Detection Method, Device, Equipment and Storage Medium for Abnormal Express Delivery Weight

Abstract

The present invention relates to the field of detection, and discloses a method, device, equipment and storage medium for detecting abnormal weight of express parcels, which are used to solve the problems of low detection efficiency and low detection accuracy for express parcels with abnormal weight in the prior art. The method includes: obtaining historical weight data of express parcels in the to-be-weighed sequence, and calculating an abnormal judgment threshold according to the historical weight data; judging whether an express parcel is marked as suspected of having abnormal weight; if it is not marked as suspected of having abnormal weight, weighing the express parcel that is not marked as suspected of having abnormal weight to obtain a first real-time weight and judging whether it exceeds the abnormal judgment threshold. If it exceeds, mark the express parcel as suspected of having abnormal weight, and re-add the express parcel to the weighing sequence; if the express parcel has been marked as suspected of having abnormal weight, weighing the express parcel that is marked as suspected of having abnormal weight to obtain a second real-time weight and judging whether it exceeds the abnormal judgment threshold. If it exceeds, mark the express parcel as an express parcel with abnormal weight.

Description

Technical Field

[0001] The present invention relates to the field of detection, and particularly to a method, device, equipment and storage medium for detecting abnormal weight of express parcels. Background Art

[0002] The logistics and express delivery industry requires as accurate collection as possible of the weight values of each express parcel. The weight of the express parcel is an important indicator for measuring whether the goods are damaged, reduced or missing, and the freight of the goods is also settled according to the weight of the express parcel. At present, both the network points and the sorting centers will weigh the express parcels multiple times. When weighing the express parcels, mechanical equipment is generally used to move the goods onto the weighing platform, and the goods are moved away after weighing.

[0003] In the existing technology, there may be deviations in the multiple weight values measured for the express parcels, and manual operations are required to perform repeated weight detections on the express parcels with abnormal weights. There is no automatic verification function for the express parcels with abnormal weights, resulting in low detection efficiency and detection accuracy for the express parcels with abnormal weights. Summary of the Invention

[0004] The main object of the present invention is to solve the problem of low detection efficiency and detection accuracy for express parcels with abnormal weights in the existing technology.

[0005] The first aspect of the present invention provides a method for detecting abnormal weight of express parcels, including: obtaining historical weight data of the express parcels in the to-be-weighed sequence, and calculating an abnormal judgment threshold according to the historical weight data; judging whether the express parcel is marked as suspected of having abnormal weight; if the express parcel is not marked as suspected of having abnormal weight, weighing the express parcel that is not marked as suspected of having abnormal weight to obtain a first real-time weight, and judging whether the first real-time weight exceeds the abnormal judgment threshold. If it exceeds the abnormal judgment threshold, marking the express parcel as suspected of having abnormal weight, and re-adding the express parcel to the weighing sequence; if the express parcel has been marked as suspected of having abnormal weight, weighing the express parcel that is marked as suspected of having abnormal weight to obtain a second real-time weight, and judging whether the second real-time weight exceeds the abnormal judgment threshold. If it exceeds the abnormal judgment threshold, marking the express parcel as an express parcel with abnormal weight.

[0006] Optionally, in the first implementation manner of the first aspect of the present invention, the historical weight data includes the first sorting weight data of the express at the sorting node before the current sorting node and / or the second sorting weight data of the express at the current sorting point. Obtaining the historical weight data of the express in the to-be-weighed sequence and calculating an abnormal judgment threshold based on the historical weight data includes: identifying whether there is second sorting weight data of the express at the current sorting node; if not, obtaining the first sorting weight data of the express at the sorting node before the current sorting point, and calculating a first abnormal judgment threshold based on the first sorting weight data; if so, obtaining the second sorting weight data of the express at the current sorting point and the first sorting weight data of the express at the sorting node before the current sorting point, and calculating a second abnormal judgment threshold based on the first sorting weight data and the second sorting weight data.

[0007] Optionally, in the second implementation manner of the first aspect of the present invention, calculating the first abnormal judgment threshold based on the first sorting weight data includes: removing invalid data values in the first sorting weight data according to a preset invalid data value removal rule to obtain first valid historical weight data; sorting the first valid historical weight data to obtain a first valid historical weight sequence; screening the first valid historical weight data in the first valid historical weight sequence according to a preset index screening rule to obtain first weight index data; calculating a first abnormal judgment threshold based on the first weight index data according to a preset threshold calculation rule.

[0008] Optionally, in the third implementation manner of the first aspect of the present invention, calculating the second abnormal judgment threshold based on the first sorting weight data and the second sorting weight data includes: removing invalid data values in the first sorting weight data and the second sorting weight data according to a preset invalid data value removal rule to obtain second valid historical weight data; sorting the second valid historical weight data to obtain a second valid historical weight sequence; screening the second valid historical weight data in the second valid historical weight sequence according to a preset index screening rule to obtain second weight index data; calculating a second abnormal judgment threshold based on the second weight index data according to a preset threshold calculation rule.

[0009] Optionally, in the fourth implementation manner of the first aspect of the present invention, the invalid data values include null values and gross error values. The step of removing the invalid data values from the first sorting weight data and the second sorting weight data according to the preset invalid data value removal rule to obtain the second valid historical weight data includes: detecting the null values in the first sorting weight data and the second sorting weight data, removing the null values to obtain cleaned data; calculating the arithmetic mean of the cleaned data, and calculating the standard deviation according to Bessel's formula; removing the gross error values in the cleaned data according to the Pauta criterion to obtain the second valid historical weight data.

[0010] Optionally, in the fifth implementation manner of the first aspect of the present invention, the step of screening the second valid historical weight data in the second valid historical weight sequence according to the preset index screening rule to obtain the second weight index data includes: extracting the maximum weight data value and the adjacent weight data value of the maximum weight data value in the second valid historical weight sequence according to the sorting order in the second valid historical weight sequence; judging whether the difference between the maximum weight data value and the adjacent weight data value is greater than a preset screening threshold; if the difference is greater than the preset screening threshold, removing the maximum weight data value from the second valid historical weight sequence; if the difference is not greater than the preset screening threshold, using the maximum weight data value as the second weight index data.

[0011] Optionally, in the sixth implementation manner of the first aspect of the present invention, after labeling the express delivery as an express delivery with abnormal weight, it further includes: extracting the express delivery number of the express delivery with abnormal weight; generating a record of the express delivery with abnormal weight according to the express delivery number, and uploading the record of the express delivery with abnormal weight to the express delivery management system.

[0012] The second aspect of the present invention provides a detection device for abnormal weight of express delivery, including: an acquisition module, configured to acquire the historical weight data of the express delivery in the to-be-weighed sequence and calculate an abnormal judgment threshold according to the historical weight data; an abnormal judgment module, configured to judge whether the express delivery is labeled as suspected abnormal weight; a first weighing module, configured to, if the express delivery is not labeled as suspected abnormal weight, weigh the express delivery that is not labeled as suspected abnormal weight to obtain a first real-time weight, judge whether the first real-time weight exceeds the abnormal judgment threshold, and if it exceeds the abnormal judgment threshold, label the express delivery as suspected abnormal weight and add the express delivery back to the weighing sequence; a second weighing module, configured to, if the express delivery is already labeled as suspected abnormal weight, weigh the express delivery that is labeled as suspected abnormal weight to obtain a second real-time weight, judge whether the second real-time weight exceeds the abnormal judgment threshold, and if it exceeds the abnormal judgment threshold, label the express delivery as an express delivery with abnormal weight.

[0013] Optionally, in the first implementation manner of the second aspect of the present invention, the obtaining module includes: a data recognition unit, configured to recognize whether there is second sorting weight data of the express item at the current sorting node; a first threshold calculation unit, configured to, if not, obtain the first sorting weight data of the express item at the sorting node before the current sorting point, and calculate a first abnormal judgment threshold according to the first sorting weight data; a second threshold calculation unit, configured to, if so, obtain the second sorting weight data of the express item at the current sorting point and the first sorting weight data of the express item at the sorting node before the current sorting point, and calculate a second abnormal judgment threshold according to the first sorting weight data and the second sorting weight data.

[0014] Optionally, in the second implementation manner of the second aspect of the present invention, the first threshold calculation unit includes: a first invalid value elimination subunit, configured to eliminate invalid data values in the first sorting weight data according to a preset invalid data value elimination rule, to obtain first valid historical weight data; a first sorting subunit, configured to sort the first valid historical weight data, to obtain a first valid historical weight sequence; a first screening subunit, configured to screen the first valid historical weight data in the first valid historical weight sequence according to a preset index screening rule, to obtain first weight index data; a first threshold calculation subunit, configured to calculate based on the first weight index data according to a preset threshold calculation rule, to obtain a first abnormal judgment threshold.

[0015] Optionally, in the third implementation manner of the second aspect of the present invention, the second threshold calculation unit includes: a second invalid value elimination subunit, configured to eliminate invalid data values in the first sorting weight data and the second sorting weight data according to a preset invalid data value elimination rule, to obtain second valid historical weight data; a second sorting subunit, configured to sort the second valid historical weight data, to obtain a second valid historical weight sequence; a second screening subunit, configured to screen the second valid historical weight data in the second valid historical weight sequence according to a preset index screening rule, to obtain second weight index data; a second threshold calculation subunit, configured to calculate based on the second weight index data according to a preset threshold calculation rule, to obtain a second abnormal judgment threshold.

[0016] Optionally, in the fourth implementation manner of the second aspect of the present invention, the second invalid value elimination subunit is specifically configured to: detect null values in the first distribution weight data and the second distribution weight data, eliminate the null values to obtain cleaned data; calculate the arithmetic mean of the cleaned data, and calculate the standard deviation according to Bessel's formula; eliminate the gross error values in the cleaned data according to the Pauta criterion to obtain the second effective historical weight data.

[0017] Optionally, in the fifth implementation manner of the second aspect of the present invention, the second screening subunit is specifically configured to: extract the maximum value of the weight data and the adjacent weight data value of the maximum value of the weight data in the second effective historical weight sequence according to the sorting order in the second effective historical weight sequence; determine whether the difference between the maximum value of the weight data and the adjacent weight data value is greater than a preset screening threshold; if the difference is greater than the preset screening threshold, then eliminate the maximum value of the weight data from the second effective historical weight sequence; if the difference is not greater than the preset screening threshold, then use the maximum value of the weight data as the second weight index data.

[0018] Optionally, in the sixth implementation manner of the second aspect of the present invention, the express delivery weight anomaly detection device further includes a record generation module, and the record generation module is specifically configured to: extract the express delivery number of the weight anomaly express delivery; generate a weight anomaly express delivery record according to the express delivery number, and upload the weight anomaly express delivery record to the express delivery management system.

[0019] The third aspect of the present invention provides an express delivery weight anomaly detection device, including: a memory and at least one processor, wherein instructions are stored in the memory; the at least one processor calls the instructions in the memory so that the express delivery weight anomaly detection device executes the steps of the above-mentioned express delivery weight anomaly detection method.

[0020] The fourth aspect of the present invention provides a computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium, and when the instructions are run on a computer, the computer is made to execute the steps of the above-mentioned express delivery weight anomaly detection method.

[0021] In the technical solution provided by the present invention, historical weight data of express items in a to-be-weighed sequence is obtained, and an abnormal judgment threshold is calculated based on the historical weight data; it is judged whether an express item is marked as suspected weight abnormal; if the express item is not marked as suspected weight abnormal, the express item not marked as suspected weight abnormal is weighed to obtain a first real-time weight, and it is judged whether the first real-time weight exceeds the abnormal judgment threshold. If it exceeds the abnormal judgment threshold, the express item is marked as suspected weight abnormal and the express item is re-added to the weighing sequence; if the express item has been marked as suspected weight abnormal, the express item marked as suspected weight abnormal is weighed to obtain a second real-time weight, and it is judged whether the second real-time weight exceeds the abnormal judgment threshold. If it exceeds the abnormal judgment threshold, the express item is marked as a weight-abnormal express item. In the embodiment of the present invention, the express items are automatically weighed and the express items with weight abnormalities are detected, improving the detection efficiency and detection accuracy of the express items with weight abnormalities. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a schematic diagram of the first embodiment of the detection method for weight abnormality of express items in the embodiment of the present invention;

[0023] Figure 2 It is a schematic diagram of the second embodiment of the detection method for weight abnormality of express items in the embodiment of the present invention;

[0024] Figure 3 It is a schematic diagram of the third embodiment of the detection method for weight abnormality of express items in the embodiment of the present invention;

[0025] Figure 4 It is a schematic diagram of the fourth embodiment of the detection method for weight abnormality of express items in the embodiment of the present invention;

[0026] Figure 5 It is a schematic diagram of an embodiment of the detection device for weight abnormality of express items in the embodiment of the present invention;

[0027] Figure 6 It is a schematic diagram of another embodiment of the detection device for weight abnormality of express items in the embodiment of the present invention;

[0028] Figure 7 It is a schematic diagram of an embodiment of the detection equipment for weight abnormality of express items in the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] An embodiment of the present invention provides a method, device, equipment, and storage medium for detecting abnormal express weights. The historical weight data of the express in the to-be-weighed sequence is obtained, and an abnormal judgment threshold is calculated based on the historical weight data; it is judged whether the express is marked as suspected of abnormal weight; if the express is not marked as suspected of abnormal weight, the express that is not marked as suspected of abnormal weight is weighed to obtain a first real-time weight and it is judged whether the first real-time weight exceeds the abnormal judgment threshold. If it exceeds the abnormal judgment threshold, the express is marked as suspected of abnormal weight and the express is added back to the weighing sequence; if the express has been marked as suspected of abnormal weight, the express that is marked as suspected of abnormal weight is weighed to obtain a second real-time weight, and it is judged whether the second real-time weight exceeds the abnormal judgment threshold. If it exceeds the abnormal judgment threshold, the express is marked as an express with abnormal weight. In the embodiment of the present invention, the express is automatically weighed and the express with abnormal weight is detected, improving the detection efficiency and detection accuracy of the express with abnormal weight.

[0030] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" or "having" and any variation thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or equipment that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or equipment.

[0031] For ease of understanding, the specific process of the embodiment of the present invention is described below. Please refer to Figure 1 , an embodiment of the method for detecting abnormal express weights in the embodiment of the present invention includes:

[0032] 101. Obtain the historical weight data of the express in the to-be-weighed sequence, and calculate an abnormal judgment threshold based on the historical weight data;

[0033] It can be understood that the execution subject of the present invention can be a detection device for abnormal express weights, or a terminal or a server. Specifically, no limitation is made here. The embodiment of the present invention takes the server as the execution subject as an example for explanation.

[0034] In this embodiment, to solve the problem of low detection efficiency and detection accuracy of express with abnormal weight in the prior art, the express to be weighed is first arranged in order to generate a to-be-weighed sequence.

[0035] During the delivery process of express parcels, there are multiple links that require weight detection and verification operations on the express parcels to keep track of the weight status of the express parcels at any time for subsequent inquiries. For example, weight detection is carried out during sorting at each sorting point, and weight detection is carried out before final delivery, etc. After obtaining the weight detection data, according to the waybill number of the detected express parcel, the weight data is saved as historical weight data in the express parcel database. Subsequently, based on the historical weight data in the express parcel database, information such as the responsible party for the cargo damage can be determined when abnormal conditions such as damaged items occur to the express parcel.

[0036] Specifically, in this embodiment, the historical weight data may refer to all the historical weight data before the current time node for weight anomaly detection. When detecting the weight of the express parcels in the to-be-weighed sequence, generally, mechanical devices such as robotic arms are used to sequentially place the express parcels in the to-be-weighed sequence on the weighing platform for weighing to obtain the weight of the current express parcel at this node. In addition, before or during weighing, identification labels such as QR codes or induction tags on the express parcel are scanned to obtain the waybill number corresponding to the express parcel, and based on the waybill number corresponding to the express parcel, the historical weight data of the express parcel during the weight detection operation before the current weight detection is queried in the express parcel database. Among them, for one to-be-weighed express parcel, there are multiple pieces of such historical weight data.

[0037] Obtain the preset anomaly judgment rule, and based on the aforementioned obtained historical weight data, calculate the anomaly judgment threshold for weight detection at this node according to this anomaly judgment rule.

[0038] 102. Determine whether the express parcel is marked as suspected weight anomaly;

[0039] In this embodiment, when detecting the weight of the express parcels in the to-be-weighed sequence, the waybill number corresponding to the express parcel is obtained by scanning identification labels such as QR codes or induction tags on the express parcel, and information in the express parcel database is queried according to this waybill number to determine whether the express parcel is marked as a suspected weight anomaly express parcel during weight detection at this logistics node.

[0040] 103. If the express parcel is not marked as suspected weight anomaly, weigh the express parcel that is not marked as suspected weight anomaly to obtain the first real-time weight;

[0041] 104. Determine whether the first real-time weight exceeds the anomaly judgment threshold;

[0042] 105. If it exceeds the anomaly judgment threshold, mark the express parcel as suspected weight anomaly and re-add the express parcel to the weighing sequence;

[0043] If the express parcel is not marked as suspected weight anomaly at this node, perform a weighing operation on this express parcel, and use the obtained weight information as the first real-time weight.

[0044] Obtain the abnormal judgment threshold calculated in the previous step, and determine whether the obtained first real-time weight exceeds the abnormal judgment threshold. If it exceeds the abnormal judgment threshold, mark the express as suspected weight abnormal, and update the weight information of this express in the express database, marking it as an express with suspected weight abnormal. Among them, the abnormal judgment threshold is a numerical range calculated based on the previous historical weight data. When the first real-time weight is within the numerical range, it is considered not to exceed the abnormal judgment threshold, and when the first real-time weight is not within the numerical range, it is considered to exceed the abnormal judgment threshold; after marking, add this express back to the weighing sequence and wait for secondary weighing.

[0045] If the express is not marked as suspected weight abnormal at this node and the obtained first real-time weight does not exceed the abnormal judgment threshold, then mark the express as normal weight and save the obtained first real-time weight to the express database.

[0046] 106. If the express has been marked as suspected weight abnormal, weigh the express marked as suspected weight abnormal to obtain the second real-time weight;

[0047] 107. Determine whether the second real-time weight exceeds the abnormal judgment threshold;

[0048] 108. If it exceeds the abnormal judgment threshold, mark the express as an express with abnormal weight.

[0049] If when obtaining the express waybill number, it is found in the express database according to the express waybill number that the express is marked as suspected weight abnormal at this node, then perform a weighing operation on this express marked as suspected weight abnormal, and use the obtained weight information as the second real-time weight.

[0050] Obtain the abnormal judgment threshold corresponding to this express calculated in the previous step, and determine whether the second real-time weight exceeds the abnormal judgment threshold.

[0051] If the second real-time weight exceeds the abnormal judgment threshold, mark the express as an express with abnormal weight, save the second real-time weight marked as abnormal weight to the express database, and process this express with abnormal weight according to the weight abnormal information;

[0052] If the second real-time weight does not exceed the abnormal judgment threshold, it is considered that the weight of the express is normal, clear the suspected weight abnormal information in the express database, and save the second real-time weight within the normal range to the express database.

[0053] The embodiment of the present invention can automatically weigh the express and detect the express with abnormal weight, improving the detection efficiency and detection accuracy of the express with abnormal weight.

[0054] Please refer to Figure 2 , the second embodiment of the detection method for abnormal express weight in the embodiments of the present invention includes:

[0055] 201. Identify whether there is second sorting weight data for the express at the current sorting node;

[0056] If the express in the sequence to be weighed is not weighed for the first time at the current sorting point or the weight value obtained when the express is weighed at the current sorting point contains valid data, it is considered that there is second sorting weight data.

[0057] 202. If there is second sorting weight data, obtain the second sorting weight data of the express at the current sorting point and the first sorting weight data at the sorting node before the current sorting point;

[0058] 203. Calculate the second abnormal judgment threshold according to the first sorting weight data and the second sorting weight data;

[0059] Obtain the second sorting weight data of the express at the current sorting point and the first sorting weight data at the sorting node before the current sorting point. According to the preset invalid data value elimination rule, eliminate the invalid data values in the first sorting weight data and the second sorting weight data, and form the second valid historical weight data with the remaining sorting weight data; sort the second valid historical weight data to obtain the second valid historical weight sequence; screen the second valid historical weight data in the second valid historical weight sequence according to the preset index screening rule to obtain the second weight index data.

[0060] Specifically, when calculating the second weight index data, according to the preset invalid data value elimination rule, eliminate the invalid data values in the first sorting weight data and the second sorting weight data to obtain the second valid historical weight data; wherein, the invalid data values include null values and gross error values; first detect the null values in the first weight data set and the second weight data set, eliminate the null values to obtain the second cleaned data after eliminating null values; calculate the arithmetic mean of the second cleaned data and calculate the standard deviation according to Bessel's formula; subsequently, eliminate the gross error values in the second cleaned data according to the Pauta criterion to obtain the second valid historical weight data, where the specific expression of Bessel's formula is:

[0061]

[0062] where S represents the standard deviation, represents the arithmetic mean, n represents the number of first historical weight data, x j represents the second cleaned data.

[0063] Sort the second effective historical weight data to obtain a second effective historical weight sequence; according to the sorting order in the second effective historical weight sequence, extract the maximum value of the weight data in the second effective historical weight sequence and the adjacent weight data value of the maximum value of the weight data; determine whether the difference between the maximum value of the weight data and the adjacent weight data value is greater than a preset screening threshold.

[0064] In this step, calculate the difference between the maximum value of the weight data and the adjacent weight data value; determine whether the difference is greater than the screening threshold.

[0065] Among them, the screening threshold is a data range determined in advance according to the screening rule, and this data range describes the proximity between the maximum value and the adjacent weight data value in the second effective historical weight sequence. When the difference is greater than the screening threshold, it indicates that the gap between the maximum value of the weight data and the adjacent weight data value is too large, and it is considered that the maximum value of the weight data in the second effective historical sequence has a large fluctuation at this time; then remove the maximum value of the weight data from the second effective historical weight sequence, do not use the maximum value of the weight data as the weight index data, and update the sorting order in the second effective historical weight sequence according to the weight data information after removal, continue to extract the new maximum value of the weight data and calculate the difference; if the difference between the obtained maximum value of the weight data and the adjacent weight data value is less than the above screening threshold, it is considered that the fluctuation of the maximum value of the weight data meets the requirements, and the maximum value of the weight data is used as the weight index data; calculate based on the first weight index data according to the preset threshold calculation rule to obtain the second anomaly judgment threshold.

[0066] 204. Determine whether the express item is marked as suspected weight anomaly;

[0067] Obtain the waybill number corresponding to the express item, query the information in the express item database according to the waybill number, and determine whether the express item is marked as a suspected weight anomaly express item when the weight of the express item is detected at this logistics node.

[0068] 205. If the express item is not marked as suspected weight anomaly, weigh the express item that is not marked as suspected weight anomaly to obtain the first real-time weight;

[0069] 206. Determine whether the first real-time weight exceeds the second anomaly judgment threshold;

[0070] 207. If it exceeds the second anomaly judgment threshold, mark the express item as suspected weight anomaly and add the express item back to the weighing sequence;

[0071] If the express item is not marked as suspected weight anomaly at this node, perform a weighing operation on this express item, and use the obtained weight information as the first real-time weight.

[0072] Obtain the second abnormal judgment threshold calculated in the previous step, and determine whether the obtained first real-time weight exceeds the second abnormal judgment threshold. If it exceeds the second abnormal judgment threshold, mark the express as suspected weight abnormal, update the weight information of this express in the express database, mark it as an express with suspected weight abnormal, and after marking, add this express back to the weighing sequence and wait for secondary weighing.

[0073] If this express is not marked as suspected weight abnormal at this node and the obtained first real-time weight does not exceed the second abnormal judgment threshold, then mark this express as normal weight and save the obtained first real-time weight to the express database.

[0074] 208. If the express has been marked as suspected weight abnormal, weigh the express marked as suspected weight abnormal to obtain the second real-time weight;

[0075] 209. Determine whether the second real-time weight exceeds the second abnormal judgment threshold;

[0076] 210. If it exceeds the second abnormal judgment threshold, mark the express as a weight abnormal express;

[0077] If when obtaining the express waybill number, it is found in the express database according to this express waybill number that this express is marked as suspected weight abnormal at this node, then perform a weighing operation on this express marked as suspected weight abnormal, and use the obtained weight information as the second real-time weight.

[0078] Obtain the second abnormal judgment threshold corresponding to this express calculated in the previous step, and determine whether this second real-time weight exceeds this second abnormal judgment threshold.

[0079] If this second real-time weight exceeds this second abnormal judgment threshold, mark this express as a weight abnormal express, save the second real-time weight marked as abnormal weight to the express database, and perform processing on this weight abnormal express according to this weight abnormal information;

[0080] If this second real-time weight does not exceed this second abnormal judgment threshold, then consider the weight of this express as normal, clear the suspected weight abnormal information in the express database, and save this second real-time weight within the normal range to the express database.

[0081] 211. Extract the express waybill numbers of the weight abnormal expresses;

[0082] 212. Generate weight abnormal express records according to the express waybill numbers and upload the weight abnormal express records to the express management system.

[0083] Extract the waybill numbers of the express parcels marked as having abnormal weights, generate weight-abnormal express parcel records based on these waybill numbers, and upload them to the express parcel database to update the corresponding express parcel information. At the same time, generate abnormal notification information based on these weight-abnormal express parcel records and push this abnormal notification information to the express parcel management system for the administrator to handle. The administrator can choose to notify the shipping user of the weight-abnormal express parcel record according to the specific information of this weight-abnormal express parcel record.

[0084] In the embodiment of the present invention, the express parcels are automatically weighed and the express parcels with abnormal weights are detected, improving the detection efficiency and detection accuracy of the express parcels with abnormal weights.

[0085] Please refer to Figure 3 , the third embodiment of the detection method for abnormal express parcel weights in the embodiment of the present invention includes:

[0086] 301. Identify whether there is second sorting weight data of the express parcel at the current sorting node;

[0087] In the detection method for abnormal express parcel weights in this embodiment, after obtaining the waybill numbers of the express parcels in the to-be-weighed sequence, the historical weight data is queried from the express parcel database according to the waybill numbers. Among them, the historical weight data in this embodiment may include the first sorting weight data of the sorting nodes before the current sorting node of the express parcel and / or the second sorting weight data of the express parcel at the current sorting point. In this step, first, identify whether there is second sorting weight data of the express parcel at the current sorting node.

[0088] 302. If there is no second sorting weight data, obtain the first sorting weight data of the express parcel at the sorting node before the current sorting point;

[0089] 303. Calculate the first abnormal judgment threshold according to the first sorting weight data;

[0090] If the express parcel is not weighed for the first time at the current sorting point or the weight value obtained when the express parcel is weighed at the current sorting point contains valid data, there is second sorting weight data; if the express parcel is weighed for the first time at the current sorting point or the weight values obtained when the express parcel is weighed at the current sorting point are all invalid data, there is no second sorting weight data in the express parcel database. At this time, obtain the first sorting weight data of the express parcel at the sorting node before the current sorting point.

[0091] Subsequently, detect the null values in the first sorting weight data, remove the null values to obtain the first cleaned data after removing the null values; calculate the arithmetic mean of the first cleaned data, and calculate the standard deviation according to the Bessel formula; subsequently, remove the gross error values in the first cleaned data according to the Pauta criterion to obtain the first effective historical weight data. Among them, the specific expression of the Bessel formula is:

[0092]

[0093] Among them, S represents the standard deviation, represents the arithmetic mean, n represents the number of the first cleaned data, and x i represents the first cleaned data.

[0094] Sort the first effective historical weight data to obtain the first effective historical weight sequence; according to the sorting order in the first effective historical weight sequence, extract the maximum value of the weight data and the adjacent weight data value of the maximum value of the weight data in the first effective historical weight sequence; determine whether the difference between the maximum value of the weight data and the adjacent weight data value is greater than a preset screening threshold. If the difference between the obtained maximum value of the weight data and the adjacent weight data value is less than the above screening threshold, it is considered that the fluctuation of the maximum value of the weight data meets the requirements, and the maximum value of the weight data is used as the first weight index data.

[0095] 304. Determine whether the express is marked as suspected weight anomaly;

[0096] 305. If the express is not marked as suspected weight anomaly, weigh the express that is not marked as suspected weight anomaly to obtain the first real-time weight;

[0097] 306. Determine whether the first real-time weight exceeds the first anomaly judgment threshold;

[0098] 307. If it exceeds the first anomaly judgment threshold, mark the express as suspected weight anomaly and add the express back to the weighing sequence;

[0099] If the express is not marked as suspected weight anomaly at this node, perform a weighing operation on this express, and use the obtained weight information as the first real-time weight.

[0100] Obtain the first anomaly judgment threshold calculated in the previous steps, determine whether the obtained first real-time weight exceeds the first anomaly judgment threshold. If it exceeds the first anomaly judgment threshold, mark the express as suspected weight anomaly, update the weight information of this express in the express database, mark it as an express with suspected weight anomaly, and after marking, add this express back to the weighing sequence and wait for secondary weighing.

[0101] If the express is not marked as suspected weight anomaly at this node and the obtained first real-time weight does not exceed the first anomaly judgment threshold, mark the express as weight normal and save the obtained first real-time weight to the express database.

[0102] 308. If the express parcel has been marked as suspected of abnormal weight, weigh the express parcel marked as suspected of abnormal weight to obtain the second real-time weight;

[0103] 309. Determine whether the second real-time weight exceeds the first abnormal judgment threshold;

[0104] 310. If it exceeds the first abnormal judgment threshold, mark the express parcel as an express parcel with abnormal weight.

[0105] If when obtaining the express parcel number, it is found in the express parcel database according to the express parcel number that the express parcel is marked as suspected of abnormal weight at this node, then perform a weighing operation on the express parcel marked as suspected of abnormal weight, and use the obtained weight information as the second real-time weight.

[0106] Obtain the first abnormal judgment threshold corresponding to this express parcel calculated in the previous step, and determine whether the second real-time weight exceeds the first abnormal judgment threshold.

[0107] If the second real-time weight exceeds the first abnormal judgment threshold, mark the express parcel as an express parcel with abnormal weight, save the second real-time weight marked as abnormal weight to the express parcel database, and process the express parcel with abnormal weight according to the abnormal weight information;

[0108] If the second real-time weight does not exceed the first abnormal judgment threshold, it is considered that the weight of the express parcel is normal, clear the suspected abnormal weight information in the express parcel database, and save the second real-time weight within the normal range to the express parcel database.

[0109] In the embodiments of the present invention, the express parcel is automatically weighed and the express parcels with abnormal weight are detected, which improves the detection efficiency of the express parcels with abnormal weight and further improves the detection accuracy.

[0110] Please refer to Figure 4 , the fourth embodiment of the detection method for abnormal weight of express parcels in the embodiments of the present invention includes:

[0111] 401. Identify whether there is second sorting weight data for the express parcel at the current sorting node;

[0112] 402. If there is no second sorting weight data, obtain the first sorting weight data of the express parcel at the sorting node before the current sorting point, and calculate the first abnormal judgment threshold according to the first sorting weight data;

[0113] If there is no second sorting weight data, calculate the first weight index data according to the first sorting weight data. Among them, the specific calculation method of the first weight index data in this step is basically the same as the method for calculating the first weight index data in step 303 in the previous embodiment, so it will not be elaborated here.

[0114] After obtaining the first weight index data, obtain the preset abnormal judgment rule. Based on the obtained first weight index data, calculate the first abnormal judgment threshold for the weight detection of this node according to this abnormal judgment rule. Specifically, this abnormal judgment rule can be: 0.8B i <A i ≤1.5B i ; where A i represents the real-time weight, represents the weight index data, and this abnormal judgment threshold is (0.8B i , 1.5B i ; Specifically, when B1 represents the first weight index data, this first abnormal judgment threshold can be expressed as (0.8B1, 1.5B1].

[0115] 403. Determine whether the express delivery is marked as suspected weight abnormality;

[0116] 404. If the express delivery is not marked as suspected weight abnormality, weigh the express delivery that is not marked as suspected weight abnormality to obtain the first real-time weight;

[0117] 405. Determine whether the first real-time weight exceeds the first abnormal judgment threshold;

[0118] 406. If it exceeds the first abnormal judgment threshold, mark the express delivery as suspected weight abnormality and add the express delivery back to the weighing sequence;

[0119] If this express delivery is not marked as suspected weight abnormality at this node, perform a weighing operation on this express delivery and use the obtained weight information as the first real-time weight.

[0120] Specifically, using A1 to represent the first real-time weight, if this express delivery is not marked as suspected weight abnormality at this node and the first abnormal judgment threshold, that is, it satisfies: 0.8B1 < A1 ≤ 1.5B1; then mark the express delivery as normal weight and save the obtained first real-time weight to the express delivery database.

[0121] If this express delivery is not marked as suspected weight abnormality at this node but does not satisfy: 0.8B1 < A1 ≤ 1.5B1; then mark the express delivery as suspected weight abnormality. After marking this express delivery, add this express delivery back to the weighing sequence and wait for secondary weighing.

[0122] 407. If the express delivery has been marked as suspected weight abnormality, weigh the express delivery that is marked as suspected weight abnormality to obtain the second real-time weight;

[0123] 408. Determine whether the second real-time weight exceeds the first abnormal judgment threshold;

[0124] 409. If it exceeds the first abnormal judgment threshold, mark the express as an express with abnormal weight.

[0125] Specifically, let A2 represent the second real-time weight. If the express is marked as suspected of having abnormal weight at this node, but satisfies: 0.8B1 < A2 ≤ 1.5B1; then mark the express as having normal weight, clear the suspected abnormal weight information in the express database, and save the second real-time weight within the normal range to the express database.

[0126] If the express is marked as suspected of having abnormal weight at this node and does not satisfy the first abnormal judgment threshold, that is, does not satisfy: 0.8B1 < A2 ≤ 1.5B1; then mark the express as an express with abnormal weight, save the second real-time weight marked as abnormal weight to the express database, and process the express with abnormal weight according to this weight abnormal information.

[0127] 410. If there is second sorting weight data, obtain the second sorting weight data of the express at the current sorting point and the first sorting weight data at the sorting nodes before the current sorting point, and calculate the second abnormal judgment threshold according to the first sorting weight data and the second sorting weight data.

[0128] If there is second sorting weight data, obtain the second sorting weight data of the express at the current sorting point and the first sorting weight data at the sorting nodes before the current sorting point. According to the preset invalid data value elimination rule, eliminate the invalid data values in the first sorting weight data and the second sorting weight data, and form the second effective historical weight data with the remaining sorting weight data; sort the second effective historical weight data to obtain the second effective historical weight sequence; screen the second effective historical weight data in the second effective historical weight sequence according to the preset index screening rule to obtain the second weight index data; calculate based on the second weight index data according to the preset threshold calculation rule to obtain the second abnormal judgment threshold.

[0129] Among them, the calculation method of the second weight index data in this step is basically the same as the content in step 203 of the foregoing embodiment, so it will not be elaborated here.

[0130] 411. Judge whether the express is marked as suspected of having abnormal weight.

[0131] 412. If the express is not marked as suspected of having abnormal weight, weigh the express that is not marked as suspected of having abnormal weight to obtain the first real-time weight.

[0132] 413. Judge whether the first real-time weight exceeds the second abnormal judgment threshold.

[0133] Specifically, let A1 represent the first real-time weight, and B2 represent the second weight index data. If the express package is not marked as suspected weight anomaly at this node and meets the second anomaly judgment threshold, that is, it meets: 0.8B2 < A1 ≤ 1.5B2; then mark the express package as normal in weight, and save the obtained first real-time weight to the express package database.

[0134] 414. If it exceeds the second anomaly judgment threshold, then mark the express package as suspected weight anomaly and add the express package back to the weighing sequence.

[0135] If the express package is not marked as suspected weight anomaly at this node but does not meet: 0.8B2 < A1 ≤ 1.5B2; then mark the express package as suspected weight anomaly. After marking the express package, add this express package back to the weighing sequence and wait for secondary weighing.

[0136] 415. If the express package has been marked as suspected weight anomaly, then weigh the express package marked as suspected weight anomaly to obtain the second real-time weight.

[0137] 416. Determine whether the second real-time weight exceeds the second anomaly judgment threshold.

[0138] 417. If it exceeds the second anomaly judgment threshold, then mark the express package as weight anomaly.

[0139] Specifically, let A2 represent the second real-time weight. If the express package is marked as suspected weight anomaly at this node but meets: 0.8B2 < A2 ≤ 1.5B2; then mark the express package as normal in weight and clear the suspected weight anomaly information in the express package database, and save the second real-time weight within the normal range to the express package database.

[0140] If the express package is marked as suspected weight anomaly at this node and does not meet the second anomaly judgment threshold, that is, it does not meet: 0.8B2 < A2 ≤ 1.5B2; then mark the express package as weight anomaly, save the second real-time weight marked as abnormal weight to the express package database, and process the weight anomaly express package according to this weight anomaly information, and clear the suspected weight anomaly information in the express package database, and save the second real-time weight within the normal range to the express package database.

[0141] Subsequently, extract the waybill number of the express package marked as weight anomaly, generate a weight anomaly express package record according to this waybill number, and upload it to the express package database to update the corresponding express package information; at the same time, generate an anomaly notification information based on this weight anomaly express package record, and push this anomaly notification information to the express package management system for the administrator to process. The administrator can choose to notify the shipping user of the weight anomaly express package record according to the specific information of this weight anomaly express package record.

[0142] In an embodiment of the present invention, the express packages are automatically weighed and the express packages with abnormal weights are detected, which improves the detection efficiency of the express packages with abnormal weights and further enhances the detection accuracy.

[0143] The detection method for abnormal weights of express packages in the embodiments of the present invention has been described above. Next, the detection device for abnormal weights of express packages in the embodiments of the present invention will be described. Please refer to Figure 5 One embodiment of the detection device for abnormal weights of express packages in the embodiments of the present invention includes:

[0144] An acquisition module 501, configured to acquire historical weight data of the express packages in the sequence to be weighed, and calculate an abnormal judgment threshold according to the historical weight data;

[0145] An abnormal judgment module 502, configured to judge whether the express package is marked as suspected of having an abnormal weight;

[0146] A first weighing module 503, configured to weigh the express package that is not marked as suspected of having an abnormal weight if the express package is not marked as suspected of having an abnormal weight, obtain a first real-time weight, judge whether the first real-time weight exceeds the abnormal judgment threshold, and if it exceeds the abnormal judgment threshold, mark the express package as suspected of having an abnormal weight and add the express package back to the weighing sequence;

[0147] A second weighing module 504, configured to weigh the express package that is marked as suspected of having an abnormal weight if the express package is marked as suspected of having an abnormal weight, obtain a second real-time weight, judge whether the second real-time weight exceeds the abnormal judgment threshold, and if it exceeds the abnormal judgment threshold, mark the express package as an express package with an abnormal weight.

[0148] In the embodiments of the present invention, the express packages can be automatically weighed and the express packages with abnormal weights can be detected, which improves the detection efficiency and detection accuracy of the express packages with abnormal weights.

[0149] Please refer to Figure 6 Another embodiment of the detection device for abnormal weights of express packages in the embodiments of the present invention includes:

[0150] An acquisition module 501, configured to acquire historical weight data of the express packages in the sequence to be weighed, and calculate an abnormal judgment threshold according to the historical weight data;

[0151] An abnormal judgment module 502, configured to judge whether the express package is marked as suspected of having an abnormal weight;

[0152] The first weighing module 503 is configured to weigh the express that is not marked as suspected weight anomaly to obtain a first real-time weight, determine whether the first real-time weight exceeds the anomaly judgment threshold. If it exceeds the anomaly judgment threshold, mark the express as suspected weight anomaly and add the express back to the weighing sequence;

[0153] The second weighing module 504 is configured to weigh the express that is marked as suspected weight anomaly to obtain a second real-time weight, determine whether the second real-time weight exceeds the anomaly judgment threshold. If it exceeds the anomaly judgment threshold, mark the express as a weight anomaly express.

[0154] In another embodiment of the present application, the acquisition module 501 includes:

[0155] A data recognition unit 5011 for recognizing whether there is second sorting weight data of the express at the current sorting node;

[0156] A first threshold calculation unit 5012 for, if not, obtaining first sorting weight data of the express at the sorting node before the current sorting point and calculating a first anomaly judgment threshold according to the first sorting weight data;

[0157] A second threshold calculation unit 5013 for, if it exists, obtaining second sorting weight data of the express at the current sorting point and first sorting weight data of the express at the sorting node before the current sorting point, and calculating a second anomaly judgment threshold according to the first sorting weight data and the second sorting weight data.

[0158] In another embodiment of the present application, the first threshold calculation unit 5012 includes:

[0159] A first invalid value elimination subunit for eliminating invalid data values in the first sorting weight data according to a preset invalid data value elimination rule to obtain first valid historical weight data;

[0160] A first sorting subunit for sorting the first valid historical weight data to obtain a first valid historical weight sequence;

[0161] A first screening subunit for screening first valid historical weight data in the first valid historical weight sequence according to a preset index screening rule to obtain first weight index data;

[0162] A first threshold calculation subunit for calculating a first anomaly judgment threshold based on the first weight index data according to a preset threshold calculation rule.

[0163] In another embodiment of the present application, the second threshold calculation unit 5013 includes:

[0164] A second invalid value elimination subunit, configured to eliminate invalid data values in the first distribution weight data and the second distribution weight data according to a preset invalid data value elimination rule, so as to obtain second effective historical weight data;

[0165] A second sorting subunit, configured to sort the second effective historical weight data to obtain a second effective historical weight sequence;

[0166] A second screening subunit, configured to screen the second effective historical weight data in the second effective historical weight sequence according to a preset index screening rule to obtain second weight index data;

[0167] A second threshold calculation subunit, configured to calculate based on the second weight index data according to a preset threshold calculation rule to obtain a second abnormal judgment threshold.

[0168] In another embodiment of the present application, the second invalid value elimination subunit is specifically configured to: detect null values in the first distribution weight data and the second distribution weight data, eliminate the null values to obtain cleaned data;

[0169] Calculate the arithmetic mean of the cleaned data and calculate the standard deviation according to Bessel's formula;

[0170] Eliminate gross error values in the cleaned data according to the Pauta criterion to obtain second effective historical weight data.

[0171] In another embodiment of the present application, the second screening subunit is specifically configured to: extract the maximum value of the weight data and the adjacent weight data value of the maximum value of the weight data in the second effective historical weight sequence according to the sorting order in the second effective historical weight sequence;

[0172] Judge whether the difference between the maximum value of the weight data and the adjacent weight data value is greater than a preset screening threshold;

[0173] If the difference is greater than the preset screening threshold, then eliminate the maximum value of the weight data from the second effective historical weight sequence;

[0174] If the difference is not greater than the preset screening threshold, then use the maximum value of the weight data as the second weight index data.

[0175] In another embodiment of the present application, the detection device for abnormal express weight further includes a record generation module 505, and the record generation module 505 is specifically configured to: extract the express order number of the express with abnormal weight; generate a record of the express with abnormal weight according to the express order number, and upload the record of the express with abnormal weight to the express management system.

[0176] In summary, by automatically weighing the express and detecting the express with abnormal weight, the detection efficiency of the express with abnormal weight is improved, and the detection accuracy is further enhanced.

[0177] Above Figure 5 and Figure 6 The detection device for abnormal express weight in the embodiments of the present invention has been described in detail from the perspective of modular functional entities. Next, the detection device for abnormal express weight in the embodiments of the present invention will be described in detail from the perspective of hardware processing.

[0178] Figure 7 FIG. is a schematic structural diagram of a detection device for abnormal express weight provided by an embodiment of the present invention. The detection device 700 for abnormal express weight may vary greatly due to configuration or performance, and may include one or more processors (central processing units, CPU) 710 (for example, one or more processors) and a memory 720, and one or more storage media 730 for storing application programs 733 or data 732 (for example, one or more mass storage devices). Among them, the memory 720 and the storage media 730 may be transient storage or persistent storage. The program stored in the storage media 730 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the detection device 700 for abnormal express weight. Further, the processor 710 may be configured to communicate with the storage media 730 and execute a series of instruction operations in the storage media 730 on the detection device 700 for abnormal express weight.

[0179] The detection device 700 for abnormal express weight may further include one or more power supplies 740, one or more wired or wireless network interfaces 750, one or more input / output interfaces 760, and / or one or more operating systems 731, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art can understand that Figure 7 The shown structural diagram of the detection device for abnormal express weight does not limit the detection device for abnormal express weight, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0180] The present invention also provides a computer device, which can be any device capable of executing the express delivery weight anomaly detection method described in the above embodiments. The computer device includes a memory and a processor. Computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by the processor, the processor executes the steps of the express delivery weight anomaly detection method in the above embodiments.

[0181] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer, the computer is caused to execute the steps of the express delivery weight anomaly detection method.

[0182] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0183] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0184] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for detecting abnormal weight of express delivery, characterized in that, The detection method for abnormal express weight includes: Obtain the historical weight data of the express in the to-be-weighed sequence, and calculate an abnormal judgment threshold based on the historical weight data; Judge whether the express is marked as suspected of abnormal weight; If the express is not marked as suspected of abnormal weight, weigh the express that is not marked as suspected of abnormal weight to obtain a first real-time weight, and judge whether the first real-time weight exceeds the abnormal judgment threshold. If it exceeds the abnormal judgment threshold, mark the express as suspected of abnormal weight and re-add the express to the weighing sequence; If the express has been marked as suspected of abnormal weight, weigh the express that is marked as suspected of abnormal weight to obtain a second real-time weight, and judge whether the second real-time weight exceeds the abnormal judgment threshold. If it exceeds the abnormal judgment threshold, mark the express as an express with abnormal weight; The historical weight data includes the first transfer weight data of the express at the transfer node before the current transfer node and / or the second transfer weight data of the express at the current transfer point. The obtaining of the historical weight data of the express in the to-be-weighed sequence and the calculation of the abnormal judgment threshold based on the historical weight data include: identifying whether there is second transfer weight data of the express at the current transfer node. The second transfer weight data refers to the weight value obtained when the express is not detected for the first time at the current transfer node or when the express is detected for weight at the current transfer point and contains valid data; if not, obtain the first transfer weight data of the express at the transfer node before the current transfer point, and calculate a first abnormal judgment threshold based on the first transfer weight data; if it exists, obtain the second transfer weight data of the express at the current transfer point and the first transfer weight data of the express at the transfer node before the current transfer point, and calculate a second abnormal judgment threshold based on the first transfer weight data and the second transfer weight data.

2. The detection method for abnormal express weight according to claim 1, wherein The calculation of the first abnormal judgment threshold based on the first transfer weight data includes: Eliminate the invalid data values in the first transfer weight data according to the preset invalid data value elimination rule to obtain first valid historical weight data; Sort the first valid historical weight data to obtain a first valid historical weight sequence; Screen the first valid historical weight data in the first valid historical weight sequence according to the preset index screening rule to obtain first weight index data; Calculate based on the first weight index data according to the preset threshold calculation rule to obtain a first abnormal judgment threshold.

3. The detection method for abnormal express weight according to claim 1, characterized in that The calculation of the second abnormal judgment threshold based on the first transfer weight data and the second transfer weight data includes: Eliminate the invalid data values in the first transfer weight data and the second transfer weight data according to the preset invalid data value elimination rule to obtain second valid historical weight data; Sort the second valid historical weight data to obtain a second valid historical weight sequence; Screen the second effective historical weight data in the second effective historical weight sequence according to the preset index screening rules to obtain second weight index data; Calculate based on the second weight index data according to the preset threshold calculation rules to obtain a second abnormal judgment threshold.

4. The detection method for abnormal express weight according to claim 3, wherein The invalid data values include null values and gross error values. According to the preset invalid data value elimination rules, eliminate the invalid data values in the first sorting weight data and the second sorting weight data. The steps to obtain the second effective historical weight data include: Detect the null values in the first sorting weight data and the second sorting weight data, and eliminate the null values to obtain cleaned data; Calculate the arithmetic mean of the cleaned data, and calculate the standard deviation according to Bessel's formula; Eliminate the gross error values in the cleaned data according to the Pauta criterion to obtain the second effective historical weight data.

5. The detection method for abnormal express weight according to claim 4, characterized in that, The steps to screen the second effective historical weight data in the second effective historical weight sequence according to the preset index screening rules to obtain second weight index data include: According to the sorting order in the second effective historical weight sequence, extract the maximum value of the weight data and the adjacent weight data value of the maximum value of the weight data in the second effective historical weight sequence; Judge whether the difference between the maximum value of the weight data and the adjacent weight data value is greater than a preset screening threshold; If the difference is greater than the preset screening threshold, then eliminate the maximum value of the weight data from the second effective historical weight sequence; If the difference is not greater than the preset screening threshold, then use the maximum value of the weight data as the second weight index data.

6. The detection method for abnormal express weight according to any one of claims 1-5, characterized in that, After labeling the express delivery as an express delivery with abnormal weight, it further includes: Extract the express delivery number of the express delivery with abnormal weight; Generate a record of the express delivery with abnormal weight according to the express delivery number, and upload the record of the express delivery with abnormal weight to the express delivery management system.

7. A detection device for abnormal weight of express parcels, characterized in that, The detection device for abnormal express delivery weight includes: An acquisition module, configured to acquire the historical weight data of the express delivery in the sequence to be weighed, and calculate an abnormal judgment threshold according to the historical weight data; An abnormal judgment module, configured to judge whether the express delivery is labeled as suspected of having abnormal weight; A first weighing module, configured to, if the express delivery is not labeled as suspected of having abnormal weight, weigh the express delivery that is not labeled as suspected of having abnormal weight to obtain a first real-time weight, judge whether the first real-time weight exceeds the abnormal judgment threshold, and if it exceeds the abnormal judgment threshold, label the express delivery as suspected of having abnormal weight, and add the express delivery back to the weighing sequence; A second weighing module, configured to, if the express delivery is already labeled as suspected of having abnormal weight, weigh the express delivery that is labeled as suspected of having abnormal weight to obtain a second real-time weight, judge whether the second real-time weight exceeds the abnormal judgment threshold, and if it exceeds the abnormal judgment threshold, label the express delivery as an express delivery with abnormal weight; The historical weight data includes the first sorting weight data of the express at the sorting nodes before the current sorting node and / or the second sorting weight data of the express at the current sorting point. The obtaining module includes: a data recognition unit, configured to recognize whether there is second sorting weight data of the express at the current sorting node, where the second sorting weight data refers to the weight value obtained when the express is not detected for the first time at the current sorting node or when the express is detected for weight at the current sorting point and contains valid data; a first threshold calculation unit, configured to, if not present, obtain the first sorting weight data of the express at the sorting node before the current sorting point, and calculate a first abnormal judgment threshold according to the first sorting weight data; a second threshold calculation unit, configured to, if present, obtain the second sorting weight data of the express at the current sorting point and the first sorting weight data of the express at the sorting node before the current sorting point, and calculate a second abnormal judgment threshold according to the first sorting weight data and the second sorting weight data.

8. A detection device for abnormal weight of express parcels, characterized in that, The detection device for abnormal express weight includes: a memory and at least one processor, where instructions are stored in the memory; The at least one processor invokes the instructions in the memory, so that the detection device for abnormal express weight executes the steps of the method for detecting abnormal express weight according to any one of claims 1-6.

9. A computer-readable storage medium having instructions stored thereon, characterized in that, When the instructions are executed by the processor, the steps of the method for detecting abnormal express weight according to any one of claims 1-6 are implemented.

Images