CN115018411A

CN115018411A - Logistics transportation overtime abnormity monitoring method, device, equipment and storage medium

Info

Publication number: CN115018411A
Application number: CN202210563614.5A
Authority: CN
Inventors: 周雨蓉; 刘大鹏
Original assignee: Dongpu Software Co Ltd
Current assignee: Dongpu Software Co Ltd
Priority date: 2022-05-23
Filing date: 2022-05-23
Publication date: 2022-09-06

Abstract

The invention relates to the technical field of logistics monitoring, and discloses a method, a device, equipment and a storage medium for monitoring logistics transportation overtime abnormity. The method comprises the following steps: preprocessing real-time logistics transportation data to obtain target logistics transportation data; predicting target logistics transportation data, and determining the timeliness index of the logistics waybill corresponding to the data; performing dimensionality analysis on the data based on the service dimensionality model to obtain multi-dimensional logistics data; determining the service dimension corresponding to the multi-dimensional logistics data, verifying the timeliness index and the timeliness confidence interval according to the service dimension, judging whether the transportation timeliness of the freight note is abnormal or not according to the verification result, and outputting prompt information to the corresponding transportation unit according to the judgment result. The scheme identifies real-time logistics transportation data to obtain the logistics freight note with the abnormal transportation state, and outputs transportation prompt information to the corresponding transportation unit according to the abnormal type and the delivery plan of the abnormal logistics freight note to guarantee delivery timeliness.

Description

Logistics transportation overtime abnormity monitoring method, device, equipment and storage medium

Technical Field

The invention relates to the technical field of logistics monitoring, in particular to a method, a device, equipment and a storage medium for monitoring logistics transportation overtime abnormity.

Background

At present, in an e-commerce platform or a logistics platform, aging monitoring of logistics tracks is only performed through existing logistics tracks and logistics information of logistics waybills, so that data monitoring is performed, however, the mode is only specific to the issued logistics waybills, aging monitoring of line dimensions cannot be achieved, advance prediction of aging monitoring cannot be performed, interference in advance is difficult to achieve, service quality is guaranteed, and experience of logistics users is guaranteed.

In order to integrate the aging data of the whole network, improve the data quality, realize the unification of the data aperture standards, build the mobile aging monitoring analysis capability, build the aging monitoring App of the whole network, realize the data sinking, from headquarter to distribution point, satisfy the requirement of each post for seeing the data, assist to promote the aging, strengthen the service quality, strengthen the industry competitiveness, strengthen the bargaining capability of the front-end market. Therefore, how to realize overtime abnormal monitoring of logistics transportation can be realized, advance prediction of time efficiency monitoring of each logistics waybill can be realized, intervention can be performed in advance to guarantee service quality, and logistics experience of users is improved.

Disclosure of Invention

The invention mainly aims to identify real-time logistics transportation data to obtain a logistics freight note with an abnormal transportation state, and output transportation prompt information to a corresponding transportation unit according to the abnormal type and the distribution plan of the abnormal logistics freight note, so that the timeliness of dispatching is guaranteed.

The invention provides a method for monitoring overtime abnormity of logistics transportation, which comprises the following steps: the method comprises the steps of obtaining real-time logistics transportation data of a logistics distribution station, and preprocessing the real-time logistics transportation data to obtain target logistics transportation data; predicting the target logistics transportation data, and determining an aging index of a logistics waybill corresponding to the target logistics transportation data; performing dimension analysis on the target logistics transportation data based on a preset service dimension model to obtain multi-dimensional logistics data; determining a service dimension corresponding to the multi-dimensional logistics data, and verifying the aging index and a preset aging confidence interval according to the service dimension to obtain a verification result; and judging whether the transportation timeliness of the logistics waybill is abnormal or not according to the checking result, and outputting transportation prompt information to the corresponding transportation unit of the logistics waybill according to the judging result.

Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining real-time logistics transportation data of a logistics distribution site, and preprocessing the real-time logistics transportation data to obtain target logistics transportation data includes: collecting logistics scanning data, transportation vehicle in-out data and logistics log data in a logistics distribution network in real time based on a preset timing task; respectively storing the logistics scanning data, the transportation vehicle in-and-out-of-station data and the logistics log data into a preset message queue to obtain real-time logistics transportation data; filtering the real-time logistics transportation data based on a preset filtering rule to obtain logistics field data which do not accord with the filtering rule; and performing data correction on the logistics field data to obtain target logistics transportation data.

Optionally, in a second implementation manner of the first aspect of the present invention, the predicting the target logistics transportation data and determining an aging index of a logistics waybill corresponding to the target logistics transportation data includes: and inputting the target logistics transportation data into a preset regression model for prediction to obtain an aging index of the logistics freight bill corresponding to the target logistics transportation data.

Optionally, in a third implementation manner of the first aspect of the present invention, the performing dimension analysis on the target logistics transportation data based on a preset business dimension model to obtain multidimensional logistics data includes: inputting the target logistics transportation data into a preset business dimension model, and splitting the target logistics transportation data through a plurality of preset business dimensions in the business dimension model to obtain business logistics data corresponding to the business dimensions; and carrying out fine grit splitting on the service logistics data based on a preset index dimension to obtain multi-dimensional logistics data.

Optionally, in a fourth implementation manner of the first aspect of the present invention, before determining a service dimension corresponding to the multidimensional logistics data, and verifying the aging index with a preset aging confidence interval according to the service dimension to obtain a verification result, the method further includes: acquiring historical logistics transportation data, and preprocessing the historical logistics transportation data to obtain aging parameters of the historical logistics transportation data; and determining an aging confidence interval corresponding to the service dimension based on the aging parameter.

Optionally, in a fifth implementation manner of the first aspect of the present invention, the determining, according to the check result, whether the transportation timeliness of the logistics waybill is abnormal includes: judging whether the aging index corresponding to the multi-dimensional logistics data is in the aging confidence interval or not according to the verification result; if so, determining that the distribution timeliness of the logistics waybill is normal; and if not, determining that the distribution timeliness of the logistics waybill is abnormal.

Optionally, in a sixth implementation manner of the first aspect of the present invention, after the determining, according to the check result, whether the transportation timeliness of the logistics waybill is abnormal or not, and outputting, according to the determination result, a transportation prompt message to a transportation unit corresponding to the logistics waybill, the method further includes: determining the type of the abnormal transportation state of the logistics waybill; determining the position data processed by the logistics waybill based on the type of the abnormal transportation state; determining a target transportation plan for transporting the physical waybill based on the distribution data and the location data of the physical waybill; and delivering the logistics waybill according to the delivery demand of the logistics waybill and the target transportation plan.

The second aspect of the present invention provides a device for monitoring timeout abnormality during logistics transportation, including: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring real-time logistics transportation data of a logistics distribution station and preprocessing the real-time logistics transportation data to obtain target logistics transportation data; the first determination module is used for predicting the target logistics transportation data and determining the timeliness index of the logistics waybill corresponding to the target logistics transportation data; the analysis module is used for carrying out dimension analysis on the target logistics transportation data based on a preset service dimension model to obtain multi-dimensional logistics data; the verification module is used for determining the service dimension corresponding to the multi-dimensional logistics data and verifying the aging index and a preset aging confidence interval according to the service dimension to obtain a verification result; and the judging module is used for judging whether the transportation timeliness of the logistics waybill is abnormal or not according to the checking result and outputting transportation prompt information to the transportation unit corresponding to the logistics waybill according to the judging result.

Optionally, in a first implementation manner of the second aspect of the present invention, the first obtaining module includes: the system comprises an acquisition unit, a monitoring unit and a control unit, wherein the acquisition unit is used for acquiring logistics scanning data, transportation vehicle in-out data and logistics log data in a logistics distribution network in real time based on a preset timing task; the storage unit is used for respectively storing the logistics scanning data, the transportation vehicle station entering and exiting data and the logistics log data into a preset message queue to obtain real-time logistics transportation data; the filtering unit is used for filtering the real-time logistics transportation data based on a preset filtering rule to obtain logistics field data which do not accord with the filtering rule; and the correction unit is used for carrying out data correction on the logistics field data to obtain target logistics transportation data.

Optionally, in a second implementation manner of the second aspect of the present invention, the first determining module is specifically configured to: and inputting the target logistics transportation data into a preset regression model for prediction to obtain an aging index of the logistics freight bill corresponding to the target logistics transportation data.

Optionally, in a third implementation manner of the second aspect of the present invention, the analysis module is specifically configured to: inputting the target logistics transportation data into a preset business dimension model, and splitting the target logistics transportation data through a plurality of preset business dimensions in the business dimension model to obtain business logistics data corresponding to the business dimensions; and carrying out fine grit splitting on the service logistics data based on a preset index dimension to obtain multi-dimensional logistics data.

Optionally, in a fourth implementation manner of the second aspect of the present invention, the apparatus for monitoring a logistics transportation timeout abnormality further includes: the second acquisition module is used for acquiring historical logistics transportation data, preprocessing the historical logistics transportation data and obtaining aging parameters of the historical logistics transportation data; and the second determining module is used for determining an aging confidence interval corresponding to the service dimension based on the aging parameter.

Optionally, in a fifth implementation manner of the second aspect of the present invention, the determining module is specifically configured to: judging whether the aging index corresponding to the multi-dimensional logistics data is in the aging confidence interval or not according to the verification result; if so, determining that the distribution timeliness of the logistics waybill is normal; if not, determining that the distribution timeliness of the logistics waybill is abnormal.

Optionally, in a sixth implementation manner of the second aspect of the present invention, the apparatus for monitoring a logistics transportation timeout abnormality further includes: the third determining module is used for determining the type of the abnormal transportation state of the logistics waybill; the fourth determination module is used for determining the position data processed by the logistics waybill based on the type of the abnormal transportation state; a fifth determining module, configured to determine a target transportation plan for transporting the physical waybill based on the distribution data and the location data of the physical waybill; and delivering the logistics waybill according to the delivery demand of the logistics waybill and the target transportation plan.

The third aspect of the present invention provides a device for monitoring timeout abnormality in logistics transportation, including: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;

the at least one processor calls the instructions in the memory to enable the logistics transportation timeout abnormality monitoring device to execute the steps of the logistics transportation timeout abnormality monitoring method.

A fourth aspect of the present invention provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to perform the steps of the above-mentioned logistics transportation timeout anomaly monitoring method.

According to the technical scheme provided by the invention, target logistics transportation data are obtained by preprocessing real-time logistics transportation data; predicting target logistics transportation data, and determining the timeliness index of the logistics waybill corresponding to the data; performing dimensionality analysis on the data based on the service dimensionality model to obtain multi-dimensional logistics data; determining the service dimension corresponding to the multi-dimensional logistics data, verifying the timeliness index and the timeliness confidence interval according to the service dimension, judging whether the transportation timeliness of the freight note is abnormal or not according to the verification result, and outputting prompt information to the corresponding transportation unit according to the judgment result. The scheme identifies real-time logistics transportation data to obtain the logistics freight note with the abnormal transportation state, and outputs transportation prompt information to the corresponding transportation unit according to the abnormal type and the delivery plan of the abnormal logistics freight note to guarantee delivery timeliness.

Drawings

Fig. 1 is a schematic diagram of a first embodiment of a method for monitoring timeout abnormality in logistics transportation according to the present invention;

fig. 2 is a schematic diagram of a second embodiment of the timeout anomaly monitoring method for logistics transportation provided by the present invention;

fig. 3 is a schematic diagram of a third embodiment of the timeout anomaly monitoring method for logistics transportation provided by the present invention;

fig. 4 is a schematic diagram of a fourth embodiment of the timeout anomaly monitoring method for logistics transportation according to the present invention;

fig. 5 is a schematic diagram of a fifth embodiment of the timeout anomaly monitoring method for logistics transportation according to the present invention;

fig. 6 is a schematic view of a first embodiment of the timeout anomaly monitoring device for logistics transportation provided by the invention;

fig. 7 is a schematic view of a second embodiment of the timeout anomaly monitoring device for logistics transportation provided by the invention;

fig. 8 is a schematic diagram of an embodiment of the timeout anomaly monitoring device for logistics transportation provided by the invention.

Detailed Description

The embodiment of the invention provides a method, a device, equipment and a storage medium for monitoring overtime abnormity of logistics transportation, and the technical scheme of the invention is that target logistics transportation data is obtained by preprocessing real-time logistics transportation data; predicting target logistics transportation data, and determining the timeliness index of the logistics waybill corresponding to the data; performing dimensionality analysis on the data based on the service dimensionality model to obtain multi-dimensional logistics data; determining the service dimension corresponding to the multi-dimensional logistics data, verifying the timeliness index and the timeliness confidence interval according to the service dimension, judging whether the transportation timeliness of the freight note is abnormal or not according to the verification result, and outputting prompt information to the corresponding transportation unit according to the judgment result. The scheme identifies real-time logistics transportation data to obtain the logistics freight note with the abnormal transportation state, and outputs transportation prompt information to the corresponding transportation unit according to the abnormal type and the delivery plan of the abnormal logistics freight note to guarantee delivery timeliness.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For convenience of understanding, a specific flow of an embodiment of the present invention is described below, and referring to fig. 1, a first embodiment of a method for monitoring timeout abnormality in logistics transportation according to an embodiment of the present invention includes:

101. acquiring real-time logistics transportation data of a logistics distribution site, and preprocessing the real-time logistics transportation data to obtain target logistics transportation data;

in this embodiment, the real-time logistics transportation data of the logistics distribution site is obtained, and the real-time logistics transportation data is preprocessed to obtain the target logistics transportation data. Specifically, the server performs data analysis and data filtering processing on real-time logistics transportation data including logistics scanning data, logistics vehicle in-and-out data, logistics video monitoring feature data and/or logistics log data in a message queue through a big data analysis engine flink to obtain target logistics transportation data.

Further, when the real-time logistics transportation data are logistics scanning data, the server analyzes the logistics scanning data reported in real time through the flink and identifies a plurality of complete statement segments; when the real-time logistics transportation data are logistics vehicle in-out data, the server analyzes the logistics vehicle in-out data through flink to obtain vehicle position information and vehicle transportation information; and when the real-time logistics transportation data are logistics video monitoring characteristic data, the server deletes the same video characteristic data through the flink convection video monitoring characteristic data to obtain a plurality of video data.

102. Predicting the target logistics transportation data, and determining the timeliness index of the logistics waybill corresponding to the target logistics transportation data;

in this embodiment, the target logistics transportation data is predicted, and the timeliness index of the logistics waybill corresponding to the target logistics transportation data is determined. In particular, a business dimension includes, but is not limited to, one or more of a full route, a trunk route, and a branch route. The full line route is from the collecting node (network point) to the signing node (network point). A trunk route is a line from an originating distribution node (mesh point) to a destination distribution node (mesh point). The branch routes include a route from the source node to the originating distribution node and/or a route from the destination distribution node to the sign-on node. Therefore, aggregation of the aging parameters of the service dimension can be achieved.

Further, in some implementation scenarios, the predicted aging parameters of the logistics waybills in each transportation may also be aggregated according to the logistics provider. Therefore, the aggregation of the aging parameters of the service dimension can be realized according to the logistics suppliers and the logistics freight notes of different logistics suppliers at the aggregation part, and then according to the lines of the logistics suppliers. Therefore, the invention can be suitable for the aging monitoring of not only a single logistics platform (logistics provider) but also a plurality of logistics platforms (logistics providers).

103. Performing dimension analysis on target logistics transportation data based on a preset service dimension model to obtain multi-dimensional logistics data;

in this embodiment, dimension analysis is performed on the target logistics transportation data based on a preset business dimension model, so as to obtain multi-dimensional logistics data. Specifically, the preset service dimension model is a pre-trained model for performing real-time streaming processing on the target logistics transportation data, and scalable, high-throughput and fault-tolerant streaming processing of the real-time logistics transportation data can be realized. For example, the preset business dimension model may be a fast computation engine spark model, or may be a real-time computation framework spark timing model, and is not limited herein.

Further, the server acquires a sample data set, and divides the sample data set into a training data set and a testing data set according to a preset proportion, wherein the preset proportion can be 6:4 or 5:5, and the specific proportion is not limited herein; the server performs model training on a preset initial model (for example, spark initial model) based on the training data set to obtain a trained model (for example, trained spark model); and the server performs model test on the trained model according to the test data set to obtain a test result, and sets the trained model as a preset service dimension model when the test result is that the test is passed. Specifically, the server determines the accuracy of the trained model according to the test result; if the accuracy of the trained model is greater than or equal to the preset accuracy threshold, the server determines that the test result is that the test is passed; and if the accuracy of the trained model is smaller than the preset accuracy threshold, the server determines that the test result is that the test fails. For example, the preset accuracy threshold is 0.935 (or 93.5%), if the accuracy of the trained model is 0.944, the server determines that the test result is that the test is passed, if the accuracy of the trained model is 0.832, the server determines that the test result is that the test is not passed, the server extracts the test data which fails the test from the test data set, updates the test data which fails the test into the training data set to obtain an updated training data set, and the server performs iterative optimization on the trained model through the updated training data set to obtain a finally trained model, and sets the finally trained model as a preset service dimension model.

104. Determining a service dimension corresponding to the multi-dimensional logistics data, and verifying the aging index and a preset aging confidence interval according to the service dimension to obtain a verification result;

in this embodiment, the service dimension corresponding to the multi-dimensional logistics data is determined, and the aging index and the preset aging confidence interval are verified according to the service dimension to obtain a verification result. Specifically, since the aging confidence interval is calculated based on the aging parameter of the historical logistics data, the normal and non-abnormal aging interval indicated in the historical logistics data can be represented. And according to the comparison between the aging parameters of the aggregated service dimensions and the aging confidence intervals, the abnormity of the line can be judged.

Furthermore, by means of abnormity judgment of the line of the logistics order in transportation, the situation that the logistics transportation order passing through the line is likely to have abnormal aging in the transportation process can be predicted, so that the line is replaced or a logistics company is replaced in advance, the logistics transportation aging is guaranteed to be normal, the logistics transportation efficiency is improved, and the logistics experience of a user is improved.

105. And judging whether the transportation timeliness of the logistics waybill is abnormal or not according to the verification result, and outputting transportation prompt information to the transportation unit corresponding to the logistics waybill according to the judgment result.

In this embodiment, whether the transportation timeliness of the logistics waybill is abnormal or not is judged according to the check result, and transportation prompt information is output to the transportation unit corresponding to the logistics waybill according to the judgment result. In a specific application scenario, the aging of a single logistics transportation order is monitored and abnormal judgment is performed, so that in the embodiment, an aging execution interval can be reused, and thus the aging abnormal judgment of the single logistics transportation order and the aging abnormal judgment of a line are realized. Further, in this embodiment, the judgment of the transportation aging abnormality of the single logistics waybill may be performed before, after or synchronously with the judgment of the line abnormality, and the present invention is not particularly limited.

In the embodiment of the invention, target logistics transportation data are obtained by preprocessing the real-time logistics transportation data; predicting target logistics transportation data, and determining the timeliness index of the logistics waybill corresponding to the data; performing dimensionality analysis on the data based on the service dimensionality model to obtain multi-dimensional logistics data; determining the service dimension corresponding to the multi-dimensional logistics data, verifying the timeliness index and the timeliness confidence interval according to the service dimension, judging whether the transportation timeliness of the freight note is abnormal or not according to the verification result, and outputting prompt information to the corresponding transportation unit according to the judgment result. The scheme identifies real-time logistics transportation data to obtain the logistics freight note with the abnormal transportation state, and outputs transportation prompt information to the corresponding transportation unit according to the abnormal type and the delivery plan of the abnormal logistics freight note to guarantee delivery timeliness.

Referring to fig. 2, a second embodiment of the method for monitoring timeout anomaly in logistics transportation according to the embodiment of the present invention includes:

201. collecting logistics scanning data, transportation vehicle in-out data and logistics log data in a logistics distribution network in real time based on a preset timing task;

in this embodiment, the real-time logistics transportation data in the logistics distribution network is recorded in real time for the logistics in and out, where the real-time logistics transportation data includes logistics scanning data, transportation vehicle in and out data, and logistics log data.

202. Respectively storing logistics scanning data, transport vehicle in-and-out-of-station data and logistics log data into a preset message queue to obtain real-time logistics transport data;

in this embodiment, the logistics scan data, the transportation vehicle in-and-out data, and the logistics log data are stored in the preset message queue, respectively. Specifically, the real-time logistics transportation data recorded in real time by the logistics entry and exit station is used for providing basic data such as express company scanning operation data, vehicle entry and exit station recording data, vehicle Global Positioning System (GPS) data, monitoring video stream data and organizational structure employee information. The real-time logistics transportation data comprises logistics scanning data, logistics vehicle in-and-out data, logistics video monitoring characteristic data and logistics log data, and the logistics scanning data, the logistics vehicle in-and-out data, the logistics video monitoring characteristic data and the logistics log data are all unstructured data type logistics data.

Further, the server receives logistics scanning data and logistics vehicle in-and-out-of-station data which are reported by the terminal in real time, wherein the logistics scanning data comprise logistics order data and logistics distribution data, and the logistics vehicle in-and-out-of-station data comprise logistics vehicle position data, electronic wagon balance weighing data and logistics vehicle sign-in data; the method comprises the steps that a server collects high-definition video streams (namely, monitoring video stream data) in a polling mode through a preset video collecting interface according to network connection addresses and network ports corresponding to video monitoring, and captures video data snapshots and extracts video features of the high-definition video streams in sequence to obtain logistics video monitoring feature data; the server regularly acquires binary log files binlog of various databases, and carries out structural analysis on the binlog to obtain logistics log data. And the server also respectively clears abnormal data in a preset data source in the process of collecting the real-time logistics transportation data. It should be noted that the enqueuing and dequeuing speeds of the message queue (e.g., kaffka) can reach millisecond level, and the message queue buffers the real-time logistics transportation data during the peak period of the logistics data, thereby improving the acquisition and processing efficiency of the logistics data.

203. Filtering the real-time logistics transportation data based on a preset filtering rule to obtain logistics field data which do not accord with the filtering rule;

in this embodiment, the real-time logistics transportation data is filtered based on the preset filtering rule, and the logistics field data which does not conform to the filtering rule is obtained.

Specifically, real-time logistics transportation data including logistics scanning data, logistics vehicle in-and-out data, logistics video monitoring characteristic data and/or logistics log data in a message queue are subjected to data analysis and data filtering processing through a big data analysis engine flink, and target logistics transportation data are obtained.

204. Carrying out data correction on the logistics field data to obtain target logistics transportation data;

in this embodiment, data correction is performed on the logistics field data to obtain target logistics transportation data. Specifically, when the real-time logistics transportation data are logistics scanning data, the server analyzes the logistics scanning data reported in real time through the flink and identifies a plurality of complete statement segments; when the real-time logistics transportation data are logistics vehicle in-out data, the server performs data analysis on the logistics vehicle in-out data through flink to obtain vehicle position information and vehicle transportation information; when the real-time logistics transportation data are logistics video monitoring characteristic data, the server deletes the same video characteristic data through the flink convection video monitoring characteristic data to obtain a plurality of video data; when the real-time logistics transportation data IS logistics log data, the server extracts corresponding IS object notation (JSON) characters from a binary log file binlog (that IS, logistics log data) through a flink according to preset operation types, and extracts target operation data from the JSON characters, wherein the preset operation types comprise a writing type, a modification type and a deletion type.

Further, the server can also collect slowly-changing dimension data at regular time. Then, the server performs data filtering and data correction processing on the complete statement fragment, the vehicle position information, the vehicle transportation information, the plurality of video data and the target operation data to obtain target logistics transportation data, and stores the target logistics transportation data into a distributed non-relational database pika.

205. Predicting the target logistics transportation data, and determining the timeliness index of the logistics waybill corresponding to the target logistics transportation data;

206. performing dimension analysis on the target logistics transportation data based on a preset service dimension model to obtain multi-dimensional logistics data;

207. determining a service dimension corresponding to the multi-dimensional logistics data, and verifying the aging index and a preset aging confidence interval according to the service dimension to obtain a verification result;

208. and judging whether the transportation timeliness of the logistics waybill is abnormal or not according to the verification result, and outputting transportation prompt information to the transportation unit corresponding to the logistics waybill according to the judgment result.

The steps 205-208 in this embodiment are similar to the steps 102-105 in the first embodiment, and are not described herein again.

Referring to fig. 3, a third embodiment of the method for monitoring timeout anomaly in logistics transportation according to the embodiment of the present invention includes:

301. acquiring real-time logistics transportation data of a logistics distribution site, and preprocessing the real-time logistics transportation data to obtain target logistics transportation data;

302. inputting the target logistics transportation data into a preset regression model for prediction to obtain an aging index of a logistics freight bill corresponding to the target logistics transportation data;

in this embodiment, the target logistics transportation data is input into the preset regression model for prediction, and the timeliness index of the logistics waybill corresponding to the target logistics transportation data is obtained. Specifically, the regression model may be a XGBoost algorithm (lifting tree extensible machine learning system) -based regression model for predicting the express delivery timeliness. The aging prediction algorithm may employ any machine learning model or combination of models. Wherein different logistics data can be agreed upon according to different predictive algorithms. For example, some age prediction models only require a delivery city and an addressee city; some aging prediction models require delivery cities, receiving cities and current logistics trajectory information.

In this embodiment, the regression model is a predictive modeling technique that studies the relationship between the dependent variable (target) and the independent variable (predictor). This technique is commonly used for predictive analysis, time series modeling, and discovering causal relationships between variables. For example, the relationship between the driver's reckless driving and the number of road traffic accidents. In particular, the regression model (regression model) is a mathematical model that quantitatively describes statistical relationships. A mathematical model such as multiple linear regression can be expressed as y ═ β 0+ β 1 × x + ∈ i, where β 0, β 1, …, β p are p +1 parameters to be estimated, ∈ i are random variables independent of each other and obeying the same normal distribution N (0, σ 2), and y is a random variable; x can be a random variable or a non-random variable, and beta i is called a regression coefficient and characterizes the degree of influence of independent variables on dependent variables.

303. Performing dimension analysis on target logistics transportation data based on a preset service dimension model to obtain multi-dimensional logistics data;

304. acquiring historical logistics transportation data, and preprocessing the historical logistics transportation data to obtain aging parameters of the historical logistics transportation data;

in this embodiment, historical logistics transportation data is obtained, and the historical logistics transportation data is preprocessed to obtain aging parameters of the historical logistics transportation data. In particular, a traffic dimension includes, but is not limited to, one or more of a full route, a trunk route, and a branch route for all traffic. The full-line route is a full-line route from a collecting node (network point) to a signing node (network point). A trunk route is a line from an originating distribution node (mesh point) to a destination distribution node (mesh point). The branch routes include a route from the source node to the originating distribution node and/or a route from the destination distribution node to the sign-on node. Therefore, the aggregation of the aging parameters of the service dimension can be realized.

Further, in some specific service scenarios, the predicted aging parameters of the logistics waybills in each transportation can be aggregated according to the logistics providers. Therefore, the aggregation of the aging parameters of the service dimension can be realized according to the logistics suppliers and the logistics freight notes of different logistics suppliers at the aggregation part and the lines of the logistics suppliers.

305. Determining an aging confidence interval corresponding to the service dimension based on the aging parameter;

in this embodiment, an aging confidence interval corresponding to the service dimension is determined based on the aging parameter. Specifically, since the aging confidence interval is calculated based on the aging parameter of the historical logistics data, it is possible to represent a normal, non-abnormal aging interval indicated in the historical logistics data. And according to the comparison between the aging parameters of the aggregated service dimensions and the aging confidence interval, the abnormity of the line in the logistics transportation process can be judged.

306. Determining the service dimension corresponding to the multi-dimensional logistics data, and verifying the aging index and a preset aging confidence interval according to the service dimension to obtain a verification result;

307. and judging whether the transportation timeliness of the logistics waybill is abnormal or not according to the verification result, and outputting transportation prompt information to the transportation unit corresponding to the logistics waybill according to the judgment result.

The

steps

301, 303, and 306-307 in this embodiment are similar to the

steps

101, 103, and 104-105 in the first embodiment, and are not described herein again.

Referring to fig. 4, a fourth embodiment of the method for monitoring timeout anomaly in logistics transportation according to the embodiment of the present invention includes:

401. acquiring real-time logistics transportation data of a logistics distribution site, and preprocessing the real-time logistics transportation data to obtain target logistics transportation data;

402. predicting the target logistics transportation data, and determining the timeliness index of the logistics waybill corresponding to the target logistics transportation data;

403. inputting target logistics transportation data into a preset business dimension model, and splitting the target logistics transportation data through a plurality of preset business dimensions in the business dimension model to obtain business logistics data corresponding to the plurality of business dimensions;

in this embodiment, the target logistics transportation data is input into the preset business dimension model, and the target logistics transportation data is split through a plurality of preset business dimensions in the business dimension model, so as to obtain business logistics data corresponding to the plurality of business dimensions. Specifically, the server extracts target logistics transportation data from pika; the method comprises the steps that a server analyzes and processes theme, dimensionality and indexes of target logistics transportation data according to a preset data index system through a preset service dimensionality model (such as a flink-sink model) to obtain multi-dimensional logistics data, wherein the multi-dimensional logistics data are multi-dimensional index data of a structured data type, and the multi-dimensional logistics data are multi-dimensional index data of the structured data type; the server stores the multi-dimensional logistics data into a preset detail data table, and the preset detail data table corresponds to a preset theme.

It should be noted that the pre-trained real-time stream data processing model is a preset service dimension model. The server constructs a preset data index system according to a preset service theme, a preset service dimension and a preset service index, and stores the preset data index system into the mysql mirror image library so as to realize the timeliness and consistency of real-time processing of the logistics data. And an association mapping relation exists among the preset service theme, the preset service dimension and the preset service index.

404. Performing fine-grained splitting on the business logistics data based on preset index dimensions to obtain multi-dimensional logistics data;

in this embodiment, the service logistics data is subjected to fine-grained splitting based on the preset index dimension, so as to obtain multi-dimensional logistics data. Wherein the fine granularity is a computer programming term. The fine-grained model is a popular way to subdivide objects in the business model, so that a more scientific and reasonable object model is obtained, and a plurality of objects are visually divided. What is called fine-grained partitioning is object-oriented partitioning on the pojo class, not on table partitions such as: in the three-layer structure, only pure database operation is carried out in the persistence layer.

Further, the server splits the target logistics data according to a plurality of preset themes through a preset service dimension model to obtain a plurality of service logistics data, each service logistics data has a corresponding theme tag, for example, logistics data corresponding to a logistics basic data theme has a basic data tag, logistics data corresponding to a vehicle track theme has a vehicle track tag, a logistics monitoring theme has a logistics monitoring tag, and logistics data corresponding to a logistics distribution theme has a logistics distribution tag; the server divides the multiple service logistics data into fine grit according to preset index dimensions to obtain multi-dimensional logistics data, the server stores the multi-dimensional logistics data into detail data tables corresponding to all subjects, and the multi-dimensional logistics data are structured data type multi-dimensional index data. The preset index dimension is used for indicating dimension information and index information which are configured in advance according to various themes. Furthermore, the server performs fine-grained division on the multiple service logistics data according to the dimension information and the index information to obtain the multi-dimensional logistics data, and the content of the detail data table is used for indicating the target service or the sub-service classification of the target service.

405. Determining the service dimension corresponding to the multi-dimensional logistics data, and verifying the aging index and a preset aging confidence interval according to the service dimension to obtain a verification result;

406. and judging whether the transportation timeliness of the logistics waybill is abnormal or not according to the verification result, and outputting transportation prompt information to the transportation unit corresponding to the logistics waybill according to the judgment result.

The steps 401-.

Referring to fig. 5, a fifth embodiment of the method for monitoring timeout anomaly in logistics transportation according to the embodiment of the present invention includes:

501. acquiring real-time logistics transportation data of a logistics distribution site, and preprocessing the real-time logistics transportation data to obtain target logistics transportation data;

502. predicting the target logistics transportation data, and determining the timeliness index of the logistics waybill corresponding to the target logistics transportation data;

503. performing dimension analysis on target logistics transportation data based on a preset service dimension model to obtain multi-dimensional logistics data;

504. determining a service dimension corresponding to the multi-dimensional logistics data, and verifying the aging index and a preset aging confidence interval according to the service dimension to obtain a verification result;

505. judging whether the aging index corresponding to the multi-dimensional logistics data is in an aging confidence interval or not according to the check result;

in this embodiment, whether the aging index corresponding to the multidimensional logistics data is within the aging confidence interval is judged according to the check result. Specifically, since the aging confidence interval is calculated based on the aging parameter of the historical logistics data, it is possible to represent a normal, non-abnormal aging interval indicated in the historical logistics data. And judging the abnormity of the line according to the comparison of the aging parameters of the aggregated line dimensions and the aging confidence interval.

506. If so, determining that the distribution timeliness of the logistics waybills is normal;

in this embodiment, if the timeliness index corresponding to the multidimensional logistics data is within the timeliness confidence interval, it is determined that the distribution timeliness of the logistics waybill is normal. The aging confidence interval is calculated based on aging parameters of the historical logistics data, and thus can represent a normal, non-abnormal aging interval indicated in the historical logistics data. And according to the comparison between the aging parameters of the aggregated line dimensions and the aging confidence interval, judging that the distribution aging of the logistics waybill is abnormal.

507. If not, determining that the distribution timeliness of the logistics waybill is abnormal;

in this embodiment, if the aging index corresponding to the multidimensional logistics data is not within the aging confidence interval, the abnormality notification information may be sent to the logistics management terminal. The logistics management terminal comprises but is not limited to terminal equipment of logistics suppliers' aging managers, terminal equipment of logistics aging managers of e-commerce platforms, terminal equipment of senders and terminal equipment of receivers. The sent abnormal notification message can be a telephone message, a short message, a push message, a message of a working system which is developed by each platform, and the like.

508. Determining the type of the abnormal transportation state of the logistics waybill;

in this embodiment, the type of the abnormal transportation state of the logistics waybill is determined. Wherein, the types of abnormal transportation states of the logistics waybill can include but are not limited to: goods are abnormal, transport vehicles are abnormal, transport personnel are abnormal, a transport road is abnormal, and the like.

509. Determining position data processed by the logistics waybill based on the type of the abnormal transportation state;

in this embodiment, the location data processed by the logistics waybill is determined based on the type of the transportation abnormal state. Specifically, the distribution equipment of the abnormal logistics waybill determines the position information for processing the order to be distributed based on the type of the abnormal distribution state; wherein the location information may refer to location information where a service point capable of reprocessing the order to be delivered is located.

510. Determining a target transportation plan for transporting the physical freight bill based on the distribution data and the position data of the logistics freight bill;

in this embodiment, the target transportation plan for transporting the physical waybill is determined based on the distribution data and the location data of the physical waybill. The distribution equipment of the abnormal logistics waybill determines a distribution plan set to be selected based on the distribution information and the position information; for example, the number of delivery plans in the candidate delivery plan set may be one, two, or more. The distribution equipment of the abnormal logistics waybill determines a distribution destination of an order to be distributed and/or a distribution plan of position information for processing the order to be distributed through a path based on the distribution information and the position information, integrates or sequences the distribution plans, and forms a distribution plan set to be selected.

In an embodiment, the distribution equipment of the abnormal logistics waybill may analyze the distribution information to obtain a distribution position and a fulfillment time window, where the fulfillment time window may refer to a distribution time range corresponding to the to-be-distributed order, and further determine the to-be-selected distribution plan set based on the fulfillment time window, the distribution position, and the position information for processing the to-be-distributed order.

The distribution equipment of the abnormal logistics freight note determines a fulfillment time window, namely a distribution time range corresponding to the order to be distributed, determines a distribution plan of position information for processing the order to be distributed by the distribution destination and/or the route of the order to be distributed, and obtains a distribution plan set to be selected based on the distribution plan

511. And delivering the logistics freight bill according to the delivery requirement of the logistics freight bill and the target transportation plan.

In this embodiment, the logistics waybill is delivered according to the delivery demand and the target transportation plan of the logistics waybill. Specifically, the distribution equipment of the abnormal logistics freight note determines a target distribution plan which is used for distributing the distribution capacity required by the order to be distributed and meets the preset conditions from a distribution plan set to be selected; the number of the target delivery plans may be one, or two or more. The delivery capacity required for delivering the orders to be delivered can be the delivery capacity required for additionally delivering the orders to be delivered on the premise that the delivery plan to be selected in the delivery plan set to be selected is normally executed; the distribution capacity refers to mechanical equipment and personnel allocation in transportation in the distribution process.

The distribution equipment of the abnormal logistics freight note can calculate the distribution plans in the distribution plan set to be selected based on the ant colony algorithm so as to determine the target distribution plan which is required by the distribution of the orders to be distributed and meets the preset conditions.

The ant colony algorithm is a probability algorithm used for searching for an optimized path; the basic idea for solving the optimization problem is as follows: representing a feasible solution of the problem to be optimized by using the walking paths of the ants, wherein all paths of the whole ant colony form a solution space of the problem to be optimized; the pheromone released by the ants with shorter paths is more, the concentration of the pheromone accumulated on the shorter paths is gradually increased along with the advance of time, and the number of the ants selecting the paths is increased more and more; finally, the whole ant can be concentrated on the optimal path under the action of positive feedback, and the corresponding optimal solution of the problem to be optimized is obtained.

The steps 501-504 in the present embodiment are similar to the steps 101-104 in the first embodiment, and are not described herein again.

In the embodiment of the invention, the target logistics transportation data is obtained by preprocessing the real-time logistics transportation data; predicting the target logistics transportation data, and determining the timeliness index of the logistics waybill corresponding to the data; performing dimensionality analysis on the data based on the service dimensionality model to obtain multi-dimensional logistics data; determining the service dimension corresponding to the multi-dimensional logistics data, verifying the timeliness index and the timeliness confidence interval according to the service dimension, judging whether the transportation timeliness of the freight note is abnormal or not according to the verification result, and outputting prompt information to the corresponding transportation unit according to the judgment result. The scheme identifies real-time logistics transportation data to obtain the logistics freight note with the abnormal transportation state, and outputs transportation prompt information to the corresponding transportation unit according to the abnormal type and the delivery plan of the abnormal logistics freight note to guarantee delivery timeliness.

The above description is made on the method for monitoring timeout anomaly in logistics transportation according to the embodiment of the present invention, and referring to fig. 6, the following description is made on a device for monitoring timeout anomaly in logistics transportation according to the embodiment of the present invention, where a first embodiment of the device for monitoring timeout anomaly in logistics transportation according to the embodiment of the present invention includes:

the system comprises a first acquisition module 601, a first storage module and a second storage module, wherein the first acquisition module 601 is used for acquiring real-time logistics transportation data of a logistics distribution station and preprocessing the real-time logistics transportation data to obtain target logistics transportation data;

a first determining module 602, configured to predict the target logistics transportation data, and determine an aging index of a logistics waybill corresponding to the target logistics transportation data;

the analysis module 603 is configured to perform dimension analysis on the target logistics transportation data based on a preset service dimension model to obtain multidimensional logistics data;

the verification module 604 is configured to determine a service dimension corresponding to the multidimensional logistics data, and verify the aging index and a preset aging confidence interval according to the service dimension to obtain a verification result;

and the judging module 605 is configured to judge whether the transportation timeliness of the logistics waybill is abnormal according to the check result, and output transportation prompt information to the transportation unit corresponding to the logistics waybill according to the judgment result.

Referring to fig. 7, a second embodiment of the timeout anomaly monitoring device for logistics transportation according to the embodiment of the present invention specifically includes:

In this embodiment, the first obtaining module 601 includes:

the acquisition unit 6011 is configured to acquire, in real time, logistics scan data, transportation vehicle in-and-out-of-station data, and logistics log data in a logistics distribution network based on a preset timing task;

a storage unit 6012, configured to store the logistics scan data, the transportation vehicle inbound and outbound data, and the logistics log data in a preset message queue, respectively, to obtain real-time logistics transportation data;

a filtering unit 6013, configured to filter the real-time logistics transportation data based on a preset filtering rule, so as to obtain logistics field data that does not meet the filtering rule;

and a correcting unit 6014, configured to perform data correction on the logistics field data to obtain target logistics transportation data.

In this embodiment, the first determining module 602 is specifically configured to:

and inputting the target logistics transportation data into a preset regression model for prediction to obtain an aging index of the logistics freight bill corresponding to the target logistics transportation data.

In this embodiment, the analysis module 603 is specifically configured to:

inputting the target logistics transportation data into a preset business dimension model, and splitting the target logistics transportation data through a plurality of preset business dimensions in the business dimension model to obtain business logistics data corresponding to the business dimensions;

and carrying out fine-grained splitting on the service logistics data based on preset index dimensionality to obtain multi-dimensional logistics data.

In this embodiment, the monitoring device for overtime anomaly in logistics transportation further includes:

a second obtaining module 606, configured to obtain historical logistics transportation data, and preprocess the historical logistics transportation data to obtain aging parameters of the historical logistics transportation data;

a second determining module 607, configured to determine an aging confidence interval of the corresponding service dimension based on the aging parameter.

In this embodiment, the determining module 605 is specifically configured to:

judging whether the aging index corresponding to the multi-dimensional logistics data is in the aging confidence interval or not according to the verification result;

if so, determining that the distribution timeliness of the logistics waybill is normal;

and if not, determining that the distribution timeliness of the logistics waybill is abnormal.

a third determining module 608, configured to determine a type of the transportation abnormal state of the logistics waybill;

a fourth determining module 609, configured to determine, based on the type of the abnormal transportation state, location data processed by the logistics waybill;

a fifth determining module 610, configured to determine a target transportation plan for transporting the physical waybill based on the distribution data of the physical waybill and the location data; and delivering the logistics waybill according to the delivery demand of the logistics waybill and the target transportation plan.

Fig. 6 and fig. 7 describe the logistics transportation timeout anomaly monitoring apparatus in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the logistics transportation timeout anomaly monitoring apparatus in the embodiment of the present invention is described in detail from the perspective of hardware processing.

Fig. 8 is a schematic structural diagram of a logistics transportation timeout abnormality monitoring apparatus according to an embodiment of the present invention, where the logistics transportation timeout abnormality monitoring apparatus 800 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 810 (e.g., one or more processors) and a memory 820, and one or more storage media 830 (e.g., one or more mass storage devices) storing an application 833 or data 832. Memory 820 and storage medium 830 may be, among other things, transient or persistent storage. The program stored in the storage medium 830 may include one or more modules (not shown), each of which may include a series of instruction operations for the logistics transportation timeout abnormality monitoring apparatus 800. Further, the processor 810 may be configured to communicate with the storage medium 830, and execute a series of instruction operations in the storage medium 830 on the logistics transportation timeout abnormality monitoring apparatus 800, so as to implement the steps of the logistics transportation timeout abnormality monitoring method provided by the above-mentioned method embodiments.

The logistics transportation timeout anomaly monitoring device 800 may also include one or more power supplies 840, one or more wired or wireless network interfaces 850, one or more input-output interfaces 860, and/or one or more operating systems 831, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the configuration of the logistics transportation timeout anomaly monitoring device shown in fig. 8 does not constitute a limitation of the logistics transportation timeout anomaly monitoring device provided herein, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.

The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and may also be a volatile computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed on a computer, the instructions cause the computer to execute the steps of the above logistics transportation timeout anomaly monitoring method.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a portable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A logistics transportation overtime abnormity monitoring method is characterized by comprising the following steps:

the method comprises the steps of obtaining real-time logistics transportation data of a logistics distribution station, and preprocessing the real-time logistics transportation data to obtain target logistics transportation data;

predicting the target logistics transportation data, and determining the timeliness index of the logistics waybill corresponding to the target logistics transportation data;

performing dimension analysis on the target logistics transportation data based on a preset service dimension model to obtain multi-dimensional logistics data;

determining a service dimension corresponding to the multi-dimensional logistics data, and verifying the aging index and a preset aging confidence interval according to the service dimension to obtain a verification result;

and judging whether the transportation timeliness of the logistics waybill is abnormal or not according to the checking result, and outputting transportation prompt information to the corresponding transportation unit of the logistics waybill according to the judging result.

2. The method for monitoring timeout anomaly of logistics transportation according to claim 1, wherein the step of obtaining real-time logistics transportation data of a logistics distribution site and preprocessing the real-time logistics transportation data to obtain target logistics transportation data comprises:

collecting logistics scanning data, transportation vehicle in-out data and logistics log data in a logistics distribution network in real time based on a preset timing task;

respectively storing the logistics scanning data, the transportation vehicle in-and-out-of-station data and the logistics log data into a preset message queue to obtain real-time logistics transportation data;

filtering the real-time logistics transportation data based on a preset filtering rule to obtain logistics field data which do not accord with the filtering rule;

and performing data correction on the logistics field data to obtain target logistics transportation data.

3. The method for monitoring timeout anomaly of logistics transportation according to claim 1, wherein said predicting the target logistics transportation data and determining the timeliness index of the logistics waybill corresponding to the target logistics transportation data comprises:

4. The method for monitoring timeout anomaly of logistics transportation according to claim 1, wherein the performing dimension analysis on the target logistics transportation data based on a preset business dimension model to obtain multi-dimensional logistics data comprises:

5. The method for monitoring timeout abnormality in logistics transportation according to any one of claims 1 to 4, wherein before the determining a service dimension corresponding to the multidimensional logistics data and verifying the aging index with a preset aging confidence interval according to the service dimension to obtain a verification result, the method further comprises:

acquiring historical logistics transportation data, and preprocessing the historical logistics transportation data to obtain aging parameters of the historical logistics transportation data;

and determining an aging confidence interval corresponding to the service dimension based on the aging parameter.

6. The method for monitoring overtime abnormal logistics transportation according to claim 1, wherein the step of judging whether the transportation timeliness of the logistics waybill is abnormal or not according to the verification result comprises the steps of:

7. The method for monitoring overtime abnormal transportation of logistics, according to claim 1, wherein after said determining whether the transportation timeliness of the logistics waybill is abnormal according to the verification result, and outputting the transportation prompt information to the transportation unit corresponding to the logistics waybill according to the determination result, further comprising:

determining the type of the abnormal transportation state of the logistics waybill;

determining the position data processed by the logistics waybill based on the type of the abnormal transportation state;

determining a target transportation plan for transporting the physical waybill based on the distribution data and the location data of the physical waybill;

and delivering the logistics waybill according to the delivery demand of the logistics waybill and the target transportation plan.

8. A logistics transportation overtime anomaly monitoring device is characterized by comprising:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring real-time logistics transportation data of a logistics distribution station and preprocessing the real-time logistics transportation data to obtain target logistics transportation data;

the first determination module is used for predicting the target logistics transportation data and determining the timeliness index of the logistics waybill corresponding to the target logistics transportation data;

the analysis module is used for carrying out dimension analysis on the target logistics transportation data based on a preset service dimension model to obtain multi-dimensional logistics data;

the verification module is used for determining the service dimension corresponding to the multi-dimensional logistics data and verifying the aging index and a preset aging confidence interval according to the service dimension to obtain a verification result;

and the judging module is used for judging whether the transportation timeliness of the logistics waybill is abnormal or not according to the checking result and outputting transportation prompt information to the transportation unit corresponding to the logistics waybill according to the judging result.

9. A logistics transportation timeout abnormality monitoring apparatus, characterized in that the logistics transportation timeout abnormality monitoring apparatus comprises: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;

the at least one processor invokes the instructions in the memory to cause the logistics transportation timeout anomaly monitoring device to perform the steps of the logistics transportation timeout anomaly monitoring method of any one of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for monitoring logistics transportation timeout anomaly monitoring according to any one of claims 1-7.