until the vehicle is sealed, at which point the first package data is obtained.

[0123] Step S504: The offline platform determines the second pickup information based on historical package pickup information.

[0124] In this example, the second pickup information may include trusted pickup merchant information. This can involve statistically analyzing the historical package pickup information of each merchant to obtain information such as the number of over-limit packages picked up by each merchant and the total number of packages. Merchants whose over-limit package count is below a certain percentage (e.g., 5%) of the total package volume can be designated as trusted pickup merchants.

[0125] In step S505, the offline platform sends the second collection information (such as trusted collection merchant information) to the online data processing center.

[0126] Step S506: Based on the second pickup information and the first pickup information in the vehicle data pool, the online data processing center removes the package information in the first package data that corresponds to the second pickup information.

[0127] In step S507, the online data processing center removes the package information corresponding to the file attribute waybill from the first package data to obtain the second package data.

[0128] Step S508: The online data processing center compiles the total parcel information in the first parcel data and the risk parcel information in the second parcel data; based on the risk parcel information and the total parcel information, the target vehicle for random inspection is determined.

[0129] In this example implementation, vehicles whose ratio of the number of risky packages to the total number of packages in the vehicle data pool is greater than a first threshold and whose number of risky packages exceeds a second threshold can be selected as target sampling vehicles.

[0130] Step S509: The online data processing center constructs a site data pool for each pickup station in the vehicle data pool and stores the waybill information of each pickup station in the corresponding site data pool.

[0131] In this example implementation, data from different stations can be isolated within the vehicle data pool, creating a separate station data pool for each pickup station. This allows the pickup station to serve as a risk assessment factor, improving the detection rate of abnormal packages during random sampling. Furthermore, isolating pickup station data facilitates tracing abnormal packages or waybills back to the pickup station in subsequent random sampling results.

[0132] Step S510: The online data processing center counts the waybill information in each of the station data pools in the vehicle data pool and sends the waybill information of each collection station to the offline platform.

[0133] In this example implementation, the waybill information may include the waybill number, the number of waybills, the weight of the waybill, and the parcel number corresponding to the waybill number.

[0134] Step S511: The offline platform determines the risk site information based on the waybill information of each collection site within the target period.

[0135] In this example implementation, the offline platform, based on the acquired information on sampled waybills and oversized waybills, counts the number of sampled waybills and oversized waybills within a specified target period (within one month from the current date). The proportion of oversized waybills to the total number of sampled waybills is used as the waybill discrepancy rate. A risk score is then assigned to the collection station based on this waybill discrepancy rate. Alternatively, the proportion of oversized waybills to the total number of collected waybills and the waybill discrepancy rate can be used together to assign a risk score to the collection station. Collection stations with risk scores higher than a specified value are designated as high-risk stations.

[0136] In step S512, the offline platform sends risk site information to the online data processing center.

[0137] Step S513: The online data processing center determines the sampling site information based on the risk site information.

[0138] In this example implementation, high-risk sites can be used as random sampling sites. Alternatively, some high-risk sites can be used as random sampling sites. The settings can be freely configured according to the actual situation.

[0139] In step S514, the online data processing center sends the target inspection vehicle and inspection site information to the inspection personnel of the corresponding logistics sorting center.

[0140] In this example, the target vehicle for inspection can be uniquely identified by its license plate number and departure time; that is, the license plate number plus the departure time is sufficient to uniquely identify the target vehicle. Inspection stations can be identified by station identifiers and / or station names.

[0141] Step S515: The inspection personnel conduct random inspections on packages belonging to the inspection stations within the target inspection vehicle.

[0142] Step S516: The sampling personnel upload the sampling results to the offline platform.

[0143] In this example, after the inspectors conduct random inspections (weight verification) of packages based on the target inspection vehicles and inspection stations, they send the inspection results (such as information on packages exceeding the standard, information on inspected packages, and information on packages that were inspected normally) to the offline platform, so that the offline platform can update the risk station information based on the actual inspection results.

[0144] In the above embodiments, subsequent data processing can be performed a certain time (e.g., 10 minutes) after the vehicle sealing operation corresponding to each vehicle data pool, allowing sufficient time for data transmission and storage to ensure data accuracy. The online data processing center can use the same vehicle, same time, and same pickup station as the sole statistical dimension. When a vehicle picks up goods and loads them at each pickup station, the cargo flow is stored in the station data pool according to the pickup station. When the vehicle is sealed and departed at the last pickup station before arriving at the sorting center, calculations are triggered based on the quantity and attributes of the goods in the station data pool of the vehicle data pool. Then, the pickup station of the vehicle is tagged to determine whether random inspection is required, and the vehicle itself is tagged to determine whether random inspection is necessary. When the vehicle is scanned after arriving at the sorting center, a prompt is made indicating whether random inspection is required, guiding the inspection personnel to perform the inspection operation.

[0145] The parcel sampling method for logistics sorting centers disclosed herein, on the one hand, uses factors such as trusted pickup entities (e.g., trusted pickup merchants), risk site information, and waybill type as risk assessment factors to determine target sampling vehicles and risky parcels. This guides sampling personnel to enter the corresponding sorting centers in a timely manner to conduct parcel sampling, promptly identify abnormal parcels (e.g., overweight parcels), and improve sampling efficiency and abnormal parcel detection rate. On the other hand, it utilizes Flink real-time data stream processing technology to store the loading, dispatching, sealing, and unsealing of goods in a stateful manner. It isolates and calculates the data distribution of different vehicles and different pickup sites. Vehicle isolation facilitates sampling by vehicle, and pickup site isolation facilitates the traceability process when sampling personnel detect abnormal parcels, allowing direct access to the pickup site of the abnormal parcel. Simultaneously, it provides data support for risk site assessment on offline platforms, improving the accuracy of risk site assessment. After obtaining the target sampling vehicle and sampling site information, timely reminders are sent to sampling personnel or sorting center operation terminals to guide parcel sampling. Compared to random blind sampling in related technologies, this method improves sampling efficiency and effectiveness.

[0146] Furthermore, this method maximizes efficiency for sampling personnel, avoiding the manpower and resources wasted on large-scale, piecemeal sampling inspections. Simultaneously, this method sends message queues of high-risk sites to an offline platform, providing data for subsequent real-time sampling inspection alerts.

[0147] Furthermore, this example embodiment also provides a package sampling inspection device 600 for a logistics sorting center. This package sampling inspection device 600 for a logistics sorting center can be applied to a server. (Reference) Figure 6 As shown, the package sampling inspection device 600 of the logistics sorting center may include:

[0148] The first receiving module 610 is used to receive package information and loading information uploaded by the pickup station located before the logistics sorting center in the routing line, wherein the package information includes the first pickup information.

[0149] The storage module 620 is used to construct a vehicle data pool for each vehicle based on the loading information, and store the package information in the corresponding vehicle data pool until the vehicle data pool reaches the overflow condition to obtain the first package data.

[0150] The first rejection module 630 is used to obtain the second pickup information and, based on the second pickup information and the first pickup information in the vehicle data pool, reject the package information in the first package data that corresponds to the second pickup information to obtain the second package data.

[0151] The sampling inspection module 640 is used to separately count the total package information in the first package data and the risk package information in the second package data; based on the risk package information and the total package information, it determines the target sampling vehicle and issues the target sampling vehicle to the sampling personnel so that the sampling personnel can carry out package sampling inspection on the target sampling vehicle.

[0152] In one exemplary embodiment of this disclosure, the device 600 further includes:

[0153] The second rejection module can be used to reject package information in the vehicle data pool that corresponds to the target waybill attribute based on the waybill attribute; the target waybill attribute includes document-type waybills.

[0154] In one exemplary embodiment of this disclosure, the first rejection module 630 may also be used for:

[0155] The second collection information is determined based on historical parcel collection information through an offline platform; the second collection information sent by the offline platform is received.

[0156] In one exemplary embodiment of this disclosure, the device 600 may further include:

[0157] The storage submodule can be used to build a site data pool for each pickup station in the vehicle data pool, and store the waybill information of each pickup station in the corresponding site data pool.

[0158] The sending module can be used to collect the waybill information in each of the station data pools in the vehicle data pool, and send the waybill information of each collection station to the offline platform, so that the offline platform can determine the risk station information based on the waybill information of each collection station.

[0159] In one exemplary embodiment of this disclosure, the device 600 may further include:

[0160] The second receiving module can be used to receive the risk site information sent by the offline platform.

[0161] The determination module can be used to determine the sampling site information based on the risk site information.

[0162] The sampling inspection submodule can be used to conduct random inspections of packages at the logistics sorting center based on the sampling inspection site information.

[0163] In one exemplary embodiment of this disclosure, the sampling submodule can also be used for:

[0164] Based on the sampling site information, vehicles containing the sampling site information are designated as target sampling vehicles, and packages inside the target sampling vehicles are randomly sampled for inspection. Alternatively, based on the sampling site information, packages inside the target sampling vehicles that correspond to the sampling site information are randomly sampled for inspection.

[0165] In one exemplary embodiment of this disclosure, the device 600 may further include:

[0166] The filtering module can be used to filter out the vehicle data pool corresponding to vehicles whose license plate information is empty.

[0167] In one exemplary embodiment of this disclosure, the sampling inspection module 640 can also be used for:

[0168] Based on the comparison result of the proportion of the number of risky packages in the total number of packages and a first threshold, it is determined whether the corresponding vehicle meets the first sampling inspection condition.

[0169] Based on the comparison result between the number of risky packages and the second threshold, it is determined whether the corresponding vehicle meets the second sampling inspection condition.

[0170] When a vehicle meets both the first and second sampling conditions, the current vehicle is determined as the target sampling vehicle.

[0171] In one exemplary embodiment of this disclosure, the sampling inspection module 640 can also be used for:

[0172] The license plate information and departure time information of the target inspection vehicle are determined; the license plate information and departure time information of the target inspection vehicle are sent to the sorting center so that the inspection personnel can conduct random package inspections on the vehicles corresponding to the license plate information and departure time information of the target inspection vehicle.

[0173] The specific details of each module or unit in the package sampling inspection device of the aforementioned logistics sorting center have been described in detail in the corresponding package sampling inspection method of the logistics sorting center, so they will not be repeated here.

[0174] On the other hand, this application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable storage medium carries one or more programs that, when executed by the electronic device, cause the electronic device to perform the methods described in the following embodiments. For example, the electronic device may perform... Figures 2-5 The various steps shown are as follows.

[0175] It should be noted that the computer-readable storage medium disclosed herein may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0176] Figure 7 A schematic diagram of the structure of a computer system suitable for implementing the embodiments of the present disclosure is shown.

[0177] It should be noted that, Figure 7 The computer system 700 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0178] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 702 or programs loaded from storage section 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for system operation. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0179] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 710 as needed so that computer programs read from it can be installed into the storage section 708 as needed.

[0180] In particular, according to embodiments of this disclosure, the processes described below with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by central processing unit (CPU) 701, it performs the various functions defined in the methods and apparatus of this application.

[0181] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0182] It should be noted that although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps, such as omitting certain steps, combining multiple steps into one step, and / or breaking down one step into multiple steps, should all be considered part of this disclosure.

[0183] It should be understood that this disclosure, as disclosed and defined herein, extends to all alternative combinations of two or more individual features mentioned or apparent in the text and / or figures. All these different combinations constitute multiple alternative aspects of this disclosure. The embodiments described in this specification illustrate the best known mode for implementing this disclosure and will enable those skilled in the art to utilize it.

Claims

1. A method for random inspection of parcels in a logistics sorting center, characterized in that, include: The system receives real-time package and loading information uploaded by pickup stations located before the logistics sorting center along the routing route. The package information includes first pickup information. Based on the loading information, a vehicle data pool is constructed for each vehicle, and the package information is stored in the corresponding vehicle data pool until the vehicle data pool reaches the overflow condition, at which point the first package data is obtained. Obtain second pickup information, and based on the second pickup information and the first pickup information in the vehicle data pool, remove the package information corresponding to the second pickup information from the first package data to obtain the second package data; wherein, the second pickup information is used to indicate the inspection-free pickup information in the logistics database; The system separately calculates the total parcel information in the first parcel data and the risk parcel information in the second parcel data; the risk parcel information includes the number of risk parcels, and the total parcel information includes the total number of parcels; based on the comparison result of the proportion of the number of risk parcels in the total number of parcels with a first threshold, it determines whether the corresponding vehicle meets the first sampling inspection condition; based on the comparison result of the number of risk parcels with a second threshold, it determines whether the corresponding vehicle meets the second sampling inspection condition; when a vehicle meets both the first and second sampling inspection conditions, the current vehicle is determined as the target sampling inspection vehicle, and the target sampling inspection vehicle is assigned to the sampling personnel so that the sampling personnel can conduct parcel sampling inspections on the target sampling inspection vehicle.

2. The parcel sampling inspection method for a logistics sorting center according to claim 1, characterized in that, The package information includes waybill attributes. Before obtaining the second package data, the method further includes: Based on the waybill attributes, the parcel information corresponding to the first parcel data and the target waybill attributes is removed; the target waybill attributes include document-type waybills.

3. The parcel sampling inspection method for a logistics sorting center according to claim 1, characterized in that, The acquisition of the second pickup information includes: The second pickup information is determined by using an offline platform based on historical package pickup information; Receive the second collection information sent by the offline platform.

4. The parcel sampling inspection method for a logistics sorting center according to claim 1, characterized in that, The method further includes: For each pickup station in the vehicle data pool, a station data pool is constructed, and the waybill information of each pickup station is stored in the corresponding station data pool; The system collects waybill information from each of the station data pools in the vehicle data pool and sends the waybill information from each collection station to the offline platform, so that the offline platform can determine risk station information based on the waybill information from each collection station.

5. The parcel sampling inspection method for a logistics sorting center according to claim 4, characterized in that, The method further includes: Receive the risk site information sent by the offline platform; Based on the risk site information, the sampling site information is determined; Based on the information from the sampling sites, packages at the logistics sorting center are sampled and inspected.

6. The parcel sampling inspection method for a logistics sorting center according to claim 5, characterized in that, The process of randomly inspecting packages at the logistics sorting center based on the inspection site information includes: Based on the sampling site information, vehicles containing the sampling site information are selected as target sampling vehicles, and packages inside the target sampling vehicles are sampled and inspected. or, Based on the sampling site information, packages inside the target sampling vehicle that correspond to the sampling site information are sampled and inspected.

7. The parcel sampling inspection method for a logistics sorting center according to claim 4, characterized in that, The risk site information is determined based on the collection order information, sampled order information, and over-standard order information of each collection site within the target period.

8. The parcel sampling inspection method for a logistics sorting center according to claim 1, characterized in that, The loading information includes the vehicle's license plate information, and the method further includes: The vehicle data pool corresponding to vehicles with empty license plate information is filtered out.

9. The parcel sampling inspection method for a logistics sorting center according to claim 1, characterized in that, The step of distributing the target inspection vehicle to the inspection personnel so that the inspection personnel can conduct package inspections of the target inspection vehicle includes: Determine the license plate information and departure time information of the target vehicles to be sampled; The license plate information and departure time information of the target inspection vehicle are sent to the sorting center so that the inspection personnel can conduct random package inspections on the vehicles corresponding to the license plate information and departure time information of the target inspection vehicle.

10. A parcel sampling inspection device for a logistics sorting center, characterized in that, include: The first receiving module is used to receive parcel information and loading information uploaded by the pickup station located before the logistics sorting center in the routing line, wherein the parcel information includes the first pickup information. The storage module is used to construct a vehicle data pool for each vehicle based on the loading information, and store the package information in the corresponding vehicle data pool until the vehicle data pool reaches the overflow condition to obtain the first package data. The first rejection module is used to obtain the second pickup information and, based on the second pickup information and the first pickup information in the vehicle data pool, reject the package information in the first package data that corresponds to the second pickup information to obtain the second package data; wherein, the second pickup information is used to indicate the inspection-free pickup information in the logistics database; The sampling inspection module is used to separately count the total package information in the first package data and the risk package information in the second package data; the risk package information includes the number of risk packages, and the total package information includes the total number of packages; in response to the comparison result of the proportion of the number of risk packages in the total number of packages with a first threshold, it determines whether the corresponding vehicle meets the first sampling inspection condition; in response to the comparison result of the number of risk packages with a second threshold, it determines whether the corresponding vehicle meets the second sampling inspection condition; when a vehicle meets both the first sampling inspection condition and the second sampling inspection condition, the current vehicle is determined as the target sampling inspection vehicle, and the target sampling inspection vehicle is assigned to the sampling personnel so that the sampling personnel can conduct package sampling inspections on the target sampling inspection vehicle.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-9.

12. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1-9.

Images