Abnormal express delivery identification method, device, computer equipment and storage medium

Abstract

The present application relates to a method, device, computer equipment and storage medium for identifying abnormal express parcels. The method includes: obtaining scene identifications of the express parcel to be identified in multiple preset abnormal identification scenarios; obtaining corresponding historical duplicate waybill data and real-time waybill data based on the scene identification, and obtaining abnormal risk information of the express parcel to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data; determining the target risk information of the express parcel to be identified based on the abnormal risk information in each of the preset abnormal identification scenarios; and determining the abnormal identification results of the express parcel to be identified based on the target risk information. The use of this method can improve the accuracy of the identification results of the express parcel to be identified, thereby solving the problem of low recognition accuracy of underweight express parcels in traditional identification methods due to the randomness of duplication and the limitations of rules.

Description

Technical Field

[0001] The present application relates to the field of logistics technology, and in particular to a method, device, computer equipment and storage medium for identifying abnormal express shipments. Background Art

[0002] Underweight occurs when the billable weight entered on a shipment is lower than the actual billable weight, with a significant discrepancy. Underweighting can cause a vehicle's actual load to exceed its rated capacity, or even lead to an accident due to overloading. Therefore, identifying underweighted shipments is a crucial aspect of logistics.

[0003] Currently, methods for identifying underweight express parcels include random reweighing on dynamic scales, random spot checks on static scales, and using rules to push waybills of high-risk employees or users to the delivery end. However, due to the randomness of transit reweighing and the limitations of the rules, the limited situations considered have led to the current identification methods reaching a bottleneck in the number and accuracy of identifying underweight express parcels.

[0004] Therefore, the current method for identifying underweight express parcels has the problem of low recognition accuracy. Summary of the Invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for identifying abnormal express parcels to address the technical problem of low recognition accuracy in the above-mentioned method for identifying underweight express parcels.

[0006] A method for identifying abnormal express shipments, the method comprising:

[0007] Obtain scene identifications of the express shipment to be identified in multiple preset abnormal identification scenarios;

[0008] Acquire corresponding historical duplicate waybill data and real-time waybill data according to the scenario identifier, and obtain abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data;

[0009] Determining target risk information of the express shipment to be identified based on the abnormal risk information under each of the preset abnormal identification scenarios;

[0010] Based on the target risk information, an abnormality identification result of the express shipment to be identified is determined.

[0011] In one embodiment, the abnormal risk information includes a scenario risk value and a scenario weight. If the preset abnormal identification scenario is any one of a combination scenario of a receiving employee and a monthly billing user, a combination scenario of a receiving employee and a consignment type, or a combination scenario of a monthly billing user and a consignment type, then the abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios is obtained based on the historical duplicate waybill data and the real-time waybill data, including:

[0012] Based on the historical duplicate waybill data, a duplicate parameter value for the preset abnormality identification scenario is obtained; the duplicate parameter value includes a red check rate, which represents the ratio of the number of express parcels found to be underweight during duplicate checking to the total number of duplicate express parcels;

[0013] According to the red punch rate and the red punch rate threshold, the scenario risk value of the express parcel to be identified is obtained in any one of the combined scenarios of the receiving employee and the monthly settlement user, the combined scenario of the receiving employee and the consignment type, and the combined scenario of the monthly settlement user and the consignment type.

[0014] In one embodiment, if the preset abnormality identification scenario is a record of modification of the billing weight before executing the shipping operation rule, then obtaining abnormality risk information of the express shipment to be identified in each of the preset abnormality identification scenarios based on the historical duplicate waybill data and the real-time waybill data further includes:

[0015] Obtaining the maximum chargeable weight in the modification record before generating the express list of the express shipment to be identified in the real-time waybill data and the list chargeable weight when generating the express list;

[0016] According to the maximum billing weight and the list billing weight, a scenario risk value is obtained in the scenario of modification record of the billing weight of the express shipment to be identified before the execution of the shipping operation rule.

[0017] In one embodiment, if the preset abnormality identification scenario is a waybill of a user who does not implement the shipping operation rules, then obtaining abnormality risk information of the express shipment to be identified in each of the preset abnormality identification scenarios based on the historical duplicate waybill data and the real-time waybill data further includes:

[0018] Determine whether the express parcel to be identified belongs to the waybill of a user who has not implemented the shipping operation rules based on the real-time waybill data, and determine the scenario risk value of the express parcel to be identified in the scenario of the waybill of the user who has not implemented the shipping operation rules based on the identification result.

[0019] In one embodiment, if the preset abnormality identification scenario is visual data from a transit dynamic weighing scale, then obtaining abnormality risk information of the express shipment to be identified in each of the preset abnormality identification scenarios based on the historical weighing waybill data and the real-time waybill data further includes:

[0020] Determining the duplicate weight identifier, duplicate weight, and billing weight of the shipment to be identified from the real-time waybill data;

[0021] According to the duplicate weight mark, the duplicate weight and the invoiced weight, a scenario risk value of the express item to be identified in the scenario of the visual data of the duplicate weight on the transit dynamic scale is obtained.

[0022] In one embodiment, obtaining abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data further includes:

[0023] Obtaining, from the historical duplicate waybill data, duplicate parameter values ​​of the historical duplicate waybill within multiple time intervals under each of the preset abnormality identification scenarios;

[0024] Sort the repeated parameter values ​​in each time interval according to numerical values ​​to obtain a repeated parameter value sequence for each preset abnormality identification scenario;

[0025] The median of each of the repeated parameter value sequences is obtained respectively as the scene weight of the corresponding preset abnormality recognition scene.

[0026] In one embodiment, obtaining the target risk information of the express shipment to be identified based on the abnormal risk information in each of the preset abnormal identification scenarios includes:

[0027] Obtaining the product of the scenario risk value of each of the preset abnormality identification scenarios and the corresponding scenario weight respectively as the scenario risk index value of each of the preset abnormality identification scenarios;

[0028] The cumulative sum of the scenario risk index values ​​of each of the preset abnormality identification scenarios is obtained as the target risk information of the express shipment to be identified.

[0029] In one embodiment, before determining the abnormality identification result of the express shipment to be identified based on the target risk information, the method further includes:

[0030] Obtain duplicate parameter values ​​of duplicate waybills under different target risk information, and obtain the precision and recall rate of duplicates based on the duplicate parameter values;

[0031] Obtaining risk information thresholds corresponding to different target risk information based on the precision rate and the recall rate;

[0032] Determining an abnormality identification result for the express shipment to be identified based on the target risk information includes:

[0033] Obtaining a target risk information threshold corresponding to the target risk information;

[0034] If the target risk information is greater than the target risk information threshold, it is determined that there is an abnormality in the express shipment to be identified.

[0035] An abnormal express delivery identification device, comprising:

[0036] An identification acquisition module is used to obtain the scene identification of the express shipment to be identified in multiple preset abnormal identification scenarios;

[0037] An abnormal risk information acquisition module is used to obtain corresponding historical duplicate waybill data and real-time waybill data according to the scenario identifier, and obtain abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data;

[0038] A target risk information acquisition module is used to determine the target risk information of the express shipment to be identified based on the abnormal risk information under each of the preset abnormal identification scenarios;

[0039] The abnormality identification module is used to determine the abnormality identification result of the express shipment to be identified based on the target risk information.

[0040] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0041] Obtain scene identifications of the express shipment to be identified in multiple preset abnormal identification scenarios;

[0042] Acquire corresponding historical duplicate waybill data and real-time waybill data according to the scenario identifier, and obtain abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data;

[0043] Determining target risk information of the express shipment to be identified based on the abnormal risk information under each of the preset abnormal identification scenarios;

[0044] Based on the target risk information, an abnormality identification result of the express shipment to be identified is determined.

[0045] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0046] Obtain scene identifications of the express shipment to be identified in multiple preset abnormal identification scenarios;

[0047] Acquire corresponding historical duplicate waybill data and real-time waybill data according to the scenario identifier, and obtain abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data;

[0048] Determining target risk information of the express shipment to be identified based on the abnormal risk information under each of the preset abnormal identification scenarios;

[0049] Based on the target risk information, an abnormality identification result of the express shipment to be identified is determined.

[0050] The above-mentioned abnormal express shipment identification method, apparatus, computer equipment, and storage medium obtain scenario identifications for the express shipment to be identified in multiple preset abnormal identification scenarios; obtain corresponding historical duplicate waybill data and real-time waybill data based on the scenario identifications; obtain abnormal risk information for the express shipment to be identified in each preset abnormal identification scenario based on the historical duplicate waybill data and real-time waybill data; determine target risk information for the express shipment to be identified based on the abnormal risk information in each preset abnormal identification scenario; and determine abnormal identification results for the express shipment to be identified based on the target risk information. This method determines multiple abnormal identification scenarios by analyzing and mining the entire life cycle of the express shipment waybill and considering multiple dimensions. It then identifies abnormal risk situations for the express shipment to be identified based on the abnormal risk information of the express shipment to be identified in various abnormal identification scenarios, thereby improving the accuracy of abnormal identification results for the express shipment to be identified, thereby increasing the number of identifications, thereby solving the problem of low accuracy in identifying underweight express shipments in traditional methods due to the randomness of duplicates and the limitations of rules. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 1 is a flow chart of a method for identifying abnormal express shipments in one embodiment;

[0052] Figure 2 Schematic diagram of a flow chart of a scene weight determination step in one embodiment;

[0053] Figure 3 A schematic flow chart of a method for identifying abnormal express shipments in another embodiment;

[0054] Figure 4 This is a structural block diagram of an abnormal express delivery identification device in one embodiment;

[0055] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0057] In one embodiment, Figure 1 As shown, a method for identifying abnormal express shipments is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0058] Step S102: Obtain scene identifications of the express shipment to be identified in multiple preset abnormality identification scenes.

[0059] Among them, the preset abnormal identification scenarios include historical behavior scenarios (i.e. pre-event scenarios, representing historical data of other express parcels) and real-time behavior scenarios (i.e. in-event scenarios, representing the data of the express parcel to be identified).

[0060] Among them, the pre-scenarios include the combination scenario of the receiving employee and the monthly settlement user, the combination scenario of the receiving employee and the type of consignment, and the combination scenario of the monthly settlement user and the type of consignment.

[0061] Among them, the in-process scene represents the modification record of the billing weight before the execution of the shipping operation rules, the waybill of the user who did not execute the shipping operation rules, and the visual data of the transit dynamic weighing.

[0062] The scenario identifier can represent the identifier of the parcel to be identified in each preset abnormality identification scenario, together with its own information. For example, if the parcel to be identified is furniture collected by receiving employee a from monthly settlement account b, then in the combined scenario of the receiving employee and the monthly settlement user, the scenario identifier can be a combination of the receiving employee identifier and the monthly settlement account identifier, i.e., receiving employee a and monthly settlement account b. In the combined scenario of the receiving employee and the type of consignment, the scenario identifier can be a combination of the receiving employee identifier and the type of consignment, i.e., receiving employee a and consigned furniture. In the combined scenario of the monthly settlement user and the type of consignment, the scenario identifier can be a combination of the monthly settlement account identifier and the type of consignment, i.e., monthly settlement account b and consigned furniture.

[0063] Step S104, obtaining corresponding historical duplicate waybill data and real-time waybill data according to the scenario identifier, and obtaining abnormal risk information of the express shipment to be identified in each preset abnormal identification scenario based on the historical duplicate waybill data and the real-time waybill data.

[0064] Among them, abnormal risk information includes scenario risk value and scenario weight.

[0065] The scenario risk value includes a first scenario risk value and a second scenario risk value. The first scenario risk value can be recorded as 1, indicating that the scenario has risk, and the second scenario risk value can be recorded as 0, indicating that the scenario has no risk.

[0066] Among them, the scene weight can represent the relative importance of each abnormal identification scene to the abnormal situation of the express delivery to be identified.

[0067] In a specific implementation, based on the scene identification of the express shipment to be identified in each preset abnormal identification scene, the corresponding historical duplicate waybill data of the recent period (for example, the past week) can be obtained, and the scene risk value of the express shipment to be identified in each pre-event scene can be calculated based on the historical duplicate waybill data. In addition, the real-time waybill data of the express shipment to be identified in the in-event scene, that is, the modification record of the billing weight before the execution of the shipping operation rules, the waybill of the user who did not execute the shipping operation rules, and the visual data of the transit dynamic weighing, can be obtained. The scene risk value of the express shipment to be identified in each in-event scene can be determined based on the real-time waybill data. By obtaining the duplicate parameter values ​​of the historical duplicate waybill data in different time intervals in each preset abnormal identification scene, the duplicate parameter values ​​of each time interval are sorted according to the numerical value to obtain a duplicate parameter value sequence, and the median of the duplicate parameter value sequence of each preset abnormal identification scene is obtained as the scene weight of each preset abnormal identification scene. The risk value of each scene and the scene weight are used as the abnormal risk information of the express shipment to be identified in each preset abnormal identification scene.

[0068] Step S106: Determine the target risk information of the express shipment to be identified based on the abnormal risk information in each preset abnormal identification scenario.

[0069] Furthermore, in one embodiment, the above-mentioned step S106 specifically includes: obtaining the product of the scenario risk value of each preset abnormal identification scenario and the corresponding scenario weight as the scenario risk index value of each preset abnormal identification scenario; obtaining the cumulative sum of the scenario risk index values ​​of each preset abnormal identification scenario as the target risk information of the express delivery to be identified.

[0070] In the specific implementation, the product of the scenario risk value and the scenario weight under each preset abnormal identification scenario can be calculated respectively to obtain the scenario risk index value of each preset abnormal identification scenario, and the cumulative sum of the scenario risk index values ​​of each preset abnormal identification scenario can be calculated as the target risk information of the express delivery to be identified.

[0071] For example, if the scenario risk values ​​under each preset abnormality identification scenario are recorded as x1, x2, x3, x4, x5 and x6 respectively, and the scenario weights under each preset abnormality identification scenario are recorded as c1, c2, c3, c4, c5 and c6, then the target risk information Y of the express shipment to be identified can be expressed as follows:

[0072] Y=c1*x1+c2*x2+c3*x3+c4*x4+c5*x5+c6*x6.

[0073] Step S108: Determine the abnormality identification result of the express shipment to be identified based on the target risk information.

[0074] In the specific implementation, before performing abnormal identification on the express delivery to be identified based on the target risk information, it is also necessary to obtain the target risk information threshold corresponding to the target risk information, compare the target risk information with the target risk information threshold, and determine the abnormal identification result of the express delivery to be identified based on the comparison result.

[0075] Furthermore, step S108 specifically includes: obtaining a target risk information threshold corresponding to the target risk information; if the target risk information is greater than the target risk information threshold, determining that the express shipment to be identified is abnormal.

[0076] Specifically, when the target risk information is greater than the target risk information threshold, it can be determined that there is an abnormality in the express parcel to be identified, that is, the express parcel to be identified may be an underweight express parcel, and then an early warning information of the express parcel to be identified can be generated and sent to the staff's terminal to instruct the staff to review the weight of the express parcel to be identified to confirm whether the weight of the express parcel to be identified is underweight. In this way, it is possible to re-weigh the express parcels whose target risk information is greater than the target risk information from a large number of express parcels, and realize accurate identification of underweight express parcels. This overcomes the defect of the traditional method of randomly selecting express parcels for re-weighing, which is the ineffective work of re-weighing normal express parcels but omitting abnormal express parcels, thereby improving the accuracy of identifying abnormal express parcels.

[0077] In one embodiment, the process of obtaining the risk information threshold includes: obtaining the duplicate parameter values ​​of duplicate waybills under different target risk information, and obtaining the precision and recall rate of the duplicates based on the duplicate parameter values; and obtaining the risk information threshold corresponding to the different target risk information based on the precision and recall rate.

[0078] Among them, the repetition parameter values ​​include the number of hot stamping parts and the hot stamping rate.

[0079] Among them, the number of red-punched parts can indicate the number of waybills that were found to have under-counted the billable weight after re-weighing, and the under-counted billable weight and freight were red-punched.

[0080] The "red check rate" can be expressed as the ratio of the number of red check items to the number of re-weighed items, and can be expressed as: (number of red check items / number of re-weighed items) * 100%. The number of re-weighed items refers to the number of waybills that have undergone weight verification.

[0081] Specifically, the risk information threshold Y0 can be determined by calculating the number and rate of red-punched duplicated waybills under different target risk information thresholds Y based on the duplication results data from the past month. The threshold Y0 of Y can be selected based on the combined number and rate of red-punched duplicated waybills. Under the conditions of ensuring both the accuracy of duplicated and the recall rate of undercounted waybills, the F1 value can be used as the risk information threshold because it balances the accuracy and recall rates. The confusion matrix formed by each indicator in the F1 value is shown in Table 1 below:

[0082]

[0083] Table 1

[0084] TP means the prediction was 1 and the actual value was not 1, which is a correct prediction. FP means the prediction was 1 and the actual value was 0, which is a wrong prediction. FN means the prediction was 0 and the actual value was 1, which is a wrong prediction. TN means the prediction was 0 and the actual value was 0, which is a correct prediction.

[0085] The accuracy can be expressed as: The recall rate can be expressed as: Then the F1 value is

[0086] In the above-mentioned abnormal express shipment identification method, scenario identifiers for the express shipment to be identified under multiple preset abnormal identification scenarios are obtained; corresponding historical duplicate waybill data and real-time waybill data are obtained based on the scenario identifiers; abnormal risk information of the express shipment to be identified under each preset abnormal identification scenario is obtained based on the historical duplicate waybill data and real-time waybill data; target risk information of the express shipment to be identified is determined based on the abnormal risk information under each preset abnormal identification scenario; and abnormal identification results for the express shipment to be identified are determined based on the target risk information. This method determines multiple abnormal identification scenarios by analyzing and mining the entire life cycle of the express shipment waybill and considering multiple dimensions. It then identifies abnormal risk situations of the express shipment to be identified based on the abnormal risk information of the express shipment to be identified under various abnormal identification scenarios, thereby improving the accuracy of abnormal identification results for the express shipment to be identified and thereby increasing the number of identifications. This solves the problem of low accuracy in identifying underweight express shipments in traditional methods due to the randomness of duplicates and the limitations of rules.

[0087] In one embodiment, if the preset abnormal identification scenario is any one of the combination scenario of the receiving employee and the monthly settlement user, the combination scenario of the receiving employee and the type of consignment, and the combination scenario of the monthly settlement user and the type of consignment, then the above-mentioned step S104 includes: obtaining the duplicate parameter value under the preset abnormal identification scenario based on the historical duplicate waybill data; the duplicate parameter value includes the red check rate, which represents the ratio of the number of express parcels found to be underweight during duplicate checking to the total number of duplicate express parcels; according to the red check rate and the red check rate threshold, obtaining the scenario risk value of the express parcel to be identified in any one of the scenarios of the combination scenario of the receiving employee and the monthly settlement user, the combination scenario of the receiving employee and the type of consignment, and the combination scenario of the monthly settlement user and the type of consignment.

[0088] Among them, the re-weighing parameter values ​​include the number of re-weighed parts, the number of red-punched parts and the red-punching rate.

[0089] In the specific implementation, taking the combination scenario of the preset abnormal identification scenario of the receiving employee and the monthly settlement user as an example, after obtaining the receiving employee identification and the monthly settlement user identification corresponding to the express to be identified as the scenario identification, the historical duplicate waybill data of the recent period (such as within the past week) corresponding to the scenario identification can be obtained. For example, the historical duplicate waybill data of the receiving employee a and the monthly settlement account b in the past week are obtained. Based on the historical duplicate waybill data, the number of duplicate items, the number of red-checked items, and the red-check rate in the combination scenario of the receiving employee and the monthly settlement user are calculated. The red-check rate is compared with the red-check rate threshold. If the red-check rate is greater than or equal to the red-check rate threshold, the first scenario risk value is obtained, and the first scenario risk value is 1; if the red-check rate is less than the red-check rate threshold, the second scenario risk value is obtained, and the second scenario risk value is 0.

[0090] For example, if the red-check rate is greater than or equal to the red-check rate threshold of 50%, the scenario risk value x1 in the combined scenario of the receiving employee a and the monthly settlement user b is recorded as 1, recorded as x1=1; otherwise, it is recorded as x1=0. That is, if half of all the duplicate waybills of the receiving employee a and the monthly settlement user b are found to be underweight, then all the receiving waybills in this combined scenario are marked as x1=1.

[0091] Similarly, according to the above method, the scenario risk values ​​for the combination scenario of the receiving employee and the type of consignment, and the combination scenario of the monthly settlement user and the type of consignment can be obtained, which are recorded as x2 and x3 respectively.

[0092] In this embodiment, by analyzing historical waybill information, it is determined that in addition to human factors, underweight waybills are also highly correlated with the type of consignment. Finally, three dimensions are selected: the combination scenario of receiving employees and monthly settlement users, the combination scenario of receiving employees and consignment types, and the combination scenario of monthly settlement users and consignment types. By analyzing the historical duplicate waybill data in the recent period under each dimension, the abnormal risk information of any express delivery under each dimension is determined, so as to determine the target risk information of the express delivery to be identified based on each abnormal risk information, thereby determining the risk situation of the express delivery to be identified, and determining whether the weight of the express delivery to be identified needs to be reviewed based on the identification results.

[0093] In one embodiment, if the preset abnormal identification scenario is the modification record of the billing weight before executing the shipping operation rules, the above-mentioned step S104 also includes: obtaining the maximum billing weight in the modification record before generating the express list of the express to be identified in the real-time waybill data and the list billing weight when generating the express list; based on the maximum billing weight and the list billing weight, obtaining the scenario risk value in the scenario of the modification record of the billing weight of the express to be identified before executing the shipping operation rules.

[0094] In a specific implementation, when receiving employees perform receiving operations on the bar gun, there is embedded data to record the receiving employees' operations during each receiving operation. Therefore, the bar gun can obtain the weight modification record before generating the express list of the express shipment to be identified. From this weight modification record, the maximum billable weight and the list billing weight when the express list of the express shipment to be identified are determined. Based on the maximum billable weight and the list billing weight, the scenario risk value under the abnormal identification scenario of the billing weight modification record before executing the shipping operation rules is determined. More specifically, if the maximum billable weight is greater than the list billing weight, the first scenario risk value is obtained; if the maximum billable weight is less than or equal to the list billing weight, the second scenario risk value is obtained.

[0095] For example, if the maximum billing weight before generating the express list of the express to be identified is recorded as w1, and the billing weight of the uploaded list is w2, the difference between the maximum billing weight and the billing weight of the list is calculated as w1-w2. If w1-w2>0, the scenario risk value of the abnormal identification scenario of the modification record of the billing weight before executing the mailing operation rules (recorded as x4) is recorded as x4=1, otherwise, it is recorded as x4=0.

[0096] In this embodiment, by comparing the maximum billing weight in the modification record before generating the express list of the express to be identified with the billing weight of the list when generating the express list, the scenario risk value of the abnormal identification scenario of the modification record of the billing weight of the express to be identified before executing the mailing operation rules is determined, so as to identify the risk situation of the express to be identified based on the scenario risk value and determine whether the weight of the express to be identified needs to be reviewed.

[0097] In one embodiment, if the preset abnormal identification scenario is the waybill of a user who has not executed the shipping operation rules, the above-mentioned step S104 also includes: determining whether the express parcel to be identified belongs to the waybill of a user who has not executed the shipping operation rules based on the real-time waybill data, and determining the scenario risk value of the express parcel to be identified in the scenario of the waybill of a user who has not executed the shipping operation rules based on the identification result.

[0098] In a specific implementation, since some users can directly send the express to the designated transfer station after executing the shipping operation rules (such as operation 50), and through analysis of historical waybills, failure to execute the shipping operation according to the shipping operation rules is a high-risk scenario that affects the under-weighting of the express, therefore, this embodiment uses this scenario as a scenario for identifying abnormal express shipments to be identified, and determines whether the express shipment to be identified belongs to the waybill of the user who has not executed the shipping operation rules, and determines the scenario risk value of the express shipment to be identified in this scenario. More specifically, if it is determined from the real-time waybill data that the express shipment to be identified belongs to the waybill of the user who has not executed the shipping operation rules, the first scenario risk value is obtained; if it is determined from the real-time waybill data that the express shipment to be identified does not belong to the waybill of the user who has not executed the shipping operation rules, the second scenario risk value is obtained.

[0099] For example, if the scenario risk value of the abnormal identification scenario of the waybill of the user who did not implement the shipping operation rules is x5, then if it is determined that the express delivery to be identified belongs to the waybill of the user who did not implement the shipping operation rules, then x5=1, otherwise, x5=0.

[0100] In this embodiment, real-time waybill data is used to determine whether the express parcel to be identified belongs to the waybill of a user who has not implemented the shipping operation rules, thereby obtaining the scenario risk value of the express parcel to be identified in the abnormal identification scenario of the waybill of a user who has not implemented the shipping operation rules, so as to identify the risk situation of the express parcel to be identified based on the scenario risk value and determine whether the weight of the express parcel to be identified needs to be reviewed.

[0101] In one embodiment, if the preset abnormal identification scenario is the visual data of the dynamic reweighing on the transit scale, the above-mentioned step S104 also includes: determining the reweighing mark, reweighing weight and the list billing weight of the express to be identified from the real-time waybill data when generating the express list; according to the reweighing mark, reweighing weight and list billing weight, obtaining the scenario risk value of the express to be identified in the scenario of the visual data of the dynamic reweighing on the transit scale.

[0102] Among them, the double-weighing mark includes the double-weighing of a single piece on a dynamic scale and the double-weighing of non-single piece on a dynamic scale (such as the double-weighing on a static scale or the double-weighing of multiple pieces on a dynamic scale).

[0103] In a specific implementation, as parcels flow through the transit yard, some parcels on the waybill are reweighed using static and dynamic scales. The reweighed data from the dynamic scale is further visually filtered to determine whether multiple shipments have been weighed. Therefore, the visual results from the dynamic scale can be used to incorporate the visual data of single parcels that have passed through the dynamic scale into the parcel anomaly identification scenario. Furthermore, the real-time waybill data can be used to determine whether the parcel to be identified is a single parcel that has been reweighed on the dynamic scale. The reweighed weight from the dynamic scale is then obtained, along with the billing weight from the last parcel manifest before the reweighing, to determine whether the reweighed weight exceeds the billing weight. If the parcel to be identified is determined to be a single parcel that has been reweighed on the dynamic scale, and the reweighed weight from the dynamic scale is greater than the billing weight used when the parcel manifest was generated, a first scenario risk value is obtained. If the real-time waybill data determines that the parcel to be identified is not a single parcel that has been reweighed on the dynamic scale, and / or the reweighed weight from the dynamic scale is less than or equal to the billing weight used when the parcel manifest was generated, a second scenario risk value is obtained.

[0104] For example, the scenario risk value for whether a single piece was reweighed on a dynamic scale can be recorded as x6, and the scenario risk value corresponding to the comparison result of the reweighed weight (recorded as w3) and the invoiced weight (recorded as w4) can be recorded as x7. If the parcel to be identified is a single piece reweighed on a dynamic scale, x6 = 1; otherwise, x6 = 0. Calculate the difference w3-w4 between the reweighed weight w3 and the invoiced weight w4. If w3-w4>0, then x7 = 1; otherwise, x7 = 0.

[0105] Therefore, in combination with the above embodiment, the relationship formula of the target risk information Y of the express shipment to be identified can be modified as follows:

[0106] Y=c1*x1+c2*x2+c3*x3+c4*x4+c5*x5+c6*x6*x7.

[0107] In this embodiment, the duplicate mark, duplicate weight and billing weight of the express parcel to be identified are determined through real-time waybill data, and then the scene risk value of the visual data of the dynamic duplicate weight of the express parcel to be identified in the abnormal identification scenario is determined, so as to identify the risk situation of the express parcel to be identified based on the scene risk value and determine whether the weight of the express parcel to be identified needs to be reviewed.

[0108] In one embodiment, Figure 2 As shown, the above step S104 also includes:

[0109] Step S202: obtaining duplicate parameter values ​​of historical duplicate waybills within multiple time intervals under various preset abnormality recognition scenarios from historical duplicate waybill data;

[0110] Step S204: sorting the repeated parameter values ​​of each time interval according to the magnitude of the values ​​to obtain a repeated parameter value sequence for each preset abnormality recognition scenario;

[0111] In step S206 , the median of each repeated parameter value sequence is obtained as the scene weight of the corresponding preset abnormality recognition scene.

[0112] In the specific implementation, after determining the scenario risk value of each preset abnormal identification scenario, the duplicate waybill data of the recent time period (for example, within the last month) is obtained, and the recent time period is divided into multiple time intervals. For example, in units of days, each day is regarded as a time interval, and the number of duplicate pieces, the number of red-punched pieces and the red-punch rate of the historical duplicate waybills in each day under each preset abnormal identification scenario are calculated. The red-punch rate of each day is sorted according to the numerical value to obtain the red-punch rate sequence, and the median of the red-punch rate sequence is obtained as the scenario weight of the corresponding preset abnormal identification scenario.

[0113] In this embodiment, by using the median of the repeated parameter value sequence as the scene weight of the abnormal identification scene, it is not affected by the extreme red burst rate value, thereby improving the accuracy of the determined scene weight, so as to further improve the accuracy of the identification result when determining the risk situation of the express delivery to be identified based on the scene weight.

[0114] In another embodiment, Figure 3 As shown, a method for identifying abnormal express shipments is provided, and the specific process of the method includes:

[0115] Determination of scenario risk value for ex ante scenarios:

[0116] (1) First, determine the scene identification of the express parcel to be identified in the combination scenario of the receiving employee and the monthly settlement user, the combination scenario of the receiving employee and the type of consignment, and the combination scenario of the monthly settlement user and the type of consignment.

[0117] (2) According to the scenario identifier, the duplicate waybill data in the most recent time period (such as the most recent week) is obtained, the red rush rate under each combination scenario is calculated, and it is determined whether the red rush rate is greater than or equal to the red rush rate threshold. If so, the scenario risk value xi (i = 1, 2, 3) is recorded as 1; otherwise, the scenario risk value xi is recorded as 0.

[0118] Determination of the scenario risk value for the in-process scenario:

[0119] (1) Obtain real-time waybill data. For scenarios where the billing weight is modified before executing the shipping operation rules, the maximum billing weight in the weight modification record (record Figure 3 w1) and the billing weight when generating the bill (i.e. Figure 3Subtract w2) from the difference to obtain the difference w3. If w3>0, the scenario risk value of the modification record of the billing weight before executing the shipping operation rule (denoted as x4) is recorded as 1; otherwise, the scenario risk value of the scenario is recorded as 0.

[0120] (2) For the scenario of the waybill of the user who does not implement the shipping operation rules, it is determined whether the express parcel to be identified belongs to the waybill of the user who does not implement the shipping operation rules. If so, the scenario risk value of the waybill of the user who does not implement the shipping operation rules (denoted as x5) is recorded as 1; otherwise, the scenario risk value of the scenario is recorded as 0.

[0121] (3) For the scenario of visual data of reweighing on a dynamic scale during transit, first determine whether the parcel to be identified is a single piece reweighed on a dynamic scale (record this scenario as x6). If so, record x6 as 1; otherwise, record x6 as 0. Next, calculate the difference between the reweighed weight (recorded as w4) and the invoice billing weight before reweighing (recorded as w5), and determine whether w5 is greater than 0 (record this scenario as x7). If w5>0, record x7 as 1; otherwise, record x7 as 0.

[0122] Thus, the scenario risk values ​​under 6 preset abnormal recognition scenarios are obtained. Further, the scenario weight of each scenario is determined. Specifically, by obtaining the historical duplicate waybill data of each abnormal recognition scenario, the daily red rush rate of each abnormal recognition scenario is calculated according to the mark xi in the duplicate waybill data, and the daily red rush rate is formed into a red rush rate sequence according to the numerical size. The median of the red rush rate sequence of each abnormal recognition scenario is used as the scenario weight cj (j = 1, 2, ...6) of each abnormal recognition scenario.

[0123] After determining the scenario risk value and scenario weight of the express shipment to be identified in each abnormal identification scenario, the target risk information Y of the express shipment to be identified can be calculated as:

[0124] Y=c1*x1+c2*x2+c3*x3+c4*x4+c5*x5+c6*x6*x7.

[0125] Using the duplicate waybill data of the most recent time period, calculate the number and rate of duplicate waybills under different Y values. Select the threshold value Y0 of Y based on the number and rate of duplicate waybills. Finally, compare the Y value with the threshold value Y0. If Y>Y0, it is determined that there is an abnormality in the express shipment to be identified, and there may be a problem of under-counting. The weight of the express shipment to be identified needs to be rechecked.

[0126] The abnormal express shipment identification method provided in this embodiment not only takes into account the three combined features under human factors, but also fully considers the real-time data of each link in the entire life cycle of the waybill. The express shipment to be identified is identified according to the scenario risk value and scenario weight of the express shipment to be identified in six scenarios, thereby effectively improving the recognition accuracy rate. It can effectively help logistics companies recover cost losses caused by under-weighing, and enable employees to improve the hit rate of double-weighing while doing the same workload, increase personal income, and mobilize employees' enthusiasm for double-weighing.

[0127] It should be understood that although Figure 1-3 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1-3 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The order of execution of these steps or stages is not necessarily one by one, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0128] In one embodiment, Figure 4 As shown, an abnormal express delivery identification device is provided, including: an identification acquisition module 402, an abnormal risk information acquisition module 404, a target risk information acquisition module 406 and an abnormality identification module 408, wherein:

[0129] The identification acquisition module 402 is used to obtain the scene identification of the express delivery to be identified in multiple preset abnormal identification scenes;

[0130] Abnormal risk information acquisition module 404 is used to obtain corresponding historical duplicate waybill data and real-time waybill data according to the scenario identifier, and obtain abnormal risk information of the express shipment to be identified in each preset abnormal identification scenario based on the historical duplicate waybill data and the real-time waybill data;

[0131] Target risk information acquisition module 406, used to determine target risk information of the express shipment to be identified based on the abnormal risk information in each preset abnormal identification scenario;

[0132] The abnormality identification module 408 is used to determine the abnormality identification result of the express shipment to be identified based on the target risk information.

[0133] In one embodiment, the abnormal risk information includes a scenario risk value and a scenario weight. If the preset abnormal identification scenario is any one of the combination scenario of the receiving employee and the monthly settlement user, the combination scenario of the receiving employee and the consignment type, and the combination scenario of the monthly settlement user and the consignment type, then the above-mentioned abnormal risk information acquisition module 404 is specifically used to obtain the duplicate parameter value under the preset abnormal identification scenario based on the historical duplicate waybill data; the duplicate parameter value includes the red-punch rate, which represents the ratio of the amount of express parcels found to be underweight in duplicate to the total amount of duplicate express parcels; based on the red-punch rate and the red-punch rate threshold, the scenario risk value of the express parcel to be identified in any one of the scenarios of the combination scenario of the receiving employee and the monthly settlement user, the combination scenario of the receiving employee and the consignment type, and the combination scenario of the monthly settlement user and the consignment type is obtained.

[0134] In one embodiment, if the preset abnormal identification scenario is the modification record of the billing weight before executing the mailing operation rules, the above-mentioned abnormal risk information acquisition module 404 is specifically used to obtain the maximum billing weight in the modification record before generating the express list of the express to be identified in the real-time waybill data and the list billing weight when generating the express list; based on the maximum billing weight and the list billing weight, the scenario risk value is obtained in the scenario of the modification record of the billing weight of the express to be identified before executing the mailing operation rules.

[0135] In one embodiment, if the preset abnormal identification scenario is the waybill of a user who has not executed the shipping operation rules, the above-mentioned abnormal risk information acquisition module 404 is also used to determine whether the express parcel to be identified belongs to the waybill of a user who has not executed the shipping operation rules based on the real-time waybill data, and determine the scenario risk value of the express parcel to be identified in the scenario of the waybill of a user who has not executed the shipping operation rules based on the identification result.

[0136] In one embodiment, if the preset abnormal identification scenario is the visual data of the dynamic reweighing on the transit scale, the above-mentioned abnormal risk information acquisition module 404 is also used to determine the reweighing mark, reweighing weight and the list billing weight of the express to be identified from the real-time waybill data when generating the express list; based on the reweighing mark, reweighing weight and list billing weight, the scenario risk value of the express to be identified in the scenario of the visual data of the dynamic reweighing on the transit scale is obtained.

[0137] In one embodiment, the above-mentioned abnormal risk information acquisition module 404 is also used to obtain the duplicate parameter values ​​of historical duplicate waybills in multiple time intervals under each preset abnormal identification scenario from the historical duplicate waybill data; sort the duplicate parameter values ​​of each time interval according to the numerical value to obtain the duplicate parameter value sequence under each preset abnormal identification scenario; obtain the median of each duplicate parameter value sequence as the scenario weight of the corresponding preset abnormal identification scenario.

[0138] In one embodiment, the above-mentioned target risk information acquisition module 406 is specifically used to obtain the product of the scenario risk value of each preset abnormal identification scenario and the corresponding scenario weight, as the scenario risk index value of each preset abnormal identification scenario; obtain the cumulative sum of the scenario risk index values ​​of each preset abnormal identification scenario, as the target risk information of the express delivery to be identified.

[0139] In one embodiment, the apparatus further comprises:

[0140] The risk information threshold determination module is used to obtain the duplicate parameter values ​​of the duplicate waybills corresponding to different target risk information, and obtain the precision and recall rate of the duplicates based on the duplicate parameter values; based on the precision and recall rate, the risk information threshold values ​​corresponding to different target risk information are obtained;

[0141] The above-mentioned abnormality identification module 408 is specifically used to obtain the target risk information threshold corresponding to the target risk information; if the target risk information is greater than the target risk information threshold, it is determined that there is an abnormality in the express delivery to be identified.

[0142] It should be noted that the abnormal express parcel identification device of the present application corresponds one-to-one to the abnormal express parcel identification method of the present application. The technical features and beneficial effects described in the above-mentioned embodiment of the abnormal express parcel identification method are applicable to the embodiment of the abnormal express parcel identification device. For specific contents, please refer to the description in the embodiment of the method of the present application. No further details will be given here. This is hereby declared.

[0143] Furthermore, each module in the aforementioned abnormal shipment identification device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor within a computer device in the form of hardware, or may be stored in a computer device memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0144] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an abnormal express delivery identification method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0145] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0146] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0147] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0148] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0149] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0150] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for identifying abnormal express shipments, characterized in that: The method comprises: Obtaining scenario identifiers for the parcel to be identified under multiple preset anomaly identification scenarios; the preset anomaly identification scenarios include historical behavior scenarios and real-time behavior scenarios. The historical behavior scenarios represent scenarios related to historical data of other parcels, including scenarios combining recipient employees and monthly billing users, scenarios combining recipient employees and consignment types, and scenarios combining monthly billing users and consignment types. The real-time behavior scenarios represent scenarios related to the data of the parcel to be identified, including modification records of the billing weight before executing the shipping operation rules, waybills of users who did not execute the shipping operation rules, and visual data of the transit dynamic reweight. Acquire corresponding historical duplicate waybill data and real-time waybill data according to the scenario identifier, and obtain abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data; the abnormal risk information includes a scenario risk value and a scenario weight; Obtaining the product of the scenario risk value and the corresponding scenario weight in the abnormal risk information of each of the preset abnormal identification scenarios as the scenario risk index value of each of the preset abnormal identification scenarios, and determining the cumulative sum of the scenario risk index values ​​as the target risk information of the express shipment to be identified; Based on the target risk information, an abnormality identification result of the express shipment to be identified is determined.

2. The method according to claim 1, characterized in that The step of obtaining abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data includes: Based on the historical duplicate waybill data, a duplicate parameter value for the preset abnormality identification scenario is obtained; the duplicate parameter value includes a red check rate, which represents the ratio of the number of express parcels found to be underweight during duplicate checking to the total number of duplicate express parcels; According to the red punch rate and the red punch rate threshold, the scenario risk value of the express parcel to be identified is obtained in any one of the combined scenarios of the receiving employee and the monthly settlement user, the combined scenario of the receiving employee and the consignment type, and the combined scenario of the monthly settlement user and the consignment type.

3. The method according to claim 1, characterized in that The step of obtaining abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data further includes: Obtaining the maximum chargeable weight in the modification record before generating the express list of the express shipment to be identified in the real-time waybill data and the list chargeable weight when generating the express list; According to the maximum billing weight and the list billing weight, a scenario risk value is obtained in the scenario of modification record of the billing weight of the express shipment to be identified before the execution of the shipping operation rule.

4. The method according to claim 1, wherein The step of obtaining abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data further includes: Determine whether the express parcel to be identified belongs to the waybill of a user who has not implemented the shipping operation rules based on the real-time waybill data, and determine the scenario risk value of the express parcel to be identified in the scenario of the waybill of the user who has not implemented the shipping operation rules based on the identification result.

5. The method according to claim 1, wherein The step of obtaining abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data further includes: Determining the duplicate weight identifier, duplicate weight, and billing weight of the shipment to be identified from the real-time waybill data; According to the duplicate weight mark, the duplicate weight and the invoiced weight, a scenario risk value of the express item to be identified in the scenario of the visual data of the duplicate weight on the transit dynamic scale is obtained.

6. The method according to any one of claims 1 to 5, characterized in that The step of obtaining abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data further includes: Obtaining, from the historical duplicate waybill data, duplicate parameter values ​​for the historical duplicate waybill within multiple time intervals for each of the preset anomaly identification scenarios; the duplicate parameter values ​​include a red check rate, which represents the ratio of the number of parcels found to be undercounted during the duplicate check to the total number of duplicate parcels; Sort the repeated parameter values ​​in each time interval according to numerical values ​​to obtain a repeated parameter value sequence for each preset abnormality identification scenario; The median of each of the repeated parameter value sequences is obtained respectively as the scene weight of the corresponding preset abnormality recognition scene.

7. The method according to claim 1, characterized in that Before determining an abnormality identification result for the express shipment to be identified based on the target risk information, the method further includes: Obtain duplicate parameter values ​​for duplicate waybills corresponding to different target risk information, and calculate duplicate precision and recall rates based on the duplicate parameter values; the duplicate parameter values ​​include a red-check rate, which represents the ratio of the number of parcels found to be undercounted during re-checking to the total number of duplicate parcels; Obtaining risk information thresholds corresponding to different target risk information based on the precision rate and the recall rate; Determining an abnormality identification result for the express shipment to be identified based on the target risk information includes: Obtaining a target risk information threshold corresponding to the target risk information; If the target risk information is greater than the target risk information threshold, it is determined that there is an abnormality in the express shipment to be identified.

8. An abnormal express delivery identification device, characterized in that: The device comprises: An identification acquisition module is used to obtain scenario identifications for the express shipment to be identified under multiple preset abnormality identification scenarios; the preset abnormality identification scenarios include historical behavior scenarios and real-time behavior scenarios. The historical behavior scenarios represent scenarios related to historical data of other express shipments, including scenarios combining recipient employees and monthly billing users, scenarios combining recipient employees and consignment types, and scenarios combining monthly billing users and consignment types. The real-time behavior scenarios represent scenarios related to the data of the express shipment to be identified, including modification records of the billing weight before executing the shipping operation rules, waybills of users who did not execute the shipping operation rules, and visual data of the transit dynamic weighing; An abnormal risk information acquisition module is used to obtain corresponding historical duplicate waybill data and real-time waybill data according to the scenario identifier, and obtain abnormal risk information of the express shipment to be identified in each of the preset abnormal identification scenarios based on the historical duplicate waybill data and the real-time waybill data; the abnormal risk information includes a scenario risk value and a scenario weight; a target risk information acquisition module, configured to respectively obtain the product of the scenario risk value and the corresponding scenario weight in the abnormal risk information of each of the preset abnormal identification scenarios as the scenario risk index value of each of the preset abnormal identification scenarios, and to determine the cumulative sum of the scenario risk index values ​​as the target risk information of the express shipment to be identified; The abnormality identification module is used to determine the abnormality identification result of the express shipment to be identified based on the target risk information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images